AI Paper Atlas

Research map / Video / Video generation

Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis

Bowen Zhang, Sicheng Xu, Chuxin Wang, Jiaolong Yang, Feng Zhao, Dong Chen, Baining Guo

ICCV 2025 · Video › Video generation · approach: Efficient video diffusion models · 17 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 mesh-guided loss (ablation)GVFDiffusion VAE · VAE ablationPSNR: 23.25 -> 26.17Improved
add mesh-guided loss (ablation)GVFDiffusion VAE · VAE ablationLPIPS: 0.0678 -> 0.0544Improved
use motion-aware displacement query via mesh-guided interpolation (ablation)GVFDiffusion VAE · VAE ablationPSNR: 26.17 -> 28.58Improved
add color and opacity variations to variation fields (ablation)GVFDiffusion VAE · VAE ablationPSNR: 28.58 -> 29.28Improved
add color and opacity variations (ablation)GVFDiffusion VAE · VAE ablationLPIPS: 0.0478 -> 0.0439Improved
add positional embeddings from canonical GS positions (ablation)GVFDiffusion diffusion model · Video-to-4D test setPSNR: 17.86 -> 18.47Improved
add positional embeddings from canonical GS positions (ablation)GVFDiffusion diffusion model · Video-to-4D test setFVD: 547.20 -> 476.83Improved
jointly finetune canonical GS decoder D_GS (ablation)GVFDiffusion VAE · VAE ablationPSNR: 28.80 -> 29.28Improved
set K=8 neighbors rather than K=16 (ablation)mesh-guided interpolation · VAE ablationPSNR: 28.38 -> 29.28Improved
set K=8 neighbors rather than K=1 (ablation)mesh-guided interpolation · VAE ablationPSNR: 28.22 -> 29.28Improved
set beta=7.0 rather than 10.0 (ablation)mesh-guided interpolation · VAE ablationPSNR: 28.55 -> 29.28Improved
use GVFDiffusion instead of L4GMvideo-to-4D generation · Video-to-4D test setFVD: 529.10 -> 476.83Improved

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