This story on HackerNoon has a decentralized backup on Sia.
Transaction ID: IVW6YuI3uGXiNnh60N8f-SVqSauoEdbe7Us4H46wxD8
Cover

Optimizing Video Matting: Curriculum Learning and Motion Blur Augmentation

Written by @instancing | Published on 2025/12/21
TL;DR —
MaGGIe achieves feature temporal consistency in videos using bidirectional Conv-GRU. It utilizes A100 GPUs and AdamW optimization for robust results.

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

9.2. Training details

Authors:

(1) Chuong Huynh, University of Maryland, College Park (chuonghm@cs.umd.edu);

(2) Seoung Wug Oh, Adobe Research (seoh,jolee@adobe.com);

(3) Abhinav Shrivastava, University of Maryland, College Park (abhinav@cs.umd.edu);

(4) Joon-Young Lee, Adobe Research (jolee@adobe.com).

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

[story continues]

Written by
@instancing
Pioneering instance management, driving innovative solutions for efficient resource utilization, and enabling a more sus
Topics and
tags
deep-learning|maggie-video-matting|bidirectional-conv-gru|feature-temporal-consistency|coarse-alpha-matte-a8|a100-gpu-training|adamw-optimization|curriculum-learning
This story on HackerNoon has a decentralized backup on Sia.
Transaction ID: IVW6YuI3uGXiNnh60N8f-SVqSauoEdbe7Us4H46wxD8