arXiv Computer Vision
GSPotential: Camera Potential Field for Sparse-View 3D Gaussian Splatting
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Sep 22
VDGS: Visibility-Driven Large-Scale 3D Gaussian Splatting for Aerial Scene Reconstruction
arXiv:2609.23049v1 Announce Type: new Abstract: Large-scale scene reconstruction is a critical foundational technology in robotic autonomous systems such as 3D mapping and autonomous driving. In rece...
arXiv Computer Vision
Oct 1
FrontierGS: Progressive View-Space Frontier Expansion for Sparse 3D Gaussian Splatting
arXiv:2511.16030v3 Announce Type: replace Abstract: 3D Gaussian Splatting (3DGS) enables efficient, high-fidelity novel view synthesis, yet its performance degrades severely under sparse-view supervi...
arXiv Computer Vision
Sep 14
NOVA-GS: Noise-Aware View-Consistent Gaussian Splatting for Low-Light Novel View Synthesis
arXiv:2609.12682v1 Announce Type: new Abstract: Reconstructing 3D scenes under real-world low-light conditions remains challenging due to severe sensor noise, low signal-to-noise ratios, and degraded...
arXiv Computer Vision
Oct 2
HierGF: Hierarchical Gaussian Fields via Geometry-perception Message Passing for Sparse-view 3D Reconstruction
The paper introduces HierGF, a method for sparse‑view 3D reconstruction that uses a hierarchical geometry‑perception backbone to generate structured pseudo‑supervision from limited views. It incorporates a learnable confidence network to focus gradients on cross‑view consistent content and a geometrically consistent densification module to improve alignment and fill under‑sampled regions. This approach aims to overcome the challenges of few images and incomplete coverage that typically lead to overfitting and structural holes in existing methods.
Hugging Face Trending Papers
4d ago
ACD-GS: Asymmetric Curvature-aware Densification for 3D Gaussian Splatting
ACD-GS introduces an Asymmetric Curvature-aware Densification framework for 3D Gaussian Splatting that uses second-order depth responses to guide cloning and splitting, thereby better capturing geometric discontinuities. It incorporates a multi-view photometric consistency constraint and a capacity-aware adaptive regulation strategy to balance densification and pruning during training. The approach reduces Gaussian count and storage by nearly 60% while maintaining competitive rendering fidelity, outperforming existing methods across multiple datasets.
arXiv Computer Vision
Sep 15
Filling the Unseen: Scene Extrapolation via 3D Gaussian Splatting
arXiv:2609.13262v1 Announce Type: new Abstract: 3D Gaussian Splatting achieves photorealistic reconstruction within training view distribution, yet it degrades on out-of-distribution novel views, exh...