RefineSplat removes ambiguous distractors from 3DGS via entropy-aware adaptive masking and density control, releasing an 18-scene Ambiguous wild dataset and reporting SOTA metrics on multiple wild benchmarks.
Robustsplat: Decoupling densification and dynamics for transient-free 3dgs
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
fields
cs.CV 4years
2026 4representative citing papers
DualSplat bootstraps object-level pseudo-masks from initial 3DGS reconstruction failures using residuals and SAM2 to enable robust second-pass optimization in transient-heavy scenes.
SwiftGS predicts satellite 3D surfaces and renderings zero-shot via meta-learned Gaussian-SDF hybrid, reporting 1.22 m DSM MAE on DFC2019 at 2.5 min per scene.
A 3D Gaussian Splatting pipeline that uses a mask-aware one-step diffusion refiner, opacity-driven Gaussian densification, and LoRA/SDS regularization to do few-shot novel-view synthesis on unconstrained images with distractors.
citing papers explorer
-
Rectifying Mask via Entropy for Distractor-Free 3DGS in Ambiguous Scenarios
RefineSplat removes ambiguous distractors from 3DGS via entropy-aware adaptive masking and density control, releasing an 18-scene Ambiguous wild dataset and reporting SOTA metrics on multiple wild benchmarks.
-
DualSplat: Robust 3D Gaussian Splatting via Pseudo-Mask Bootstrapping from Reconstruction Failures
DualSplat bootstraps object-level pseudo-masks from initial 3DGS reconstruction failures using residuals and SAM2 to enable robust second-pass optimization in transient-heavy scenes.
-
SwiftGS: Episodic Priors for Immediate Satellite Surface Recovery
SwiftGS predicts satellite 3D surfaces and renderings zero-shot via meta-learned Gaussian-SDF hybrid, reporting 1.22 m DSM MAE on DFC2019 at 2.5 min per scene.
-
Difix3D-W: Distractor-Free Few-Shot 3D Gaussian Splatting in the Wild
A 3D Gaussian Splatting pipeline that uses a mask-aware one-step diffusion refiner, opacity-driven Gaussian densification, and LoRA/SDS regularization to do few-shot novel-view synthesis on unconstrained images with distractors.