ZeroShape: What We Can Conclude From This Strong Regression-Based Model

Table of Links Abstract and 1 Introduction 2. Related Work 3. Method and 3.1. Architecture 3.2. Loss and 3.3. Implementation Details 4. Data Curation 4.1. Training Dataset 4.2. Evaluation Benchmark 5. Experiments and 5.1. Metrics 5.2. Baselines 5.3. Comparison to SOTA Methods 5.4. Qualitative Results and 5.5. Ablation Study 6. Limitations and Discussion 7. Conclusion and References A. Additional Qualitative Comparison B. Inference on AI-generated Images C. Data Curation Details 7. Conclusion We present a strong regression-based model for zero-shot shape reconstruction. The core of our model is an intermediate representation of the 3D visible surface which facilitates effective explicit 3D geometric reasoning. We also curate a large real-world evaluation benchmark to test zeroshot shape reconstruction methods. Our benchmark pools data from three different real-world 3D datasets and has an order of magnitude larger scale than the test sets used by prior work. Tested on our benchmark, our model significantly outperforms other SOTA methods and achieves higher computational efficiency, despite being trained with much less 3D data. We hope our effort is a meaningful step towards building zero-shot generalizable 3D reconstruction models. Acknowledgement. This work was supported by NIH R01HD104624-01A1. References [1] Midjourney: https : / / www . midjourney . com / showcase/recent/. Accessed: May 5, 2023. 1, 3 [2] Panos Achlioptas, Olga Diamanti, Ioannis Mitliagkas, and Leonidas Guibas. Learning representations and generative models for 3d point clouds. In International conference on machine learning, pages 40–49. PMLR, 2018. 3 [3] Jean-Baptiste Alayrac, Jeff Donahue, Pauline Luc, Antoine Miech, Iain Barr, Yana Hasson, Karel Lenc, Arthur Mensch, Katherine Millican, Malcolm Reynolds, et al. Flamingo: a visual language model for few-shot learning. Advances in Neural Information Processing Systems, 35:23716–23736, 2022. 1 [4] Kalyan Vasudev Alwala, Abhinav Gupta, and Shubham Tulsiani. Pre-train, self-train, distill: A simple recipe for supersizing 3d reconstruction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 3773–3782, 2022. 7 [5] Jan Bechtold, Maxim Tatarchenko, Volker Fischer, and Thomas Brox. Fostering generalization in single-view 3d reconstruction by learning a hierarchy of local and global shape priors. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 15880– 15889, 2021. 2, 3 [6] Angel X Chang, Thomas Funkhouser, Leonidas Guibas, Pat Hanrahan, Qixing Huang, Zimo Li, Silvio Savarese, Manolis Savva, Shuran Song, Hao Su, et al. Shapenet: An information-rich 3d model repository. arXiv preprint arXiv:1512.03012, 2015. 5 [7] Rui Chen, Yongwei Chen, Ningxin Jiao, and Kui Jia. Fantasia3d: Disentangling geometry and appearance for highquality text-to-3d content creation. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023. 8 [8] Christopher B Choy, Danfei Xu, JunYoung Gwak, Kevin Chen, and Silvio Savarese. 3d-r2n2: A unified approach for single and multi-view 3d object reconstruction. In European conference on computer vision, pages 628–644. Springer, 2016. 3 [9] Matt Deitke, Dustin Schwenk, Jordi Salvador, Luca Weihs, Oscar Michel, Eli VanderBilt, Ludwig Schmidt, Kiana Ehsani, Aniruddha Kembhavi, and Ali Farhadi. Objaverse: A universe of annotated 3d objects. arXiv preprint arXiv:2212.08051, 2022. 2, 5 [10] Matt Deitke, Ruoshi Liu, Matthew Wallingford, Huong Ngo, Oscar Michel, Aditya Kusupati, Alan Fan, Christian Laforte, Vikram Voleti, Samir Yitzhak Gadre, et al. Objaverse-xl: A universe of 10m+ 3d objects. arXiv preprint arXiv:2307.05663, 2023. 2 [11] Congyue Deng, Chiyu Jiang, Charles R Qi, Xinchen Yan, Yin Zhou, Leonidas Guibas, Dragomir Anguelov, et al. Nerdi: Single-view nerf synthesis with languageguided diffusion as general image priors. arXiv preprint arXiv:2212.03267, 2022. 3, 8 [12] Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, et al. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929, 2020. 8 [13] Ainaz Eftekhar, Alexander Sax, Jitendra Malik, and Amir Zamir. Omnidata: A scalable pipeline for making multitask mid-level vision datasets from 3d scans. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 10786–10796, 2021. 5 [14] Haoqiang Fan, Hao Su, and Leonidas J Guibas. A point set generation network for 3d object reconstruction from a single image. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 605–613, 2017. 3 [15] Thibault Groueix, Matthew Fisher, Vladimir G. Kim, Bryan Russell, and Mathieu Aubry. AtlasNet: A Papier-Mach ˆ e Ap- ´ proach to Learning 3D Surface Generation. In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2018. 3, 6 [16] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016. 4 [17] Zexin He and Tengfei Wang. Openlrm: Open-source large reconstruction models. https://github.com/ 3DTopia/OpenLRM, 2023. 7 [18] Yicong Hong, Kai Zhang, Jiuxiang Gu, Sai Bi, Yang Zhou, Difan Liu, Feng Liu, Kalyan Sunkavalli, Trung Bui, and Hao Tan. Lrm: Large reconstruction model for single image to 3d. arXiv preprint arXiv:2311.04400, 2023. 7 [19] Zixuan Huang, Stefan Stojanov, Anh Thai, Varun Jampani, and James M Rehg. Planes vs. chairs: Category-guided 3d shape learning without any 3d cues. In European Conference on Computer Vision, pages 727–744. Springer, 2022. 5, 6 [20] Zixuan Huang, Varun Jampani, Anh Thai, Yuanzhen Li, Stefan Stojanov, and James M Rehg. Shapeclipper: Scalable 3d shape learning from single-view images via geometric and clip-based consistency. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023. 6 [21] Muhammad Zubair Irshad, Sergey Zakharov, Rares Ambrus, Thomas Kollar, Zsolt Kira, and Adrien Gaidon. Shapo: Implicit representations for multi-object shape appearance and pose optimization. 2022. 3 [22] Heewoo Jun and Alex Nichol. Shap-e: Generating conditional 3d implicit functions. arXiv preprint arXiv:2305.02463, 2023. 1, 3, 7 [23] Angjoo Kanazawa, Shubham Tulsiani, Alexei A Efros, and Jitendra Malik. Learning category-specific mesh reconstruction from image collections. In Proceedings of the European Conference on Computer Vision (ECCV), pages 371– 386, 2018. 3 [24] Jared Kaplan, Sam McCandlish, Tom Henighan, Tom B Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei. Scaling laws for neural language models. arXiv preprint arXiv:2001.08361, 2020. 8 [25] Diederik P Kingma and Jimmy Ba. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014. 5 [26] Alexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao, Chloe Rolland, Laura Gustafson, Tete Xiao, Spencer Whitehead, Alexander C. Berg, Wan-Yen Lo, Piotr Dollar, and ´ Ross Girshick. Segment anything. arXiv:2304.02643, 2023. 1 [27] Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597, 2023. 1 [28] Chen-Hsuan Lin, Chaoyang Wang, and Simon Lucey. Sdfsrn: Learning signed distance 3d object reconstruction from static images. arXiv preprint arXiv:2010.10505, 2020. 6 [29] Chen-Hsuan Lin, Jun Gao, Luming Tang, Towaki Takikawa, Xiaohui Zeng, Xun Huang, Karsten Kreis, Sanja Fidler, Ming-Yu Liu, and Tsung-Yi Lin. Magic3d: High-resolution text-to-3d content creation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 300–309, 2023. 8 [30] Minghua Liu, Chao Xu, Haian Jin, Linghao Chen, Zexiang Xu, Hao Su, et al. One-2-3-45: Any single image to 3d mesh in 45 seconds without per-shape optimization. arXiv preprint arXiv:2306.16928, 2023. 1, 2, 3, 5, 7 [31] Ruoshi Liu, Rundi Wu, Basile Van Hoorick, Pavel Tokmakov, Sergey Zakharov, and Carl Vondrick. Zero-1-to3: Zero-shot one image to 3d object. arXiv preprint arXiv:2303.11328, 2023. 1, 2, 3, 5, 7 [32] William E Lorensen and Harvey E Cline. Marching cubes: A high resolution 3d surface construction algorithm. ACM siggraph computer graphics, 21(4):163–169, 1987. 6, 7 [33] David Marr. Vision: A computational investigation into the human representation and processing of visual information. MIT press, 2010. 2, 3 [34] Luke Melas-Kyriazi, Christian Rupprecht, Iro Laina, and Andrea Vedaldi. Realfusion: 360 reconstruction of any object from a single image. In CVPR, 2023. 3, 8 [35] Lars Mescheder, Michael Oechsle, Michael Niemeyer, Sebastian Nowozin, and Andreas Geiger. Occupancy networks: Learning 3d reconstruction in function space. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4460–4470, 2019. 3 [36] Ben Mildenhall, Pratul P Srinivasan, Matthew Tancik, Jonathan T Barron, Ravi Ramamoorthi, and Ren Ng. Nerf: Representing scenes as neural radiance fields for view synthesis. In European Conference on Computer Vision, pages 405–421. Springer, 2020. 7 [37] Alex Nichol, Heewoo Jun, Prafulla Dhariwal, Pamela Mishkin, and Mark Chen. Point-e: A system for generating 3d point clouds from complex prompts. arXiv preprint arXiv:2212.08751, 2022. 1, 3, 7 [38] Maxime Oquab, Timothee Darcet, Th ´ eo Moutakanni, Huy ´ Vo, Marc Szafraniec, Vasil Khalidov, Pierre Fernandez, Daniel Haziza, Francisco Massa, Alaaeldin El-Nouby, et al. Dinov2: Learning robust visual features without supervision. arXiv preprint arXiv:2304.07193, 2023. 1 [39] Songyou Peng, Michael Niemeyer, Lars Mescheder, Marc Pollefeys, and Andreas Geiger. Convolutional occupancy networks. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part III 16, pages 523–540. Springer, 2020. 3 [40] Ben Poole, Ajay Jain, Jonathan T Barron, and Ben Mildenhall. Dreamfusion: Text-to-3d using 2d diffusion. arXiv preprint arXiv:2209.14988, 2022. 3, 8 [41] Blender Project. Blender, https://blender.org/. 5 [42] Lu Qi, Jason Kuen, Tiancheng Shen, Jiuxiang Gu, Wenbo Li, Weidong Guo, Jiaya Jia, Zhe Lin, and Ming-Hsuan Yang. High quality entity segmentation. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pages 4047–4056, 2023. 1 [43] Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning, pages 8748–8763. PMLR, 2021. 1 [44] Aditya Ramesh, Prafulla Dhariwal, Alex Nichol, Casey Chu, and Mark Chen. Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125, 1 (2):3, 2022. 3 [45] Rene Ranftl, Katrin Lasinger, David Hafner, Konrad ´ Schindler, and Vladlen Koltun. Towards robust monocular depth estimation: Mixing datasets for zero-shot cross-dataset transfer. IEEE transactions on pattern analysis and machine intelligence, 44(3):1623–1637, 2020. 4 [46] Rene Ranftl, Alexey Bochkovskiy, and Vladlen Koltun. Vi- ´ sion transformers for dense prediction. ArXiv preprint, 2021. 4 [47] Jeremy Reizenstein, Roman Shapovalov, Philipp Henzler, Luca Sbordone, Patrick Labatut, and David Novotny. Common objects in 3d: Large-scale learning and evaluation of real-life 3d category reconstruction. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 10901–10911, 2021. 7 [48] Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Bjorn Ommer. High-resolution image syn- ¨ thesis with latent diffusion models, 2021. 1, 3, 8 [49] Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily L Denton, Kamyar Ghasemipour, Raphael Gontijo Lopes, Burcu Karagol Ayan, Tim Salimans, et al. Photorealistic text-to-image diffusion models with deep language understanding. Advances in Neural Information Processing Systems, 35:36479–36494, 2022. 1, 3 [50] Daeyun Shin, Charless C Fowlkes, and Derek Hoiem. Pixels, voxels, and views: A study of shape representations for single view 3d object shape prediction. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 3061–3069, 2018. 2, 3 [51] Rakesh Shrestha, Siqi Hu, Minghao Gou, Ziyuan Liu, and Ping Tan. A real world dataset for multi-view 3d reconstruction. In Computer Vision–ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part VIII, pages 56–73. Springer, 2022. 1, 2, 5, 6 [52] Xingyuan Sun, Jiajun Wu, Xiuming Zhang, Zhoutong Zhang, Chengkai Zhang, Tianfan Xue, Joshua B Tenenbaum, and William T Freeman. Pix3d: Dataset and methods for single-image 3d shape modeling. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2974–2983, 2018. 1, 2, 5 [53] Junshu Tang, Tengfei Wang, Bo Zhang, Ting Zhang, Ran Yi, Lizhuang Ma, and Dong Chen. Make-it-3d: High-fidelity 3d creation from a single image with diffusion prior. arXiv preprint arXiv:2303.14184, 2023. 3 [54] Maxim Tatarchenko, Alexey Dosovitskiy, and Thomas Brox. Octree generating networks: Efficient convolutional architectures for high-resolution 3d outputs. In Proceedings of the IEEE international conference on computer vision, pages 2088–2096, 2017. 3 [55] Maxim Tatarchenko, Stephan R Richter, Rene Ranftl, ´ Zhuwen Li, Vladlen Koltun, and Thomas Brox. What do single-view 3d reconstruction networks learn? In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 3405–3414, 2019. 4, 6 [56] Anh Thai, Stefan Stojanov, Vijay Upadhya, and James M Rehg. 3d reconstruction of novel object shapes from single images. In 2021 International Conference on 3D Vision (3DV), pages 85–95. IEEE, 2021. 2, 3, 4, 6, 8 [57] Haochen Wang, Xiaodan Du, Jiahao Li, Raymond A Yeh, and Greg Shakhnarovich. Score jacobian chaining: Lifting pretrained 2d diffusion models for 3d generation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 12619–12629, 2023. 3 [58] Nanyang Wang, Yinda Zhang, Zhuwen Li, Yanwei Fu, Wei Liu, and Yu-Gang Jiang. Pixel2mesh: Generating 3d mesh models from single rgb images. In Proceedings of the European conference on computer vision (ECCV), pages 52–67, 2018. 3 [59] Zhengyi Wang, Cheng Lu, Yikai Wang, Fan Bao, Chongxuan Li, Hang Su, and Jun Zhu. Prolificdreamer: High-fidelity and diverse text-to-3d generation with variational score distillation. arXiv preprint arXiv:2305.16213, 2023. 8 [60] Daniel Watson, William Chan, Ricardo Martin-Brualla, Jonathan Ho, Andrea Tagliasacchi, and Mohammad Norouzi. Novel view synthesis with diffusion models. arXiv preprint arXiv:2210.04628, 2022. 3 [61] Jason Wei, Yi Tay, Rishi Bommasani, Colin Raffel, Barret Zoph, Sebastian Borgeaud, Dani Yogatama, Maarten Bosma, Denny Zhou, Donald Metzler, et al. Emergent abilities of large language models. arXiv preprint arXiv:2206.07682, 2022. 8 [62] Chao Wen, Yinda Zhang, Zhuwen Li, and Yanwei Fu. Pixel2mesh++: Multi-view 3d mesh generation via deformation. In Proceedings of the IEEE/CVF international conference on computer vision, pages 1042–1051, 2019. 3 [63] Chao-Yuan Wu, Justin Johnson, Jitendra Malik, Christoph Feichtenhofer, and Georgia Gkioxari. Multiview compressive coding for 3d reconstruction. arXiv preprint arXiv:2301.08247, 2023. 2, 3, 4, 7 [64] Jiajun Wu, Yifan Wang, Tianfan Xue, Xingyuan Sun, Bill Freeman, and Josh Tenenbaum. Marrnet: 3d shape reconstruction via 2.5 d sketches. Advances in neural information processing systems, 30, 2017. 2, 3, 8 [65] Jiajun Wu, Chengkai Zhang, Xiuming Zhang, Zhoutong Zhang, William T Freeman, and Joshua B Tenenbaum. Learning shape priors for single-view 3d completion and reconstruction. In Proceedings of the European Conference on Computer Vision (ECCV), pages 646–662, 2018. 3, 8 [66] Tong Wu, Jiarui Zhang, Xiao Fu, Yuxin Wang, Jiawei Ren, Liang Pan, Wayne Wu, Lei Yang, Jiaqi Wang, Chen Qian, et al. Omniobject3d: Large-vocabulary 3d object dataset for realistic perception, reconstruction and generation. arXiv preprint arXiv:2301.07525, 2023. 1, 2, 5, 6 [67] Yongqin Xiang, Julian Chibane, Bharat Lal Bhatnagar, Bernt Schiele, Zeynep Akata, and Gerard Pons-Moll. Any-shot gin: Generalizing implicit networks for reconstructing novel classes. In 2022 International Conference on 3D Vision (3DV). IEEE, 2022. 2, 3 [68] Qiangeng Xu, Weiyue Wang, Duygu Ceylan, Radomir Mech, and Ulrich Neumann. Disn: Deep implicit surface network for high-quality single-view 3d reconstruction. Advances in neural information processing systems, 32, 2019. 2, 3 [69] Yaoqing Yang, Chen Feng, Yiru Shen, and Dong Tian. Foldingnet: Point cloud auto-encoder via deep grid deformation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 206–215, 2018. 3 [70] Xiuming Zhang, Zhoutong Zhang, Chengkai Zhang, Josh Tenenbaum, Bill Freeman, and Jiajun Wu. Learning to reconstruct shapes from unseen classes. Advances in neural information processing systems, 31, 2018. 2, 3 [71] Zhizhuo Zhou and Shubham Tulsiani. Sparsefusion: Distilling view-conditioned diffusion for 3d reconstruction. arXiv preprint arXiv:2212.00792, 2022. 3 This paper is available on arxiv under CC BY 4.0 DEED license. Authors: (1) Zixuan Huang, University of Illinois at Urbana-Champaign and both authors contributed equally to this work; (2) Stefan Stojanov, Georgia Institute of Technology and both authors contributed equally to this work; (3) Anh Thai, Georgia Institute of Technology; (4) Varun Jampani, Stability AI; (5) James M. Rehg, University of Illinois at Urbana-Champaign. Table of Links Abstract and 1 Introduction Abstract and 1 Introduction 2. Related Work 2. Related Work 3. Method and 3.1. Architecture 3. Method and 3.1. Architecture 3.2. Loss and 3.3. Implementation Details 3.2. Loss and 3.3. Implementation Details 4. Data Curation 4.1. Training Dataset 4.1. Training Dataset 4.2. Evaluation Benchmark 4.2. Evaluation Benchmark 5. Experiments and 5.1. Metrics 5. Experiments and 5.1. Metrics 5.2. Baselines 5.2. Baselines 5.3. Comparison to SOTA Methods 5.3. Comparison to SOTA Methods 5.4. Qualitative Results and 5.5. Ablation Study 5.4. Qualitative Results and 5.5. Ablation Study 6. Limitations and Discussion 6. Limitations and Discussion 7. Conclusion and References 7. Conclusion and References A. Additional Qualitative Comparison A. Additional Qualitative Comparison B. Inference on AI-generated Images B. Inference on AI-generated Images C. Data Curation Details C. Data Curation Details 7. Conclusion We present a strong regression-based model for zero-shot shape reconstruction. The core of our model is an intermediate representation of the 3D visible surface which facilitates effective explicit 3D geometric reasoning. We also curate a large real-world evaluation benchmark to test zeroshot shape reconstruction methods. Our benchmark pools data from three different real-world 3D datasets and has an order of magnitude larger scale than the test sets used by prior work. Tested on our benchmark, our model significantly outperforms other SOTA methods and achieves higher computational efficiency, despite being trained with much less 3D data. We hope our effort is a meaningful step towards building zero-shot generalizable 3D reconstruction models. Acknowledgement . This work was supported by NIH R01HD104624-01A1. Acknowledgement References [1] Midjourney: https : / / www . midjourney . com / showcase/recent/. Accessed: May 5, 2023. 1, 3 [2] Panos Achlioptas, Olga Diamanti, Ioannis Mitliagkas, and Leonidas Guibas. Learning representations and generative models for 3d point clouds. In International conference on machine learning, pages 40–49. PMLR, 2018. 3 [3] Jean-Baptiste Alayrac, Jeff Donahue, Pauline Luc, Antoine Miech, Iain Barr, Yana Hasson, Karel Lenc, Arthur Mensch, Katherine Millican, Malcolm Reynolds, et al. Flamingo: a visual language model for few-shot learning. Advances in Neural Information Processing Systems, 35:23716–23736, 2022. 1 [4] Kalyan Vasudev Alwala, Abhinav Gupta, and Shubham Tulsiani. Pre-train, self-train, distill: A simple recipe for supersizing 3d reconstruction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 3773–3782, 2022. 7 [5] Jan Bechtold, Maxim Tatarchenko, Volker Fischer, and Thomas Brox. Fostering generalization in single-view 3d reconstruction by learning a hierarchy of local and global shape priors. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 15880– 15889, 2021. 2, 3 [6] Angel X Chang, Thomas Funkhouser, Leonidas Guibas, Pat Hanrahan, Qixing Huang, Zimo Li, Silvio Savarese, Manolis Savva, Shuran Song, Hao Su, et al. Shapenet: An information-rich 3d model repository. arXiv preprint arXiv:1512.03012, 2015. 5 [7] Rui Chen, Yongwei Chen, Ningxin Jiao, and Kui Jia. Fantasia3d: Disentangling geometry and appearance for highquality text-to-3d content creation. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023. 8 [8] Christopher B Choy, Danfei Xu, JunYoung Gwak, Kevin Chen, and Silvio Savarese. 3d-r2n2: A unified approach for single and multi-view 3d object reconstruction. In European conference on computer vision, pages 628–644. Springer, 2016. 3 [9] Matt Deitke, Dustin Schwenk, Jordi Salvador, Luca Weihs, Oscar Michel, Eli VanderBilt, Ludwig Schmidt, Kiana Ehsani, Aniruddha Kembhavi, and Ali Farhadi. Objaverse: A universe of annotated 3d objects. arXiv preprint arXiv:2212.08051, 2022. 2, 5 [10] Matt Deitke, Ruoshi Liu, Matthew Wallingford, Huong Ngo, Oscar Michel, Aditya Kusupati, Alan Fan, Christian Laforte, Vikram Voleti, Samir Yitzhak Gadre, et al. Objaverse-xl: A universe of 10m+ 3d objects. arXiv preprint arXiv:2307.05663, 2023. 2 [11] Congyue Deng, Chiyu Jiang, Charles R Qi, Xinchen Yan, Yin Zhou, Leonidas Guibas, Dragomir Anguelov, et al. Nerdi: Single-view nerf synthesis with languageguided diffusion as general image priors. arXiv preprint arXiv:2212.03267, 2022. 3, 8 [12] Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, et al. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929, 2020. 8 [13] Ainaz Eftekhar, Alexander Sax, Jitendra Malik, and Amir Zamir. Omnidata: A scalable pipeline for making multitask mid-level vision datasets from 3d scans. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 10786–10796, 2021. 5 [14] Haoqiang Fan, Hao Su, and Leonidas J Guibas. A point set generation network for 3d object reconstruction from a single image. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 605–613, 2017. 3 [15] Thibault Groueix, Matthew Fisher, Vladimir G. Kim, Bryan Russell, and Mathieu Aubry. AtlasNet: A Papier-Mach ˆ e Ap- ´ proach to Learning 3D Surface Generation. In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2018. 3, 6 [16] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016. 4 [17] Zexin He and Tengfei Wang. Openlrm: Open-source large reconstruction models. https://github.com/ 3DTopia/OpenLRM, 2023. 7 [18] Yicong Hong, Kai Zhang, Jiuxiang Gu, Sai Bi, Yang Zhou, Difan Liu, Feng Liu, Kalyan Sunkavalli, Trung Bui, and Hao Tan. Lrm: Large reconstruction model for single image to 3d. arXiv preprint arXiv:2311.04400, 2023. 7 [19] Zixuan Huang, Stefan Stojanov, Anh Thai, Varun Jampani, and James M Rehg. Planes vs. chairs: Category-guided 3d shape learning without any 3d cues. In European Conference on Computer Vision, pages 727–744. Springer, 2022. 5, 6 [20] Zixuan Huang, Varun Jampani, Anh Thai, Yuanzhen Li, Stefan Stojanov, and James M Rehg. Shapeclipper: Scalable 3d shape learning from single-view images via geometric and clip-based consistency. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023. 6 [21] Muhammad Zubair Irshad, Sergey Zakharov, Rares Ambrus, Thomas Kollar, Zsolt Kira, and Adrien Gaidon. Shapo: Implicit representations for multi-object shape appearance and pose optimization. 2022. 3 [22] Heewoo Jun and Alex Nichol. Shap-e: Generating conditional 3d implicit functions. arXiv preprint arXiv:2305.02463, 2023. 1, 3, 7 [23] Angjoo Kanazawa, Shubham Tulsiani, Alexei A Efros, and Jitendra Malik. Learning category-specific mesh reconstruction from image collections. In Proceedings of the European Conference on Computer Vision (ECCV), pages 371– 386, 2018. 3 [24] Jared Kaplan, Sam McCandlish, Tom Henighan, Tom B Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei. Scaling laws for neural language models. arXiv preprint arXiv:2001.08361, 2020. 8 [25] Diederik P Kingma and Jimmy Ba. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014. 5 [26] Alexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao, Chloe Rolland, Laura Gustafson, Tete Xiao, Spencer Whitehead, Alexander C. Berg, Wan-Yen Lo, Piotr Dollar, and ´ Ross Girshick. Segment anything. arXiv:2304.02643, 2023. 1 [27] Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597, 2023. 1 [28] Chen-Hsuan Lin, Chaoyang Wang, and Simon Lucey. Sdfsrn: Learning signed distance 3d object reconstruction from static images. arXiv preprint arXiv:2010.10505, 2020. 6 [29] Chen-Hsuan Lin, Jun Gao, Luming Tang, Towaki Takikawa, Xiaohui Zeng, Xun Huang, Karsten Kreis, Sanja Fidler, Ming-Yu Liu, and Tsung-Yi Lin. Magic3d: High-resolution text-to-3d content creation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 300–309, 2023. 8 [30] Minghua Liu, Chao Xu, Haian Jin, Linghao Chen, Zexiang Xu, Hao Su, et al. One-2-3-45: Any single image to 3d mesh in 45 seconds without per-shape optimization. arXiv preprint arXiv:2306.16928, 2023. 1, 2, 3, 5, 7 [31] Ruoshi Liu, Rundi Wu, Basile Van Hoorick, Pavel Tokmakov, Sergey Zakharov, and Carl Vondrick. Zero-1-to3: Zero-shot one image to 3d object. arXiv preprint arXiv:2303.11328, 2023. 1, 2, 3, 5, 7 [32] William E Lorensen and Harvey E Cline. Marching cubes: A high resolution 3d surface construction algorithm. ACM siggraph computer graphics, 21(4):163–169, 1987. 6, 7 [33] David Marr. Vision: A computational investigation into the human representation and processing of visual information. MIT press, 2010. 2, 3 [34] Luke Melas-Kyriazi, Christian Rupprecht, Iro Laina, and Andrea Vedaldi. Realfusion: 360 reconstruction of any object from a single image. In CVPR, 2023. 3, 8 [35] Lars Mescheder, Michael Oechsle, Michael Niemeyer, Sebastian Nowozin, and Andreas Geiger. Occupancy networks: Learning 3d reconstruction in function space. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4460–4470, 2019. 3 [36] Ben Mildenhall, Pratul P Srinivasan, Matthew Tancik, Jonathan T Barron, Ravi Ramamoorthi, and Ren Ng. Nerf: Representing scenes as neural radiance fields for view synthesis. In European Conference on Computer Vision, pages 405–421. Springer, 2020. 7 [37] Alex Nichol, Heewoo Jun, Prafulla Dhariwal, Pamela Mishkin, and Mark Chen. Point-e: A system for generating 3d point clouds from complex prompts. arXiv preprint arXiv:2212.08751, 2022. 1, 3, 7 [38] Maxime Oquab, Timothee Darcet, Th ´ eo Moutakanni, Huy ´ Vo, Marc Szafraniec, Vasil Khalidov, Pierre Fernandez, Daniel Haziza, Francisco Massa, Alaaeldin El-Nouby, et al. Dinov2: Learning robust visual features without supervision. arXiv preprint arXiv:2304.07193, 2023. 1 [39] Songyou Peng, Michael Niemeyer, Lars Mescheder, Marc Pollefeys, and Andreas Geiger. Convolutional occupancy networks. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part III 16, pages 523–540. Springer, 2020. 3 [40] Ben Poole, Ajay Jain, Jonathan T Barron, and Ben Mildenhall. Dreamfusion: Text-to-3d using 2d diffusion. arXiv preprint arXiv:2209.14988, 2022. 3, 8 [41] Blender Project. Blender, https://blender.org/. 5 [42] Lu Qi, Jason Kuen, Tiancheng Shen, Jiuxiang Gu, Wenbo Li, Weidong Guo, Jiaya Jia, Zhe Lin, and Ming-Hsuan Yang. High quality entity segmentation. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pages 4047–4056, 2023. 1 [43] Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning, pages 8748–8763. PMLR, 2021. 1 [44] Aditya Ramesh, Prafulla Dhariwal, Alex Nichol, Casey Chu, and Mark Chen. Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125, 1 (2):3, 2022. 3 [45] Rene Ranftl, Katrin Lasinger, David Hafner, Konrad ´ Schindler, and Vladlen Koltun. Towards robust monocular depth estimation: Mixing datasets for zero-shot cross-dataset transfer. IEEE transactions on pattern analysis and machine intelligence, 44(3):1623–1637, 2020. 4 [46] Rene Ranftl, Alexey Bochkovskiy, and Vladlen Koltun. Vi- ´ sion transformers for dense prediction. ArXiv preprint, 2021. 4 [47] Jeremy Reizenstein, Roman Shapovalov, Philipp Henzler, Luca Sbordone, Patrick Labatut, and David Novotny. Common objects in 3d: Large-scale learning and evaluation of real-life 3d category reconstruction. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 10901–10911, 2021. 7 [48] Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Bjorn Ommer. High-resolution image syn- ¨ thesis with latent diffusion models, 2021. 1, 3, 8 [49] Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily L Denton, Kamyar Ghasemipour, Raphael Gontijo Lopes, Burcu Karagol Ayan, Tim Salimans, et al. Photorealistic text-to-image diffusion models with deep language understanding. Advances in Neural Information Processing Systems, 35:36479–36494, 2022. 1, 3 [50] Daeyun Shin, Charless C Fowlkes, and Derek Hoiem. Pixels, voxels, and views: A study of shape representations for single view 3d object shape prediction. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 3061–3069, 2018. 2, 3 [51] Rakesh Shrestha, Siqi Hu, Minghao Gou, Ziyuan Liu, and Ping Tan. A real world dataset for multi-view 3d reconstruction. In Computer Vision–ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part VIII, pages 56–73. Springer, 2022. 1, 2, 5, 6 [52] Xingyuan Sun, Jiajun Wu, Xiuming Zhang, Zhoutong Zhang, Chengkai Zhang, Tianfan Xue, Joshua B Tenenbaum, and William T Freeman. Pix3d: Dataset and methods for single-image 3d shape modeling. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2974–2983, 2018. 1, 2, 5 [53] Junshu Tang, Tengfei Wang, Bo Zhang, Ting Zhang, Ran Yi, Lizhuang Ma, and Dong Chen. Make-it-3d: High-fidelity 3d creation from a single image with diffusion prior. arXiv preprint arXiv:2303.14184, 2023. 3 [54] Maxim Tatarchenko, Alexey Dosovitskiy, and Thomas Brox. Octree generating networks: Efficient convolutional architectures for high-resolution 3d outputs. In Proceedings of the IEEE international conference on computer vision, pages 2088–2096, 2017. 3 [55] Maxim Tatarchenko, Stephan R Richter, Rene Ranftl, ´ Zhuwen Li, Vladlen Koltun, and Thomas Brox. What do single-view 3d reconstruction networks learn? In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 3405–3414, 2019. 4, 6 [56] Anh Thai, Stefan Stojanov, Vijay Upadhya, and James M Rehg. 3d reconstruction of novel object shapes from single images. In 2021 International Conference on 3D Vision (3DV), pages 85–95. IEEE, 2021. 2, 3, 4, 6, 8 [57] Haochen Wang, Xiaodan Du, Jiahao Li, Raymond A Yeh, and Greg Shakhnarovich. Score jacobian chaining: Lifting pretrained 2d diffusion models for 3d generation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 12619–12629, 2023. 3 [58] Nanyang Wang, Yinda Zhang, Zhuwen Li, Yanwei Fu, Wei Liu, and Yu-Gang Jiang. Pixel2mesh: Generating 3d mesh models from single rgb images. In Proceedings of the European conference on computer vision (ECCV), pages 52–67, 2018. 3 [59] Zhengyi Wang, Cheng Lu, Yikai Wang, Fan Bao, Chongxuan Li, Hang Su, and Jun Zhu. Prolificdreamer: High-fidelity and diverse text-to-3d generation with variational score distillation. arXiv preprint arXiv:2305.16213, 2023. 8 [60] Daniel Watson, William Chan, Ricardo Martin-Brualla, Jonathan Ho, Andrea Tagliasacchi, and Mohammad Norouzi. Novel view synthesis with diffusion models. arXiv preprint arXiv:2210.04628, 2022. 3 [61] Jason Wei, Yi Tay, Rishi Bommasani, Colin Raffel, Barret Zoph, Sebastian Borgeaud, Dani Yogatama, Maarten Bosma, Denny Zhou, Donald Metzler, et al. Emergent abilities of large language models. arXiv preprint arXiv:2206.07682, 2022. 8 [62] Chao Wen, Yinda Zhang, Zhuwen Li, and Yanwei Fu. Pixel2mesh++: Multi-view 3d mesh generation via deformation. In Proceedings of the IEEE/CVF international conference on computer vision, pages 1042–1051, 2019. 3 [63] Chao-Yuan Wu, Justin Johnson, Jitendra Malik, Christoph Feichtenhofer, and Georgia Gkioxari. Multiview compressive coding for 3d reconstruction. arXiv preprint arXiv:2301.08247, 2023. 2, 3, 4, 7 [64] Jiajun Wu, Yifan Wang, Tianfan Xue, Xingyuan Sun, Bill Freeman, and Josh Tenenbaum. Marrnet: 3d shape reconstruction via 2.5 d sketches. Advances in neural information processing systems, 30, 2017. 2, 3, 8 [65] Jiajun Wu, Chengkai Zhang, Xiuming Zhang, Zhoutong Zhang, William T Freeman, and Joshua B Tenenbaum. Learning shape priors for single-view 3d completion and reconstruction. In Proceedings of the European Conference on Computer Vision (ECCV), pages 646–662, 2018. 3, 8 [66] Tong Wu, Jiarui Zhang, Xiao Fu, Yuxin Wang, Jiawei Ren, Liang Pan, Wayne Wu, Lei Yang, Jiaqi Wang, Chen Qian, et al. Omniobject3d: Large-vocabulary 3d object dataset for realistic perception, reconstruction and generation. arXiv preprint arXiv:2301.07525, 2023. 1, 2, 5, 6 [67] Yongqin Xiang, Julian Chibane, Bharat Lal Bhatnagar, Bernt Schiele, Zeynep Akata, and Gerard Pons-Moll. Any-shot gin: Generalizing implicit networks for reconstructing novel classes. In 2022 International Conference on 3D Vision (3DV). IEEE, 2022. 2, 3 [68] Qiangeng Xu, Weiyue Wang, Duygu Ceylan, Radomir Mech, and Ulrich Neumann. Disn: Deep implicit surface network for high-quality single-view 3d reconstruction. Advances in neural information processing systems, 32, 2019. 2, 3 [69] Yaoqing Yang, Chen Feng, Yiru Shen, and Dong Tian. Foldingnet: Point cloud auto-encoder via deep grid deformation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 206–215, 2018. 3 [70] Xiuming Zhang, Zhoutong Zhang, Chengkai Zhang, Josh Tenenbaum, Bill Freeman, and Jiajun Wu. Learning to reconstruct shapes from unseen classes. Advances in neural information processing systems, 31, 2018. 2, 3 [71] Zhizhuo Zhou and Shubham Tulsiani. Sparsefusion: Distilling view-conditioned diffusion for 3d reconstruction. arXiv preprint arXiv:2212.00792, 2022. 3 This paper is available on arxiv under CC BY 4.0 DEED license. This paper is available on arxiv under CC BY 4.0 DEED license. available on arxiv Authors: (1) Zixuan Huang, University of Illinois at Urbana-Champaign and both authors contributed equally to this work; (2) Stefan Stojanov, Georgia Institute of Technology and both authors contributed equally to this work; (3) Anh Thai, Georgia Institute of Technology; (4) Varun Jampani, Stability AI; (5) James M. Rehg, University of Illinois at Urbana-Champaign. Authors: Authors: (1) Zixuan Huang, University of Illinois at Urbana-Champaign and both authors contributed equally to this work; (2) Stefan Stojanov, Georgia Institute of Technology and both authors contributed equally to this work; (3) Anh Thai, Georgia Institute of Technology; (4) Varun Jampani, Stability AI; (5) James M. Rehg, University of Illinois at Urbana-Champaign.