AI Paper Atlas

Research map / Video / Video generation

SIFT: Self-Imagination Fine-Tuning for Physically Plausible Motion in Video Diffusion Models

Ruoyu Wang, Jialun Liu, Huayang Huang, Haibin Huang, Jiepeng Wang, Chi Zhang, Xuelong Li, Yu Wu

ECCV 2026 · Video › Video generation · approach: Trajectory-guided motion control · 0 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 self-imagination generation from pure noise instead of noisy real videos (ablation)SIFT (Wan) · Camera-only (VLM, ablation)Physical Commonsense: 3.55 -> 4.15Improved
add self-imagination generation from pure noise instead of noisy real videos (ablation)SIFT (Wan) · Camera-only (VLM, ablation)Semantic Adherence: 3.05 -> 3.85Improved
add alternating supervision between R3D and SlowFast instead of R3D only (ablation)SIFT (Wan) · Camera-only (VLM, ablation)Semantic Adherence: 3.65 -> 3.85Improved
add alternating supervision between R3D and SlowFast instead of SlowFast only (ablation)SIFT (Wan) · Camera-only (VLM, ablation)Physical Commonsense: 3.25 -> 4.15Improved
use single R3D classifier instead of alternating (object-only SA higher than full) (ablation)SIFT (Wan) · Object-only (VLM, ablation)Semantic Adherence: 3.50 -> 3.20Hurt
add progressive hard case replay (ablation)SIFT (Wan) · Camera-only (VLM, ablation)Semantic Adherence: 3.00 -> 3.85Improved
add progressive hard case replay (ablation)SIFT (Wan) · Object-only (VLM, ablation)Physical Commonsense: 3.70 -> 4.00Improved
fine-tune with SFT on 4,000 motion-decoupled videosWan · Human eval object-onlyPhysical Commonsense: 2.75 -> 2.43Hurt
fine-tune with SFT on 4,000 motion-decoupled videosWan · Camera-only (VLM)Physical Commonsense: 4.06 -> 4.73Improved
replace SFT with SIFTWan · Camera-only (VLM)Physical Commonsense: 4.73 -> 4.93Improved
replace VideoREPA with SIFTCogVideoX · Object-only (VLM)Physical Commonsense: 3.50 -> 4.25Improved
add SIFT on multi-object motionWan · Multi-object (50 prompts)Physical Commonsense: 3.92 -> 4.18Improved

Earlier methods this paper compares with

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