#
Starred repositories
LiDAR-NeRF: Novel LiDAR View Synthesis via Neural Radiance Fields
💫 [CVPR 2024] LiDAR4D: Dynamic Neural Fields for Novel Space-time View LiDAR Synthesis
[CVPR 2023 Highlight] Neural Kernel Surface Reconstruction
LimSim & LimSim++: Integrated traffic and autonomous driving simulators with (M)LLM support
A general map auto annotation framework based on MapTR, with high flexibility in terms of spatial scale and element type
This is the official code base of VectorMapNet (ICML 2023)
Implementation of "GaussianFusion: Gaussian-Based Multi-Sensor Fusion for End-to-End Autonomous Driving"
[CVPR2025] Omni-Scene: Omni-Gaussian Representation for Ego-Centric Sparse-View Scene Reconstruction
[CVPR 2025] LiDAR-RT: Gaussian-based Ray Tracing for Dynamic LiDAR Re-simulation
There are some python scripts processing dataset, inferencing etc. wrote when I am using OpenMMLab.
Code for the paper entitled "Keep your Eyes on the Lane: Real-time Attention-guided Lane Detection" (CVPR 2021)
[CVPR 2023 Highlight] InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions
The simplest, fastest repository for training/finetuning small-sized VLMs.
CurveLanes is a new benchmark lane detection dataset with 150K lanes images for difficult scenarios such as curves and multi-lanes in traffic lane detection. It is collected in real urban and highw…
[CVPR 2024] PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentation
TICMapNet A Tightly Coupled Temporal Fusion Pipeline for End-to-End HD Map Construction
GussianPretrain for Visual Pre-training in Autonomous Driving, showcasing significant improvements across various 3D perception tasks, including 3D object detection, HD-map construction, and Occupa…
Low rank adaptation for segmentation anything model (SAM)
[CVPR 2024] Code for "Improving the Generalization of Segmentation Foundation Model under Distribution Shift via Weakly Supervised Adaptation"
CnOCR: Awesome Chinese/English OCR Python toolkits based on PyTorch. It comes with 20+ well-trained models for different application scenarios and can be used directly after installation. 【基于 PyTor…
[CVPR 2025] StreetCrafter: Street View Synthesis with Controllable Video Diffusion Models
RoGs: Large Scale Road Surface Reconstruction with Meshgrid Gaussian
Official PyTorch implementation of "GaussianLSS - Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting" (CVPR 2025).
[CVPR 2025 Best Paper Nomination] FoundationStereo: Zero-Shot Stereo Matching
[CVPR 2025] UniScene: Unified Occupancy-centric Driving Scene Generation
Official implementation of our RAL'24 paper: Multi-Camera Unified Pre-training for Autonomous Driving
WideRange4D: Enabling High-Quality 4D Reconstruction with Wide-Range Movements and Scenes
Official PyTorch implementation of the paper “LCCNet: Lidar and Camera Self-Calibration usingCost Volume Network”.
Deep Learning for Camera Calibration and Beyond: A Survey