-
Zhejiang University
- HangZhou,China
Stars
Zhejiang University Graduation Thesis LaTeX Template
Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation".
The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.
A procedural Blender pipeline for photorealistic training image generation
[CVPR 2024] Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion Models, a no lighting baked texture generative model
A fast and robust point cloud registration library
Python bindings to the pointcloud library (pcl)
Open3D: A Modern Library for 3D Data Processing
Papers and Datasets about Point Cloud.
[ICLR 2024 spotlight] Official implementation of "InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Prior".
Code for "ATISS: Autoregressive Transformers for Indoor Scene Synthesis", NeurIPS 2021
PyTorch-based differentiable material graph library for procedural material capture
Awesome 3D Stylization - Advances in 3D Neural Stylization
Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussians
Lightplane implements a highly memory-efficient differentiable radiance field renderer, and a module for unprojecting features from images to 3D grids.
Neural Surface reconstruction based on Instant-NGP. Efficient and customizable boilerplate for your research projects. Train NeuS in 10min!
Cuda implementation for gridsample with second derivative support
[CVPR 2023] TensoIR: Tensorial Inverse Rendering
[CVPR2024 (Highlight)] RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3D. Live Demo:https://modelscope.cn/studios/Damo_XR_Lab/3D_AIGC
Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation