AnsonYanxin's repositories
apollo-1
Apollo: An Adaptive Parameter-wise Diagonal Quasi-Newton Method for Nonconvex Stochastic Optimization
PV-RCNN
3D object detection in PyTorch.
cnn-explainer
Learning Convolutional Neural Networks with Interactive Visualization.
Depix
Recovers passwords from pixelized screenshots
FEANet
[IROS 2021] : FEANet with RGB-Thermal
first_steps_mediapipe
First steps with Google Mediapipe in C++: An Informal tutorial
meshroom
3D Reconstruction Software
MVision
机器人视觉 移动机器人 VS-SLAM ORB-SLAM2 深度学习目标检测 yolov3 行为检测 opencv PCL 机器学习 无人驾驶
nn_vis
A project for processing neural networks and rendering to gain insights on the architecture and parameters of a model through a decluttered representation.
ODM
A command line toolkit to generate maps, point clouds, 3D models and DEMs from drone, balloon or kite images. 📷
patchmatch
patchmatch和patchmatchstereo算法的python实现
PatchmatchNet
Official code of PatchmatchNet (CVPR 2021 Oral)
pytorch-image-models
PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more
pytorch-loss
label-smooth, amsoftmax, partial-fc, focal-loss, triplet-loss, lovasz-softmax. Maybe useful
QueryInst
Instances as Queries (ICCV 2021)
r3live
A Robust, Real-time, RGB-colored, LiDAR-Inertial-Visual tightly-coupled state Estimation and mapping package
RealtimeStereo
Attention-Aware Feature Aggregation for Real-time Stereo Matching on Edge Devices (ACCV, 2020)
RobustVideoMatting
Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!
RTFNet
RGB-Thermal Fusion Network for Semantic Segmentation of Urban Scenes
TEASER-plusplus
A fast and robust point cloud registration library
unimatch
[TPAMI'23] Unifying Flow, Stereo and Depth Estimation
vision
Datasets, Transforms and Models specific to Computer Vision
vision-based-robotic-grasping
Related papers and codes for vision-based robotic grasping
Yolo-Fastest
:zap: Based on yolo's ultra-lightweight universal target detection algorithm, the calculation amount is only 250mflops, the ncnn model size is only 666kb, the Raspberry Pi 3b can run up to 15fps+, and the mobile terminal can run up to 178fps+
Yolo-FastestV2
:zap: Based on Yolo's low-power, ultra-lightweight universal target detection algorithm, the parameter is only 250k, and the speed of the smart phone mobile terminal can reach ~300fps+
YOLOP
You Only Look Once for Panopitic Driving Perception.(https://arxiv.org/abs/2108.11250)
YOLOX
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with ONNX, TensorRT, ncnn, and OpenVINO supported.