AI Paper Atlas

Research map / 3D vision / 3D generation

Gen3R: 3D Scene Generation Meets Feed-Forward Reconstruction

Jiaxin Huang, Yuanbo Yang, Bangbang Yang, Lin Ma, Yuewen Ma, Yiyi Liao

CVPR 2026 · 3D vision › 3D generation · approach: Diffusion-based novel view synthesis · 19 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 joint RGB and geometry generation instead of a 2-stage RGB-then-VGGT pipeline (ablation)Gen3R · RealEstate10K (1-view)PSNR: 17.38 -> 20.51Improved
add joint RGB and geometry generation instead of a 2-stage pipeline (ablation)Gen3R · Co3Dv2 (1-view geometry)Chamfer distance: 1.6223 -> 1.1047Improved
add joint generation instead of 2-stage (ablation)Gen3R · RealEstate10K camera control (1-view)AUC@30: 0.6832 -> 0.7443Improved
add KL distribution alignment loss between geometry and appearance latents (ablation)Gen3R · RealEstate10K (1-view)PSNR: 16.31 -> 20.51Improved
add KL distribution alignment loss (ablation)Gen3R · RealEstate10K camera control (1-view)AUC@30: 0.4100 -> 0.7443Improved
add KL distribution alignment loss (ablation)Gen3R · Co3Dv2 (2-view geometry)Chamfer distance: 1.7144 -> 0.9767Improved
use adapter on VGGT tokens instead of WVD-style pretrained RGB VAE for point clouds (ablation)geometry VAE · Co3Dv2 (feed-forward reconstruction)Chamfer distance: 1.2080 -> 0.9986Improved
add diffusion generative model on top of the VAE for reconstruction (ablation)Gen3R · TartanAir (feed-forward reconstruction)Chamfer distance: 1.6518 -> 1.5101Improved
add generative prior to VGGT reconstructionGen3R · WildRGB-D (feed-forward reconstruction)Chamfer distance: 0.1165 -> 0.1260Hurt
add generation of novel-view geometry to VGGT with 1 or 2 viewsVGGT · Co3Dv2 (1-view geometry)Chamfer distance: 2.3561 -> 1.1047Improved
use Gen3R instead of LVSM in 2-view appearance generationRealEstate10K (2-view) · RealEstate10K (2-view)PSNR: 29.58 -> 27.05Hurt

Later papers that compared with this method

1 later accepted paper reports Gen3R 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 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