Rectifying Mask via Entropy for Distractor-Free 3DGS in Ambiguous Scenarios
For 3D scene reconstruction and novel view synthesis, this work addresses the bottleneck of handling ambiguous distractors that are hard to distinguish due to color or semantic similarity.
RefineSplat introduces an entropy-aware adaptive masking method to identify and remove ambiguous distractors (e.g., transient objects) from 3D Gaussian Splatting, achieving state-of-the-art distractor-free novel view synthesis on various datasets including a new Ambiguous wild dataset.
We present RefineSplat, a systematic framework that effectively constructs transient masks to identify diverse ambiguous distractors. To do this, we qualitatively and quantitatively analyze issues and propose a novel entropy-aware adaptive masking method. Unlike existing approaches that struggle to distinguish transient elements from static scenes due to color or semantic ambiguity, RefineSplat captures ambiguous distractors leveraging entropy and instance masks. Furthermore, we propose a simple yet effective entropy-aware density control to align Gaussians in ambiguous scenarios considering Entropy-aware positional gradients. Additionally, to rigorously validate our method, we first create and release the Ambiguous wild dataset, including 18 scenes where distractors and static scenes are hard to distinguish due to color or semantic resemblances. Experimental results on various datasets demonstrate that RefineSplat shows state-of-the-art performance, showing distractor-free novel view synthesis.