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.
Nexussplats: Efficient 3d gaussian splatting in the wild
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
fields
cs.CV 4years
2026 4representative citing papers
GenWildSplat is a feed-forward model that reconstructs 3D Gaussians from sparse unposed unconstrained images by predicting depth and poses with learned priors, an appearance adapter, and semantic segmentation for transients.
DF3DV-1K supplies 1,048 real scenes with clean/cluttered image pairs and a 41-scene hard subset to benchmark and improve distractor-free radiance-field methods.
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.
-
Generalizable Sparse-View 3D Reconstruction from Unconstrained Images
GenWildSplat is a feed-forward model that reconstructs 3D Gaussians from sparse unposed unconstrained images by predicting depth and poses with learned priors, an appearance adapter, and semantic segmentation for transients.
-
DF3DV-1K: A Large-Scale Dataset and Benchmark for Distractor-Free Novel View Synthesis
DF3DV-1K supplies 1,048 real scenes with clean/cluttered image pairs and a 41-scene hard subset to benchmark and improve distractor-free radiance-field methods.
-
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.