AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Continuous Viewpoint Adaptation for Single View 3D Object Reconstruction

Seunghyun Hwang, Qiang Qiu

ICML 2026 · 3D vision › Gaussian splatting · approach: Regularization and primitive design for 3DGS

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 world-space camera pose input (ablation)Splatter Image · ShapeNet-Cars (short training)PSNR: 21.81 -> 22.13Improved
add filter-atom decomposition with MLP atom generator (DCF) (ablation)Splatter Image + camera · ShapeNet-Cars (short training)PSNR: 22.13 -> 22.19Improved
replace MLP atom generator with NODE conditioned on azimuth (ablation)Splatter Image + DCF · ShapeNet-Cars (short training)PSNR: 22.19 -> 22.64Improved
also condition NODE initial state on polar angle (ablation)Splatter Image + ODE(Phi) · ShapeNet-Cars (short training)PSNR: 22.64 -> 23.12Improved
full view-adaptive NODE model vs vanilla (ablation)Splatter Image · ShapeNet-Cars (short training)LPIPS: 0.166 -> 0.129Improved
continuous view-adaptive filter atoms vs Splatter ImageSplatter Image · ShapeNet-Chairs view interpolationPSNR: 21.59 -> 23.51Improved
continuous view-adaptive filter atoms vs Splatter ImageSplatter Image · ShapeNet-Chairs view extrapolationPSNR: 20.82 -> 21.48Improved
continuous view-adaptive filter atoms vs Splatter ImageSplatter Image · ShapeNet-Cars view extrapolationPSNR: 22.14 -> 22.59Improved
continuous view-adaptive filter atoms vs Splatter ImageSplatter Image · Google Scanned ObjectsPSNR: 21.06 -> 21.74Improved
continuous view-adaptive filter atoms vs Splatter Image (trained on Cars, tested on Chairs)Splatter Image · Unseen category ShapeNet-Cars trainPSNR: 14.49 -> 15.24Improved
continuous view-adaptive filter atoms vs Splatter Image (trained on Chairs)Splatter Image · Unseen category ShapeNet-Chairs trainPSNR: 16.45 -> 16.46No clear effect
continuous view-adaptive filter atoms vs Splatter ImageSplatter Image · NMR multi-category ShapeNetPSNR: 29.38 -> 29.51Improved

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