AI Paper Atlas

Research map / 3D vision / 3D generation

LaVR: Scene Latent Conditioned Generative Video Trajectory Re-Rendering using Large 4D Reconstruction Models

Mingyang Xie, Numair Khan, Tianfu Wang, Naina Dhingra, Seonghyeon Nam, Haitao Yang, Zhuo Hui, Christopher Metzler, Andrea Vedaldi, Hamed Pirsiavash, Lei Luo

CVPR 2026 · 3D vision › 3D generation · approach: Diffusion-based novel view synthesis · 7 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 CUT3R latent conditioning (with source pose) (ablation)ReCamMaster-style video diffusion model · Cycle consistencyCycle PSNR: 17.90 -> 20.74Improved
add CUT3R latent conditioning (ablation)LaVR · Multi-view consistencyMulti-View: 6.832 -> 17.11Improved
add CUT3R latent conditioning (ablation)LaVR · Target pose reconstructionAbs(t) error: 19.70 -> 14.39Improved
add source camera pose conditioning on top of CUT3R latents (ablation)LaVR · Cycle consistencyCycle PSNR: 20.70 -> 20.74No clear effect
add source camera pose conditioning on top of CUT3R latents (ablation)LaVR · Multi-view consistencyMulti-View: 16.08 -> 17.11Improved
add source camera pose conditioning on top of CUT3R latents (ablation)LaVR · Target pose reconstructionAbs(t) error: 16.93 -> 14.39Improved
add source pose only, without CUT3R latents (ablation)ReCamMaster · Cycle consistencyCycle PSNR: 17.75 -> 17.90No clear effect
condition on implicit CUT3R latents instead of re-rendered point cloudsvideo re-rendering · Cycle consistency (DL3DV)Cycle PSNR: 14.84 -> 20.74Improved
condition on CUT3R latents vs unconditioned ReCamMastervideo re-rendering · VBench dynamic videosMulti-view consistency: 5.975 -> 17.11Improved
CUT3R latent conditioning vs ReCamMaster on background consistencyvideo re-rendering · VBench dynamic videosBackground consistency: 92.76 -> 92.83No clear effect

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