arXiv Computer Vision

Prior-Driven Enhancements in 3D Gaussian Splatting: Normals and Depths Regularization

arXiv Computer Vision
6d ago

DepthGS: Depth-Guided Gaussian Splatting with Adaptive Regularization for High-Quality Surface Reconstruction

DepthGS introduces a depth-guided Gaussian splatting framework that leverages depth discrepancies to bound reconstruction error in both single-view and multi-view settings. The method proposes adaptive normal regularization for single-view optimization and cross-view depth consistency regularization for multi-view optimization, guided by theoretical depth-error relationships. Experiments on DTU, Mip-NeRF360, and Tanks and Temples show that DepthGS achieves competitive performance in surface reconstruction and novel view synthesis.

By Xiao Ren, Yu Liu, Ning An, Jian Cheng, Xin Qiao, You-Fu Li, He Kong
arXiv Computer Vision
Sep 18

RGS: Reflection-aware Gaussian Splatting via Learning Geometry Continuity for Reflective Objects

The paper introduces Reflection-aware Gaussian Splatting (RGS), a physically-based deferred rendering framework that improves novel view synthesis for reflective objects. RGS leverages a powerful 3D foundation model to provide a strong geometric prior and employs cross-view shape consistency regularization to prevent surface collapse and reduce geometric hollows. Additionally, a reflection-aware densification strategy captures specular variations across views, resulting in higher-quality renderings of reflective objects.

By Xiaobiao Du, Yida Wang, Cheng Bi, Kun Zhan, Xin Yu
Hugging Face Trending Papers
Aug 19

CoMVS-GS: Collaborative Multi-View Stereo and 3D Gaussian Splatting for Surface Reconstruction

CoMVS‑GS is a surface‑reconstruction framework that fuses Multi‑View Stereo (MVS) with 3D Gaussian splatting. It initializes Gaussian primitives from dense MVS points, uses PatchMatch‑3DGS mutual supervision to refine depths and normals, and replaces voxel‑based meshing with a Delaunay graph‑cut pipeline. Experiments on DTU, GauU‑Scene V2, and MatrixCity demonstrate competitive object‑level results and improved geometric accuracy and mesh compactness in outdoor scenes while preserving high rendering quality.

Hugging Face Trending Papers
Aug 3

D^2-4DGS: Dual-Depth Guided Sparse-Camera 4D Gaussian Splatting

Dynamic 4D Gaussian Splatting has emerged as an efficient representation for dynamic novel view synthesis through explicit scene modeling and real-time rendering. However, existing methods typically require dense multi-view videos for sufficient geometric constraints, making capture expensive and limiting sparse-camera deployment.

Hugging Face Trending Papers
Jun 29

StereoGS: Sparse-View 3D Gaussian Splatting via Stereo Priors

3D Gaussian Splatting (3DGS) has achieved remarkable success in real-time novel view synthesis, yet it suffers from severe overfitting under sparse-view settings due to insufficient geometric constraints. While recent methods introduce monocular depth priors to mitigate this, they inherently struggle with scale ambiguity and cross-view inconsistency, leading to defective geometry.

arXiv Computer Vision
Aug 25

GaussVid: Sparse-View Gaussian Splatting with 3D-Aware Video Diffusion Priors

GaussVid introduces a 3D-aware video restoration framework that enhances sparse-view 3D Gaussian Splatting (3DGS) reconstructions. By creating a large-scale 3DGS video dataset and employing a camera-conditioned geometric prior anchored on the first and last frames, the method injects spatial structure into video generation, ensuring geometrically grounded restoration across viewpoints. Experiments demonstrate superior pixel- and structure-level fidelity (PSNR/SSIM) and improved multi-view consistency compared to other video-prior restoration methods, while maintaining competitive perceptual quality (LPIPS).

By Xinhui Liu, Can Wang, Wei Jiang, Wei Wang, Dong Xu
arXiv Computer Vision
Sep 24

GaussianDS: Depth-supervised Semantic Gaussian Splatting for Scene Understanding

GaussianDS introduces a depth‑supervised framework for 3D Gaussian Splatting that jointly optimizes RGB appearance, depth, and compact semantics from scratch. By arranging multi‑view images into a pose‑aware pseudo‑video and propagating view‑consistent masks via SAM2, the method aligns semantic lifting with geometric cues, using depth supervision and edge‑aware refinement to curb semantic drift and boundary leakage. The approach achieves state‑of‑the‑art performance on LERF and 3D‑OVS benchmarks while preserving high‑fidelity reconstruction and enabling downstream tasks such as 3D object removal.

By Yufei Zhang, Chenlu Zhan, Hongwei Wang
Hugging Face Trending Papers
Nov 2

OctreeSplat: Hierarchical Octree-Guided Feed-Forward Gaussian Splatting

OctreeSplat introduces a hierarchical octree-guided feed‑forward Gaussian splatting method that extracts multi‑view features and geometric priors from a frozen visual foundation model. By constructing a hierarchical octree and predicting densification scores, it allocates Gaussian primitives at spatially varying densities, improving depth rendering and surface reconstruction. The approach requires only 76 million additional parameters and 35 GPU‑hours to train, and demonstrates competitive RGB view synthesis, depth synthesis, and surface reconstruction on Replica, TUM, Tanks and Temples, and DTU datasets while reducing the number of Gaussian primitives needed.

arXiv AI
Sep 4

TruncGradGS: Improved 3D Gaussian Splatting via Truncated Gradient Updates

The paper introduces TruncGradGS, a piecewise truncated gradient approach that mitigates gradient vanishing in 3D Gaussian Splatting, enhancing optimization stability and robustness to initializations. It demonstrates consistent improvements over random and COLMAP initializations in both static and dynamic settings. Additionally, the authors highlight limitations of existing dynamic scene benchmarks and present a new synthetic dataset for evaluating dynamic Gaussian Splatting.

By Theo Morales, Nhat-Quynh Le-Pham, Robin Atkins, Binh-Son Hua