AI Paper Atlas

Research map / 3D vision / Gaussian splatting

BEA-GS: BEyond RAdiance Supervision in 3DGS for Precise Object Extraction

Alessio Mazzucchelli, Maria Naranjo-Almeida, Jorge Bustos-Sanchez, Mariella Dimiccoli, Francesc Moreno-Noguer, Jordi Sanchez-Riera, Adrian Penate-Sanchez

CVPR 2026 · 3D vision › Gaussian splatting · approach: Regularization and primitive design for 3DGS · 0 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 occupancy loss to reprojection plus boundary loss (ablation)BEA-GS · LeRFIoU: 78.2 -> 89.4Improved
add occupancy loss to reprojection plus boundary loss (ablation)BEA-GS · Mip-NeRF 360IoU: 90.5 -> 92.0Improved
add boundary loss to reprojection plus occupancy loss (ablation)BEA-GS · LeRFIoU: 85.0 -> 89.4Improved
add boundary loss to reprojection plus occupancy loss (ablation)BEA-GS · Mip-NeRF 360BIoU: 81.9 -> 85.8Improved
add multiview reprojection to boundary plus occupancy losses (ablation)BEA-GS · LeRFIoU: 86.6 -> 89.4Improved
add multiview reprojection to boundary plus occupancy losses (ablation)BEA-GS · Mip-NeRF 360IoU: 90.9 -> 92.0Improved
add multiview reprojection to boundary plus occupancy losses (ablation)BEA-GS · LLFFIoU: 93.0 -> 93.0No clear effect
add multiview reprojection to boundary plus occupancy losses (ablation)BEA-GS · 3DOVSIoU: 93.3 -> 93.2No clear effect
add all three components to the vanilla assignment baseline (ablation)BEA-GS · LeRFIoU: 66.3 -> 89.4Improved
train on noisy depth and normals (no regularization) (ablation)BEA-GS · 3DOVSIoU: 93.2 -> 89.8Hurt
train on noisy depth and normals (no regularization) (ablation)BEA-GS · Mip-NeRF 360IoU: 92.0 -> 92.3No clear effect
increase voxel-density points k from 250 to 5000 (ablation)BEA-GS · LeRFIoU: 90.4 -> 88.3Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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