Stars
[TRO 2025] NeuPAN: Direct Point Robot Navigation with End-to-End Model-based Learning.
You like pytorch? You like micrograd? You love tinygrad! ❤️
[CVPR 2024] SelfOcc: Self-Supervised Vision-Based 3D Occupancy Prediction
PyTorch Implementation of EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision
[CVPR 2023] DynamicStereo: Consistent Dynamic Depth from Stereo Videos.
Official implementation of the paper: Behind the Scenes: Density Fields for Single View Reconstruction (CVPR 2023)
[CVPR 2023] Multi-frame depth estimation in dynamic scenes. -- Li, Rui, et al. "Learning to Fuse Monocular and Multi-view Cues for Multi-frame Depth Estimation in Dynamic Scenes".
The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image" and "Metric3Dv2: A Versatile Monocular Geometric Foundation Model..."
[ECCV 2022] This is the official implementation of BEVFormer, a camera-only framework for autonomous driving perception, e.g., 3D object detection and semantic map segmentation.
OpenCalib: A Multi-sensor Calibration Toolbox for Autonomous Driving
Official project website for the CVPR 2021 paper "Exploring intermediate representation for monocular vehicle pose estimation"
🔥RandLA-Net in Tensorflow (CVPR 2020, Oral & IEEE TPAMI 2021)
Bonnet: An Open-Source Training and Deployment Framework for Semantic Segmentation in Robotics.
An unofficial styleguide and best practices summary for PyTorch
[ICLR 2019] ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware
Test winograd convolution written in TVM for CUDA and AMDGPU
Translation of <Machine Learning Yearning> by Andrew NG
Open deep learning compiler stack for cpu, gpu and specialized accelerators
Chinese Translation for Machine Learning Infographics
PyTorch implementation of PNASNet-5 on ImageNet
A PyTorch implementation of Mnasnet: MnasNet: Platform-Aware Neural Architecture Search for Mobile.
Differentiable architecture search for convolutional and recurrent networks
openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system on 300+ supported cars.
A PyTorch implementation of the architecture of Mask RCNN