Stars
No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images
A pure pytorch implementation of 3D gaussian Splatting
Official Implementation of RTGS: Enabling Real-Time Gaussian Splatting on Mobile Devices Using Efficiency-Guided Pruning and Foveated Rendering.
DepthSplat: Connecting Gaussian Splatting and Depth
Unofficial implementation of 3D Gaussian Splatting in PyTorch + CUDA with MIT license
🌊 [ECCV'24 Oral] MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images
Integrates the vision, touch, and common-sense information of foundational models, customized to the agent's perceptual needs.
[ECCV 2024] DoubleTake: Geometry Guided Depth Estimation
Splat-SLAM: Globally Optimized RGB-only SLAM with 3D Gaussians
The first open-source system for large-scale scene reconstruction training and rendering.
[TVCG2024] PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstruction
音视频学习实践，从移植ffmpeg库到android平台，混合编译x264库以及fdk-aac库，到相机音频采集编码推流到RTMP服务器的学习记录
VF-NeRF code. We learn to densely reconstruct indoor from multi-view images by representing the surface with Vector Fields (VF). We develop a novel density-VF relationship and a training scheme tha…
GPU programming related news and material links
An implementation of the transformer architecture onto an Nvidia CUDA kernel
PyTorch Lightning Optical Flow models, scripts, and pretrained weights.
[TPAMI 2024] Fast-ACV: Fast Attention Concatenation Volume for Accurate and Real-time Stereo Matching
how to optimize some algorithm in cuda.
Nuitrack™ is a 3D tracking middleware developed by 3DiVi Inc.
official implementation of AAAI 2024 paper: IINet: Implicit Intra-Inter Information Fusion for Real-time Stereo Matching
A novel neural network architecture that can concurrently achieve real-time performance, competitive accuracy, and strong generalization ability.
📚 Tensor/CUDA Cores, 📖150+ CUDA Kernels, toy-hgemm library🔥(achieve the performance of cuBLAS 🎉🎉).