ZZZENG's starred repositories
zotero-pdf-translate
Translate PDF, EPub, webpage, metadata, annotations, notes to the target language. Support 20+ translate services.
img2img-turbo
One-step image-to-image with Stable Diffusion turbo: sketch2image, day2night, and more
vokoscreenNG
vokoscreenNG is a powerful screencast creator in many languages to record the screen, an area or a window (Linux only). Recording of audio from multiple sources is supported. With the built-in camera support, you can make your video more personal. Other tools such as systray, magnifying glass, countdown, timer, Showclick and Halo support will help
X-AnyLabeling
Effortless data labeling with AI support from Segment Anything and other awesome models.
cityscapesScripts
README and scripts for the Cityscapes Dataset
wilddash_scripts
Support scripts for datasets and benchmark hosted on wilddash.cc (WildDash and RailSem)
yolov5s_bdd100k
Train a yolo v5 object detection model on Bdd100k dataset
HybridNets
HybridNets: End-to-End Perception Network
semantic-kitti-api
SemanticKITTI API for visualizing dataset, processing data, and evaluating results.
semantic_bevnet
Code repository for Semantic Terrain Classification for Off-Road Autonomous Driving (https://openreview.net/forum?id=AL4FPs84YdQ) (CoRL 2021)
patchwork-plusplus
Patchwork++: Fast and robust ground segmentation method for 3D LiDAR scans. @ IROS'22
instant-ngp
Instant neural graphics primitives: lightning fast NeRF and more
dlp-dataset
Dragon Lake Parking Dataset by MPC Lab
point_labeler
My awesome point cloud labeling tool
Codes-for-SCPNet
SCPNet: Semantic Scene Completion on Point Cloud (CVPR 2023, Highlight)
ultralytics
NEW - YOLOv8 🚀 in PyTorch > ONNX > OpenVINO > CoreML > TFLite
segment-anything
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
Swin-Transformer
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
VA-DepthNet
VA-DepthNet: A Variational Approach to Single Image Depth Prediction