REVIEW 5 cited by
GaussianRoom: Improving 3D Gaussian Splatting with SDF Guidance and Monocular Cues for Indoor Scene Reconstruction
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Embodied intelligence requires precise reconstruction and rendering to simulate large-scale real-world data. Although 3D Gaussian Splatting (3DGS) has recently demonstrated high-quality results with real-time performance, it still faces challenges in indoor scenes with large, textureless regions, resulting in incomplete and noisy reconstructions due to poor point cloud initialization and underconstrained optimization. Inspired by the continuity of signed distance field (SDF), which naturally has advantages in modeling surfaces, we propose a unified optimization framework that integrates neural signed distance fields (SDFs) with 3DGS for accurate geometry reconstruction and real-time rendering. This framework incorporates a neural SDF field to guide the densification and pruning of Gaussians, enabling Gaussians to model scenes accurately even with poor initialized point clouds. Simultaneously, the geometry represented by Gaussians improves the efficiency of the SDF field by piloting its point sampling. Additionally, we introduce two regularization terms based on normal and edge priors to resolve geometric ambiguities in textureless areas and enhance detail accuracy. Extensive experiments in ScanNet and ScanNet++ show that our method achieves state-of-the-art performance in both surface reconstruction and novel view synthesis.
Forward citations
Cited by 5 Pith papers
-
Speed Always Wins: A Survey on Efficient Architectures for Large Language Models
RayletDF predicts ray-surface distances from learned raylet segment features and shows single-forward-pass 3D surface reconstruction that generalizes across unseen indoor datasets from point clouds or pre-fit 3D Gaussians.
-
Perceptual-GS: Scene-adaptive Perceptual Densification for Gaussian Splatting
Perceptual-GS guides 3D Gaussian densification with a learnable sensitivity branch trained on binary edge maps, improving LPIPS and reducing Gaussian count compared with vanilla 3DGS.
-
SurfFill: Completion of LiDAR Point Clouds via Gaussian Surfel Splatting
SurfFill completes missing thin structures in LiDAR point clouds by focusing Gaussian surfel splatting on density-ambiguous regions surrounding the gaps.
-
Leveraging 2D Priors and SDF Guidance for Dynamic Urban Scene Rendering
UGSDF achieves state-of-the-art novel-view rendering of dynamic urban objects without LiDAR or 3D motion annotations by jointly optimizing SDFs and 3D Gaussians under 2D depth and point-tracking priors.
-
OmniIndoor3D: Comprehensive Indoor 3D Reconstruction
OmniIndoor3D jointly optimizes appearance, geometry, and panoptic labels in a single set of 3D Gaussians initialized from RGB-D camera depth, reporting state-of-the-art numbers on ScanNet and ScanNet++.
Discussion (0). Continue with ORCID to comment.