AI Paper Atlas

Research map / 3D vision / 3D generation

One Video, One World: Turning Monocular Video into Physical 4D Scenes

Junhao Chen, Boran Zhang, Mingjin Chen, Henghaofan Zhang, Saining Zhang, Congcong Zhu, HAO ZHAO, Ruqi Huang, Zhihao Li, Yufei Wang

ECCV 2026 · 3D vision › 3D generation · approach: Monocular 3D object reconstruction · 11 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
increase refinement iterations from 1 to 3 (ablation)OVOW · validation setIoU-B: 0.58 -> 0.78Improved
increase refinement iterations from 3 to 5 (ablation)OVOW · validation setIoU-B: 0.78 -> 0.79No clear effect
set rho to 0.65 instead of 0.55 (ablation)OVOW · validation setIoU-B: 0.74 -> 0.78Improved
raise rho from 0.65 to 0.75 (ablation)OVOW · validation setIoU-B: 0.78 -> 0.76Hurt
set tau_area to 200 instead of 100 (ablation)OVOW · validation setValid scenes: 84.9 -> 86.8Improved
raise tau_area from 200 to 400 (ablation)OVOW · validation setValid scenes: 86.8 -> 85.7Hurt
set tau_contact to 3% instead of 2% (ablation)OVOW · validation setSim. stability: 79.8 -> 82.7Improved
raise tau_contact from 3% to 4% (ablation)OVOW · validation setSim. stability: 82.7 -> 81.5Hurt
use 2 assembly rounds instead of 1 (ablation)OVOW · validation setSim. stability: 78.9 -> 82.7Improved
use 5 assembly rounds instead of 2 (ablation)OVOW · validation setSim. stability: 82.7 -> 82.8No clear effect
use video input (OVOW) instead of per-frame image baseline MIDIOVOW · OVOW-4D-Scene-BenchScene-IoU OBB: 0.198 -> 0.440Improved
use video input (OVOW) instead of per-frame image baseline MIDIOVOW · OVOW-4D-Scene-BenchTime (s/frame): 234 -> 3.35Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 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