TmacTmac1992

PhotoMaker

PhotoMaker

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

street_gaussians

Code for "Street Gaussians for Modeling Dynamic Urban Scenes"

OccNeRF

Code of "OccNeRF: Self-Supervised Multi-Camera Occupancy Prediction with Neural Radiance Fields".

OccWorld

3D World Model for Autonomous Driving

OpenStereo

SelfOcc

[CVPR 2024] SelfOcc: Self-Supervised Vision-Based 3D Occupancy Prediction

Drive-WM

[CVPR 2024] A world model for autonomous driving.

LaneSegNet

[ICLR 2024] Map Learning with Lane Segment for Autonomous Driving

ViDAR

[CVPR 2024 Highlight] Visual Point Cloud Forecasting

Sparse4D

GeMap

Online Vectorized HD Map Construction using Geometry

Cam4DOcc

[CVPR 2024] Cam4DOcc: Benchmark for Camera-Only 4D Occupancy Forecasting in Autonomous Driving Applications

FlashOCC

DriveMLM

WidthFormer

WidthFormer: Toward Efficient Transformer-based BEV View Transformation

Far3D

[AAAI2024] Far3D: Expanding the Horizon for Surround-view 3D Object Detection

BEV-Planner

Linfer

基于TensorRT的C++高性能推理库，YOLOPv2，Yolov5/7/X/8，RT-DETR，单目标跟踪OSTrack、LightTrack。

talk2bev

Talk2BEV: Language-Enhanced Bird's Eye View Maps (Accepted to ICRA'24)

WoVoGen

WoVoGen: World Volume-aware Diffusion for Controllable Multi-camera Driving Scene Generation

OctreeOcc

Official implement for paper "OctreeOcc: Efficient and Multi-Granularity Occupancy Prediction Using Octree Queries"

PointBeV

Official implementation of PointBeV: A Sparse Approach to BeV Predictions

ADMap

ADMap: Anti-disturbance framework for reconstructing online vectorized HD map

DQTrack

Official PyTorch implementation of End-to-end 3D Tracking with Decoupled Queries [ICCV 2023]

UniVision

PTT

[CVPR2024] PTT: Point-Trajectory Transformer for Efficient Temporal 3D Object Detection

WechatLogger

一个mmcv 的logger hook, 可以用来把模型结果推送到微信上

GroundedSAM_OccNeRF

paradrive