AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Energy-GS: Image Energy-guided Pose Alignment Gaussian Splatting with redesigned pose gradient flow

Yu Gao, Lutong Su, Ruixiang Huang, Tianji Jiang, Jiadong Tang, Yufeng Yue, Yi Yang

CVPR 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
redesign pose gradient flow (fixed Gaussian positions, fixed tile support, no early densification) (ablation)3DGS with learnable poses · Synthetic shipPSNR: 8.08 -> 12.38Improved
redesign pose gradient flow (ablation)3DGS with learnable poses · Synthetic shiprotation error (deg): 8.572 -> 7.087Improved
add image energy control (progressive low-to-high energy supervision) on top of gradient redesign (ablation)Energy-GS · Synthetic shipPSNR: 12.38 -> 24.12Improved
add image energy control (ablation)Energy-GS · Synthetic shipATE (m): 0.150 -> 0.011Improved
add image energy control (ablation)Energy-GS · Synthetic shiprotation error (deg): 7.087 -> 1.065Improved
add learnable camera poses to plain 3DGS with only RGB supervision (ablation)3DGS · Synthetic shipPSNRHurt
add progressive alignment (energy control) after stabilizing pose gradients (ablation)Energy-GS · Synthetic scenesmulti-shell failure modeImproved
1D signal alignment: redesigned gradient flow plus energy strategy versus original gradient flow (ablation)1D signal alignment toy task · 1D signal alignmentATE: 0.1205 -> 0.0001Improved
Energy-GS vs BARF on synthetic scenes (rendering)BARF · Synthetic datasetPSNR: chair 28.35 -> 29.81No clear effect
Energy-GS vs BARF on synthetic scenes (pose)BARF · Synthetic datasetrotation error (deg): hotdog 0.653 -> 0.054Improved
Energy-GS vs 3R-GS on Mip-NeRF 3603R-GS · Mip-NeRF 360PSNR / pose error: garden PSNR 25.23 vs 22.16; stump PSNR 18.87 vs 21.75Mixed
Energy-GS vs plain 3DGS with pose gradients3DGS · Synthetic chairPSNR: 15.53 -> 29.81Improved

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