Starred repositories
Code & data for ICCV2025 paper
[NeurIPS 2025] Streaming 3D Reconstruction with Explicit Spatial Pointer Memory
A Unreal Engine 5 (UE5) based plugin aiming to provide real-time visulization, management, editing, and scalable hybrid rendering of Guassian Splatting model.
Pruna is a model optimization framework built for developers, enabling you to deliver faster, more efficient models with minimal overhead.
This is a PyTorch implementation of PointMetaBase proposed by our paper "Meta Architecure for Point Cloud Analysis"
Repository containing the code used for running the experiments of the Poincare ResNet paper
Code for "HyperSDFusion: Bridging Hierarchical Structures in Language and Geometry for Enhanced 3D Text2Shape Generation" CVPR2024
Paper list about hyperbolic embedding, hyperbolic models,hyperbolic applications
GaussianObject: High-Quality 3D Object Reconstruction from Four Views with Gaussian Splatting (SIGGRAPH Asia 2024, TOG)
Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splatting
Curated list of papers and resources focused on 3D Gaussian Splatting, intended to keep pace with the anticipated surge of research in the coming months.
A new shapenet rendering 2D image dataset that also contains deph map, normal map and albedo map.
LPIPS metric. pip install lpips
Enhancing Multimodal Compositional Reasoning of Visual Language Models with Generative Negative Mining, WACV 2024
Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"
[CVPR23] FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularization
Multi-View Mesh Reconstruction with Neural Deferred Shading (CVPR 2022)
A pytorch CUDA extension implementation of instant-ngp (sdf and nerf), with a GUI.
Learning Vision Based Autonomous Lateral Vehicle Control without Supervision
(CVPR 2020) Neural Point Cloud Rendering via Multi-Plane Projection
[CVPR 2021 - Oral] UnsupervisedR&R: Unsupervised Point Cloud Registration via Differentiable Rendering
A Unified Framework for Surface Reconstruction
[NeurIPS'22] An official PyTorch implementation of PTv2.
A data generation pipeline for creating semi-realistic synthetic multi-object videos with rich annotations such as instance segmentation masks, depth maps, and optical flow.
Self-Supervised Correspondence and Optimization-Based Scene Flow (CVPR 2023)