Stars
Three.js-based implementation of 3D Gaussian splatting
CUDA implementation of Marching Cubes for Python (Depends on torch)
RenderDoc is a stand-alone graphics debugging tool.
code for deep learning courses
A concise but complete full-attention transformer with a set of promising experimental features from various papers
Hackable and optimized Transformers building blocks, supporting a composable construction.
Lightweight Python framework that provides a high-level API for creating and rendering scenes with Blender.
A unified framework for 3D content generation.
A collection of resources and papers on Diffusion Models
A latent text-to-image diffusion model
Mitsuba 3: A Retargetable Forward and Inverse Renderer
๐ A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support
Text-to-Image generation. The repo for NeurIPS 2021 paper "CogView: Mastering Text-to-Image Generation via Transformers".
๐ Geometric Computer Vision Library for Spatial AI
Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch
Dear PyGui: A fast and powerful Graphical User Interface Toolkit for Python with minimal dependencies
A pytorch CUDA extension implementation of instant-ngp (sdf and nerf), with a GUI.
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
Instant neural graphics primitives: lightning fast NeRF and more
A Robust, Real-time, RGB-colored, LiDAR-Inertial-Visual tightly-coupled state Estimation and mapping package
Making Structure-from-Motion (COLMAP) more robust to symmetries and duplicated structures
QMVC - Mean value coordinates for quad cages in 3D, reference implementation (J.-M. Thiery, P. Memari & T. Boubekeur, ACM SIGGRAPH Asia 2018/ACM Trans. Graph.)
Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes (CVPR 2021 Oral)
Mitsuba integration add-on for Blender