Stars
Recommend new arxiv papers of your interest daily according to your Zotero libarary.
This repository use GPUs to expedite the point cloud evaluation process on DTUs, utilizing Python and CUDA.
Code of π^3: Permutation-Equivariant Visual Geometry Learning
SpatialVID: A Large-Scale Video Dataset with Spatial Annotations
Lightning fast differentiable SSIM.
[CVPR 2022 Oral] Multi-View Depth Estimation by Fusing Single-View Depth Probability with Multi-View Geometry
[ECCV 2022] SimpleRecon: 3D Reconstruction Without 3D Convolutions
🌊 [ECCV'24 Oral] MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
Official implementation for "DMesh++: An Efficient Differentiable Mesh for Complex Shapes".
Official implementation for "DMesh: A Differentiable Representation for General Meshes" (NeurIPS 2024)
[SIGGRAPH Asia'24 & TOG] Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenes
A geometry-shader-based, global CUDA sorted high-performance 3D Gaussian Splatting rasterizer. Can achieve a 5-10x speedup in rendering compared to the vanialla diff-gaussian-rasterization.
[ECCV`24&ICLR`25] CityGaussian Series for High-quality Large-Scale Scene Reconstruction with Gaussians
[ICLR 2025] Flow Distillation Sampling: Regularizing 3D Gaussians with Pre-trained Matching Priors
[CVPR 2025] Official repo for "FATE: Full-head Gaussian Avatar with Textural Editing from Monocular Video"
[AAAI'24] NeuSurf: On-Surface Priors for Neural Surface Reconstruction from Sparse Input Views
A cross-platform, high performance renderer for Gaussian Splatting using Vulkan Compute. Supports Windows, Linux, macOS, iOS, and visionOS
Vulkan-based Gaussian Splatting viewer, and python binding
Official implementation of "Neuralangelo: High-Fidelity Neural Surface Reconstruction" (CVPR 2023)
RenderDoc is a stand-alone graphics debugging tool.