AI Paper Atlas

Research map / 3D vision / Gaussian splatting

SA-ResGS: Self-Augmented Residual 3D Gaussian Splatting for Next Best View Selection

Kim Jun-Seong, Tae-Hyun Oh, Eduardo Pérez Pellitero, Youngkyoon Jang

ECCV 2026 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting · 3 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 physically grounded prefiltering (SA-HashGS, MASt3R) (ablation)FisherRF · Mip-NeRF 360PSNR: 20.642 -> 21.093Improved
add physically grounded prefiltering (SA-HashGS, MASt3R) (ablation)FisherRF · Extended datasetPSNR: 19.490 -> 19.702Improved
add residual supervision (ResGS) to dynamic selection (ablation)FisherRF · Mip-NeRF 360PSNR: 20.642 -> 20.732Improved
add residual supervision (ResGS) to dynamic selection (ablation)FisherRF · Mip-NeRF 360LPIPS: 0.450 -> 0.461Hurt
add residual supervision (ResGS) with fixed view order (ablation)FisherRF · Mip-NeRF 360PSNR: 20.642 -> 21.045Improved
add residual supervision on top of SA-HashGS (MASt3R) (ablation)SA-HashGS · Mip-NeRF 360PSNR: 21.093 -> 21.410Improved
add residual supervision on top of SA-HashGS (MASt3R) (ablation)SA-HashGS · Extended datasetPSNR: 19.702 -> 20.401Improved
add residual supervision on top of SA-HashGS (MASt3R) (ablation)SA-HashGS · Mip-NeRF 360LPIPS: 0.441 -> 0.451Hurt
add residual supervision on top of SA-HashGS (DA-v3) (ablation)SA-HashGS · Extended datasetPSNR: 20.025 -> 20.348Improved
add residual supervision on top of SA-HashGS (DA-v3) (ablation)SA-HashGS · Extended datasetLPIPS: 0.357 -> 0.365Hurt
use 8 instead of 2 extrapolated views in DA-v3 SA-Points (ablation)SA-ResGS (DA-v3) · SA-Point backbone ablationPSNR: 21.247 -> 21.429Improved
add full loss to subset-only residual loss (ablation)ResGS · Mip-NeRF 360qualitativeImproved

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