This story on HackerNoon has a decentralized backup on Sia.
Transaction ID: 4ICfIMBEmvy1WbNaDbby1TJv7F1A_kpOxwH_UN-G64M
Cover

MaGGIe's Coarse Alpha Matte Prediction: Temporal Feature Aggregation

Written by @instancing | Published on 2025/12/17
TL;DR —
MaGGIe ensures temporal consistency in video matting using bidirectional Conv-GRU to fuse feature maps and predict coarse alpha mattes

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

3.2. Feature-Matte Temporal Consistency

We propose to enhance temporal consistency at both feature and alpha matte levels.

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|temporal-consistency|bidirectional-conv-gru|video-matting|feature-map-aggregation|maggie-algorithm|coarse-prediction|video-processing
This story on HackerNoon has a decentralized backup on Sia.
Transaction ID: 4ICfIMBEmvy1WbNaDbby1TJv7F1A_kpOxwH_UN-G64M