AI Paper Atlas

Research map / Video / Video generation

SV4D 2.0: Enhancing Spatio-Temporal Consistency in Multi-View Video Diffusion for High-Quality 4D Generation

Chun-Han Yao, Yiming Xie, Vikram Voleti, Huaizu Jiang, Varun Jampani

ICCV 2025 · Video › Video generation · approach: Efficient video diffusion models · 42 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 3D attention over merged view and spatial dimensions (ablation)SV4D 2.0 · ObjaverseDy NVVSFV4D: 283.10 -> 256.84Improved
add 3D attention (ablation)SV4D 2.0 · ObjaverseDy NVVSLPIPS: 0.115 -> 0.105Improved
add 3D attention (ablation)SV4D 2.0 · ObjaverseDy NVVSFVD-F: 548.14 -> 473.90Improved
add improved ObjaverseDy++ data curation (ablation)SV4D 2.0 · ObjaverseDy NVVSFV4D: 316.91 -> 256.84Improved
add improved ObjaverseDy++ data curation (ablation)SV4D 2.0 · ObjaverseDy NVVSLPIPS: 0.112 -> 0.105Improved
add improved ObjaverseDy++ data curation (ablation)SV4D 2.0 · ObjaverseDy NVVSFVD-F: 576.66 -> 473.90Improved
upgrade SV4D to SV4D 2.0 for novel-view video synthesisSV4D · ObjaverseDy NVVSFV4D: 458.34 -> 256.84Improved
upgrade SV4D to SV4D 2.0 for novel-view video synthesisSV4D · ObjaverseDy NVVSLPIPS: 0.122 -> 0.105Improved
upgrade SV4D to SV4D 2.0 for 4D optimizationSV4D · ObjaverseDy 4DFV4D: 699.04 -> 532.55Improved
upgrade SV4D to SV4D 2.0 for NVVSSV4D · Consistent4D NVVSFVD-F: 677.68 -> 553.43Improved
upgrade SV4D to SV4D 2.0 for 4D optimizationSV4D · Consistent4D 4DLPIPS: 0.118 -> 0.117No clear effect
use SV4D 2.0 instead of L4GM for 4D optimizationL4GM · Consistent4D 4DFVD-F: 691.87 -> 692.68Hurt

Later papers that compared with this method

1 later accepted paper reports SV4D 2.0 as a baseline in their results tables; 1 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 3 of 3 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