AI Paper Atlas

Research map / 3D vision / Gaussian splatting

DualSplat: Robust 3D Gaussian Splatting via Pseudo-Mask Bootstrapping from Reconstruction Failures

Xu Wang, Zhiru Wang, Shiyun Xie, Chengwei Pan, Yisong Chen

CVPR 2026 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting · 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 pseudo-masks to 3DGS (ablation)3DGS · NeRF On-the-go (mean)PSNR: 19.043 -> 22.604 (+3.56 dB)Improved
add pseudo-masks to 3DGS with delayed densification (ablation)DD · NeRF On-the-go (mean)PSNR: 20.820 -> 22.899Improved
add delayed densification to 3DGS (ablation)3DGS · NeRF On-the-go (mean)PSNR: 19.043 -> 20.820Improved
add MLP mask predictor with pseudo-mask supervision (ablation)DD+PM · NeRF On-the-go (mean)PSNR: 22.899 -> 23.262 (+0.37 dB)Improved
add robustness loss to the MLP (ablation)DD+MLP · NeRF On-the-go (mean)PSNR: 22.902 -> 23.262Improved
add pseudo-mask supervision to the MLP (ablation)DD+MLP · NeRF On-the-go (mean)PSNR: 23.122 -> 23.262Improved
add depth regularization (ablation)DD+MLP · NeRF On-the-go (mean)PSNR: 23.262 -> 23.421Improved
add depth regularization (ablation)DD+MLP · NeRF On-the-go (mean)LPIPS: 0.088 -> 0.088No clear effect
use FiT3D features instead of DINOv2 for the mask filter (ablation)mask filter · Transient mask qualityIoU: 0.744 -> 0.835Improved
use FiT3D features instead of ResNet50 (ablation)mask filter · Transient mask qualityIoU: 0.616 -> 0.835Improved
MLP-refined masks instead of FiT3D filter alone (ablation)mask filter · Transient mask qualityIoU: 0.835 -> 0.858Improved
DualSplat vs RobustSplat on transient regionsDualSplat · RobustNeRF Crab1 (inside transient regions)PSNR: 32.78 -> 33.04Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 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