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.
arXiv preprint arXiv:2412.00155 (2024)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
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.
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.
-
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.