AI Paper Atlas

Research map / 3D vision / 3D generation

MoCam: Unified Novel View Synthesis via Structured Denoising Dynamics

Haofeng Liu, Yang Zhou, Ziheng Wang, Zhengbo Xu, Zhan Peng, Jie Ma, Jun Liang, Shengfeng He, Jing Li

ECCV 2026 · 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
add late-stage source-video conditioning after scaffold (vs scaffold-only) (ablation)MoCam · OpenVid 4D re-cameraimaging quality: 0.4807 -> 0.6932Improved
add late-stage source-video conditioning (vs scaffold-early with nothing later) (ablation)MoCam · OpenVid 4D re-cameraimaging quality: 0.6172 -> 0.6932Improved
add late-stage source-video conditioning (vs scaffold-early) (ablation)MoCam · OpenVid 4D re-cameraFVD-V: 273.19 -> 260.05Improved
switch from scaffold to source at T_switch instead of static both conditions (ablation)MoCam · OpenVid 4D re-cameraRotErr / TransErr: 2.71 -> 1.36; 11.01 -> 5.12Improved
switch from scaffold to source instead of static both conditions (ablation)MoCam · OpenVid 4D re-cameraFVD-V: 242.81 -> 260.05Hurt
use Wan2.1 backbone instead of Wan2.2 (ablation)MoCam · OpenVid 4D re-cameraimaging quality: 0.6931 vs 0.6932No clear effect
use MoCam instead of GEN3Csingle-view 3D reconstruction · OpenVidFVD-V: 289.37 -> 255.16Improved
use MoCam instead of ViewCraftersingle-view 3D reconstruction · OpenVidFVD-V: 308.24 -> 255.16Improved
use MoCam instead of GEN3Cvideo re-camera · iPhone datasetFVD: 260.15 -> 180.35Improved
use MoCam instead of TrajCraftervideo re-camera · iPhone datasetPSNR: 13.74 -> 14.60Improved

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