AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Generalizable Sparse-View 3D Reconstruction from Unconstrained Images

Vinayak Gupta, Chih-Hao Lin, Shenlong Wang, Anand Bhattad, Jia-Bin Huang

CVPR 2026 · 3D vision › Gaussian splatting · approach: Sparse-view Gaussian splatting for novel views · 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 appearance adapter (ablation)GenWildSplat · MegaScenesPSNR: 13.76 -> 15.84Improved
add appearance adapter (ablation)GenWildSplat · MegaScenesLPIPS: 0.405 -> 0.407No clear effect
add occlusion handling (ablation)GenWildSplat · MegaScenesLPIPS: 0.513 -> 0.407Improved
add occlusion handling (ablation)GenWildSplat · MegaScenesPSNR: 15.14 -> 15.84Improved
add curriculum learning (ablation)GenWildSplat · MegaScenesPSNR: 11.72 -> 15.84Improved
add curriculum learning (ablation)GenWildSplat · MegaScenesSSIM: 0.318 -> 0.440Improved
add appearance adapter (ablation)GenWildSplat · MegaScenesSSIM: 0.391 -> 0.440Improved
use GenWildSplat feed-forward instead of NexusSplats optimization (6 views)GenWildSplat · MegaScenes (6-View)PSNR: 13.92 -> 15.84Improved
use GenWildSplat instead of DiffusionRenderer + AnySplatAnySplat · MegaScenesPSNR: 13.59 -> 15.84Improved
use GenWildSplat instead of vanilla AnySplatAnySplat · MegaScenesPSNR: 12.65 -> 15.84Improved
use GenWildSplat instead of vanilla AnySplatAnySplat · MegaScenesLPIPS: 0.412 -> 0.407No 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