T-3DGS: Removing Transient Objects for 3D Scene Reconstruction
We propose a novel framework to remove transient objects from input videos for 3D scene reconstruction using Gaussian Splatting. Our framework consists of the following steps. In the first step, we propose an unsupervised training strategy for a classification network to distinguish between transient objects and static scene parts based on their different training behavior inside the 3D Gaussian Splatting reconstruction. In the second step, we improve the boundary quality and stability of the detected transients by combining our results from the first step with an off-the-shelf segmentation method. We also propose a simple and effective strategy to track objects in the input video forward and backward in time. Our results show an improvement over the current state of the art in existing sparsely captured datasets and significant improvements in a newly proposed densely captured (video) dataset. More results and code are available at https://transient-3dgs.github.io.
Code (0)
등록된 구현이 없습니다.
Tasks
3DGS3D Scene ReconstructionSimilar Papers 제목 키워드 기반
Image Valuation in NeRF-based 3D reconstruction
Data valuation and monetization are becoming increasingly important across domains such as eXtended Reality (XR) and digital media. In the context of 3D scene reconstruction from a set of images -- whether casually or pr…
3D ReconstructionWild3R: Feed-Forward 3D Gaussian Splatting from Unconstrained Sparse Photo Collection
Feed-forward 3D Gaussian Splatting (3DGS) removes the need for time-consuming per-scene optimization required by traditional 3DGS. However, existing feed-forward approaches struggle with real-world photo collections that…
DualSplat: Robust 3D Gaussian Splatting via Pseudo-Mask Bootstrapping from Reconstruction Failures
While 3D Gaussian Splatting (3DGS) achieves real-time photorealistic rendering, its performance degrades significantly when training images contain transient objects that violate multi-view consistency. Existing methods …
Generalizable Sparse-View 3D Reconstruction from Unconstrained Images
Reconstructing 3D scenes from sparse, unposed images remains challenging under real-world conditions with varying illumination and transient occlusions. Existing methods rely on scene-specific optimization using appearan…
Semantic Segmentation3D ReconstructionSegmentation-Guided Neural Radiance Fields for Novel Street View Synthesis
Recent advances in Neural Radiance Fields (NeRF) have shown great potential in 3D reconstruction and novel view synthesis, particularly for indoor and small-scale scenes. However, extending NeRF to large-scale outdoor en…
3D ReconstructionNeRFNovel View Synthesis