AI Paper Atlas

Research map / 3D vision / 3D generation

UniVerse: Unleashing the Scene Prior of Video Diffusion Models for Robust Radiance Field Reconstruction

Jin Cao, Hongrui Wu, Ziyong Feng, Hujun Bao, Xiaowei Zhou, Sida Peng

ICCV 2025 · 3D vision › 3D generation · approach: Diffusion-based novel view synthesis · 1 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
sort images with ThreadPose when forming the initial video (ablation)UniVerse · Synthetic (image-to-video ablation)PSNR: 18.25 -> 20.71Improved
insert zero frames (implicit views) into ordered images (ablation)UniVerse · Synthetic (image-to-video ablation)PSNR: 17.29 -> 20.71Improved
sort and insert zero frames instead of directly stacking (ablation)UniVerse · Synthetic (image-to-video ablation)SSIM: 0.4598 -> 0.7708Improved
replace single-input Query Transformer with Multi-input Query Transformer (ablation)UniVerse · Query Transformer ablationPSNR: 16.80 -> 17.42Improved
replace single-input Query Transformer with Multi-input Query Transformer (ablation)UniVerse · Query Transformer ablationLPIPS: 0.5015 -> 0.4549Improved
replace MSE with consistency loss for VDM training (ablation)UniVerse · Loss ablationPSNR: 16.19 -> 17.42Improved
replace MSE with consistency loss for VDM training (ablation)UniVerse · Loss ablationLPIPS: 0.5340 -> 0.4549Improved
add inpainting masks to the VDM input (ablation)UniVerse · NeRF-on-the-go subset (occlusions only)visual inpaintingImproved
add style mask to the VDM input (ablation)UniVerse · visualtone controlImproved
restore images with UniVerse before reconstruction instead of ZipNeRF w/GLOZipNeRF w/GLO · Synthetic LLFF (sRGB)PSNR: 14.53 -> 18.09Improved
restore images with UniVerse before reconstruction instead of ZipNeRF w/GLOZipNeRF w/GLO · Real-world captured (sRGB)PSNR: 16.14 -> 19.65Improved
add GLO appearance embeddings to ZipNeRFZipNeRF · Synthetic LLFF (sRGB)PSNR: 11.52 -> 14.53Improved

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