AI Paper Atlas

Research map / Video / Video generation

PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation

Shaowei Liu, Zhongzheng Ren, Saurabh Gupta, Shenlong Wang

ECCV 2024 · Video › Video generation · approach: Trajectory-guided motion control · 56 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
estimate physical parameters with GPT-4V instead of random values from human-estimated ranges (ablation)PhysGen · collected GT scene videosImage-FID: 111.01 -> 105.70Improved
estimate physical parameters with GPT-4V instead of random values from human-estimated ranges (ablation)PhysGen · collected GT scene videosMotion-FID: 36.60 -> 30.20Improved
ground object dynamics in rigid-body simulation instead of purely data-driven I2VPhysGen vs SEINE, DynamiCrafter, I2VGen-XL · human evaluationphysical-realism (1-5): 2.11 -> 4.14Improved
ground dynamics in physics simulation versus best baselinePhysGen · collected GT scene videosMotion-FID: 38.76 -> 30.20Improved
physics-grounded generation versus DynamiCrafter on appearancePhysGen · collected GT scene videosImage-FID: 99.64 -> 105.70Hurt
add generative diffusion refinement after composition and relighting (ablation)PhysGen rendering · qualitativephoto-realismImproved
add relighting to composited frames (ablation)PhysGen rendering · qualitativelighting realismMixed
diffusion refinement injects generated latent into foregroundPhysGen · qualitative limitationforeground fidelityHurt

Later papers that compared with this method

2 later accepted papers report PhysGen as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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