AI Paper Atlas

Research map / Video / Video generation

WildVidFit: Video Virtual Try-On in the Wild via Image-Based Controlled Diffusion Models

Zijian He, Peixin Chen, Guangrun Wang, Guanbin Li, Philip Torr, Liang Lin

ECCV 2024 · Video › Video generation · approach: Diffusion-based human image animation · 21 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 fully cross-frame attention to image-based model (ablation)WildVidFit · TikTokVFID: 13.45 -> 12.14Improved
add VideoMAE guidance (L_MAE) (ablation)WildVidFit · TikTokVFID: 12.14 -> 10.64Improved
add DINO-V2 feature similarity guidance (L_SIM) (ablation)WildVidFit · TikTokVFID: 10.64 -> 10.28Improved
add temporal co-denoising over overlapping clips (ablation)WildVidFit · TikTokVFID: 10.28 -> 9.87Improved
add garment edge map to garment representation (ablation)WildVidFit image try-on · VITON-HDFID: 8.93 -> 8.67Improved
raise classifier-free guidance scale from 1 to 2 (ablation)WildVidFit image try-on · VITON-HDFID: 9.47 -> 8.67Improved
raise classifier-free guidance scale from 2 to 3 (ablation)WildVidFit image try-on · VITON-HDFID: 8.67 -> 8.68No clear effect
video-trained ClothFormer versus image-trained WildVidFit with diffusion guidancevideo try-on · VVTVFID: 4.192 vs 4.202No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 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