AI Paper Atlas

Research map / 3D vision / 3D generation

NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos

Yuxue Yang, Lue Fan, Ziqi Shi, Junran Peng, Feng Wang, Zhaoxiang Zhang

CVPR 2026 · 3D vision › 3D generation · approach: Diffusion-based novel view synthesis · 46 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
remove opacity regularization (add it) (ablation)NeoVerse reconstruction · DyCheckPSNR: 10.86 -> 11.56Improved
add bidirectional motion modeling (ablation)NeoVerse reconstruction · DyCheckPSNR: 11.27 -> 11.56Improved
add the generation model on top of reconstruction (ablation)NeoVerse · DyCheckPSNR: 11.56 -> 14.59Improved
reconstruct from sparse key frames (11 instead of all 81) (ablation)NeoVerse generation · VBench novel view generationimaging quality / inference time: 61.51 -> 59.75 imaging quality; 28 s -> 20 sMixed
increase key frames from 11 to full frames (ablation)NeoVerse generation · VBenchSubject Consistency: 88.43 -> 89.42Improved
use scalable monocular pipeline with degradation simulation instead of TrajectoryCrafternovel-view video generation · VBench novel view generationImaging Quality: 54.59 -> 61.51Improved
apply feed-forward pose-free 4DGS instead of AnySplatstatic reconstruction · Scannet++ (32 views)PSNR: 22.79 -> 25.34Improved
use NeoVerse instead of ReCamMasternovel-view video generation · VBenchTemporal Flickering / Motion Smoothness: 96.56 -> 96.51 (full frames); 98.86 -> 98.67No clear effect

Later papers that compared with this method

1 later accepted paper reports NeoVerse 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 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