AI Paper Atlas

Research map / Video / Video generation

VideoMaMa: Mask-Guided Video Matting via Generative Prior

Sangbeom Lim, Seoung Wug Oh, Jiahui Huang, Heeji Yoon, Seungryong Kim, Joon-Young Lee

CVPR 2026 · Video › Video generation · approach: Efficient video diffusion models · 5 citations (OpenAlex)

Read the paperCheck 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
add MA-V pseudo-labeled data to existing matting datasets for SAM2 fine-tuning (ablation)SAM2-Matte · V-HIM60 HardMAD: 7.5798 -> 2.6112Improved
train on MA-V alone instead of existing datasets alone (ablation)SAM2-Matte · V-HIM60 HardMAD: 7.5798 -> 3.1830Improved
add existing synthetic matting datasets to MA-V (ablation)SAM2-Matte · DAVIS valJ&F: 87.9 -> 85.9Hurt
add existing synthetic matting datasets to MA-V (ablation)SAM2-Matte · V-HIM60 HardMAD: 3.1830 -> 2.6112Improved
add stage 2 temporal training to stage 1 spatial training (ablation)VideoMaMa · YouTubeMatte, downsample 32xMAD: 3.7620 -> 1.2552Improved
add stage 1 high-resolution spatial training to video-only stage 2 (with DINO) (ablation)VideoMaMa · YouTubeMatte, downsample 32xMAD: 1.2350 -> 1.2552 (without DINO)Mixed
add DINOv3 semantic knowledge injection (ablation)VideoMaMa · YouTubeMatte, downsample 32xMAD: 1.2552 -> 1.0292Improved
add DINOv3 semantic knowledge injection (ablation)VideoMaMa · YouTubeMatte, hard polygon masksMAD: 1.9975 -> 1.4042Improved
add DINOv3 semantic knowledge injection (ablation)VideoMaMa · YouTubeMatte, SAM2 masksMAD: 1.9404 -> 1.7370Improved
vary number of frames per inference from 1 to 24 (ablation)VideoMaMa · YouTubeMatte, downsample 32xMAD (refined): 1.1024 (1 frame) -> 1.0237 (24 frames)No clear effect
use VideoMaMa to refine SAM2 masks versus raw SAM2 masks (first-frame setting)SAM2+VideoMaMa · V-HIM60 HardMAD: 7.8517 -> 2.7757Improved
use SAM2-Matte versus MatAnyoneSAM2-Matte · V-HIM60 HardMAD: 5.7195 -> 2.6112Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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