zou hongwei's starred repositories
VINS-RGBD-FAST
VINS-RGBD-FAST is a SLAM system based on VINS-RGBD. We do some refinements to accelerate the system's performance in resource-constrained embedded platforms, like HUAWEI Atlas 200DK, Raspberry Pi.
voxelpose-pytorch
Official implementation of "VoxelPose: Towards Multi-Camera 3D Human Pose Estimation in Wild Environment"
StreamDiffusion
StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation
Birds-eye-view-Perception
[IEEE T-PAMI] Awesome BEV perception research and cookbook for all level audience in autonomous diriving
OutfitAnyone
Outfit Anyone: Ultra-high quality virtual try-on for Any Clothing and Any Person
EfficientSAM
EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything
joint-lidar-camera-calib
Joint intrinsic and extrinsic LiDAR-camera calibration.
HyperDreamer
(Siggraph Asia 2023) Official code of "HyperDreamer: Hyper-Realistic 3D Content Generation and Editing from a Single Image"
Kintinuous
Real-time large scale dense visual SLAM system
DeepFilterNet
Noise supression using deep filtering
awesome-tensor-compilers
A list of awesome compiler projects and papers for tensor computation and deep learning.
bicubic-plusplus
Bicubic++ (NTIRE @ CVPR 2023, Real Time Super Resolution Track 2 winner)
TensorRT-LLM
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.