MaGGIe Training Setup: High-Performance Human Instance Matting with A100 GPUs

Written by instancing | Published 2025/12/19
Tech Story Tags: deep-learning | human-instance-matting | maggie-framework | feature-temporal-consistency | bidirectional-conv-gru | coarse-alpha-matte-a8 | adamw-optimization | curriculum-learning

TLDRMaGGIe ensures feature temporal consistency in videos using bidirectional Conv-GRU. It uses AdamW optimization and curriculum learning on A100 GPUs for robust matting.via the TL;DR App

Abstract and 1. Introduction

  1. Related Works

  2. MaGGIe

    3.1. Efficient Masked Guided Instance Matting

    3.2. Feature-Matte Temporal Consistency

  3. Instance Matting Datasets

    4.1. Image Instance Matting and 4.2. Video Instance Matting

  4. Experiments

    5.1. Pre-training on image data

    5.2. Training on video data

  5. Discussion and References

Supplementary Material

  1. Architecture details

  2. Image matting

    8.1. Dataset generation and preparation

    8.2. Training details

    8.3. Quantitative details

    8.4. More qualitative results on natural images

  3. Video matting

    9.1. Dataset generation

    9.2. Training details

    9.3. Quantitative details

    9.4. More qualitative results

8.2. Training details

Authors:

(1) Chuong Huynh, University of Maryland, College Park ([email protected]);

(2) Seoung Wug Oh, Adobe Research (seoh,[email protected]);

(3) Abhinav Shrivastava, University of Maryland, College Park ([email protected]);

(4) Joon-Young Lee, Adobe Research ([email protected]).


This paper is available on arxiv under CC by 4.0 Deed (Attribution 4.0 International) license.


Written by instancing | Pioneering instance management, driving innovative solutions for efficient resource utilization, and enabling a more sus
Published by HackerNoon on 2025/12/19