Block or Report
Block or report BwCai
Contact GitHub support about this user’s behavior. Learn more about reporting abuse.
Report abuseStars
Language
Sort by: Recently starred
Schedule-Free Optimization in PyTorch
Implementation of UltraPixel: Advancing Ultra-High-Resolution Image Synthesis to New Peaks
[ECCV 2024] Efficient Large-Baseline Radiance Fields, a feed-forward 2DGS model
[ArXiv 2024] WildAvatar: Web-scale In-the-wild Video Dataset for 3D Avatar Creation
Dual Octree Graph Networks for Learning Adaptive Volumetric Shape Representations
Differentiable Tool for Mesh2Occupancy & Mesh2SDF
Official implementation of Animate3D: Animating Any 3D Model with Multi-view Video Diffusion
Full python interactive 3D Gaussian Splatting viewer for real-time editing and analyzing.
code for "PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstruction"
Implementation of Reliable Feature-Line Driven Quad-Remeshing
[CVPR 2024 Highlight] VGGSfM Visual Geometry Grounded Deep Structure From Motion
Surf-D: Generating High-Quality Surfaces of Arbitrary Topologies Using Diffusion Models (ECCV 2024)
Controllable video and image Generation, SVD, Animate Anyone, ControlNet, LoRA
Code for "Director3D: Real-world Camera Trajectory and 3D Scene Generation from Text".
Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step
[SIGGRAPH'24] CharacterGen: Efficient 3D Character Generation from Single Images with Multi-View Pose Canonicalization
Lightplane implements a highly memory-efficient differentiable radiance field renderer, and a module for unprojecting features from images to 3D grids.
为GPT/GLM等LLM大语言模型提供实用化交互接口,特别优化论文阅读/润色/写作体验,模块化设计,支持自定义快捷按钮&函数插件,支持Python和C++等项目剖析&自译解功能,PDF/LaTex论文翻译&总结功能,支持并行问询多种LLM模型,支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, m…
A C++ & Python viewer for 3D data like meshes and point clouds
Ongoing research training gaussian splatting at scale by distributed system
Material for cuda-mode lectures
Cambrian-1 is a family of multimodal LLMs with a vision-centric design.