AI Paper Atlas

Research map / Video / Video segmentation and tracking

Deep Video Matting via Spatio-Temporal Alignment and Aggregation

Yanan Sun, Guanzhi Wang, Qiao Gu, Chi-Keung Tang, Yu-Wing Tai

CVPR 2021 · Video › Video segmentation and tracking · approach: Video restoration with temporal priors · 61 citations (OpenAlex)

Check your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use the full ST-FAM video matting framework instead of GCAComposited test set with full trimaps · Composited test set, full-trimapSAD: 47.49 -> 40.91Improved
Add TFA to the basic model (ablation)Basic video matting model · Composited test setSAD: 44.26 -> 42.32Improved
Add TFF to the model with TFA (ablation)Basic video matting model with TFA · Composited test setSAD: 42.32 -> 40.91Improved
Increase neighboring frames from 1 to 2 (ablation)Temporal aggregation model · Composited test setSAD: 48.72 -> 46.98Improved
Increase neighboring frames from 2 to 3 (ablation)Temporal aggregation model · Composited test setSAD: 46.98 -> 46.29Improved
Increase neighboring frames from 3 to 4 (ablation)Temporal aggregation model · Composited test setSAD: 46.29 -> 46.30No clear effect
Replace ST-FAM with naive fusion (ablation)Video matting model · Composited test setSAD: 40.91 -> 44.13Hurt
Replace ST-FAM with cross-attention fusion (ablation)Video matting model · Composited test setSAD: 40.91 -> 41.29Hurt
Replace ST-FAM with flow fusion (ablation)Video matting model · Composited test setSAD: 40.91 -> 44.06Hurt
Provide trimaps every 20 rather than every frame (ablation)ST-FAM video matting model · Composited test setSAD: 40.91 -> 43.66Hurt
Provide trimaps every 40 frames rather than every frame (ablation)ST-FAM video matting model · Composited test setSAD: 40.91 -> 52.85Hurt
Use a single trimap for the entire video rather than frame-by-frame trimaps (ablation)ST-FAM video matting model · Composited test setSAD: 40.91 -> 65.33Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy