SimpleViewOfficial Code for ICML 2021 paper "Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline"
Stars: ✭ 95 (+37.68%)
FpconvFPConv: Learning Local Flattening for Point Convolution, CVPR 2020
Stars: ✭ 114 (+65.22%)
mix3dMix3D: Out-of-Context Data Augmentation for 3D Scenes (3DV 2021 Oral)
Stars: ✭ 183 (+165.22%)
Superpoint graphLarge-scale Point Cloud Semantic Segmentation with Superpoint Graphs
Stars: ✭ 533 (+672.46%)
pointnet2-pytorchA clean PointNet++ segmentation model implementation. Support batch of samples with different number of points.
Stars: ✭ 45 (-34.78%)
Cylinder3dRank 1st in the leaderboard of SemanticKITTI semantic segmentation (both single-scan and multi-scan) (Nov. 2020) (CVPR2021 Oral)
Stars: ✭ 221 (+220.29%)
AsisAssociatively Segmenting Instances and Semantics in Point Clouds, CVPR 2019
Stars: ✭ 228 (+230.43%)
AIODriveOfficial Python/PyTorch Implementation for "All-In-One Drive: A Large-Scale Comprehensive Perception Dataset with High-Density Long-Range Point Clouds"
Stars: ✭ 32 (-53.62%)
Segmentation-Series-ChaosSummary and experiment includes basic segmentation, human segmentation, human or portrait matting for both image and video.
Stars: ✭ 75 (+8.7%)
point-cloud-predictionSelf-supervised Point Cloud Prediction Using 3D Spatio-temporal Convolutional Networks
Stars: ✭ 97 (+40.58%)
cpnetLearning Video Representations from Correspondence Proposals (CVPR 2019 Oral)
Stars: ✭ 93 (+34.78%)
graspnet-baselineBaseline model for "GraspNet-1Billion: A Large-Scale Benchmark for General Object Grasping" (CVPR 2020)
Stars: ✭ 146 (+111.59%)
satellite-Image-Semantic-Segmentation-Unet-Tensorflow-kerasCollection of different Unet Variant suchas VggUnet, ResUnet, DenseUnet, Unet. AttUnet, MobileNetUnet, NestedUNet, R2AttUNet, R2UNet, SEUnet, scSEUnet, Unet_Xception_ResNetBlock
Stars: ✭ 43 (-37.68%)
HoHoNet"HoHoNet: 360 Indoor Holistic Understanding with Latent Horizontal Features" official pytorch implementation.
Stars: ✭ 65 (-5.8%)
DLCV2018SPRINGDeep Learning for Computer Vision (CommE 5052) in NTU
Stars: ✭ 38 (-44.93%)
hsn v1HistoSegNet: Semantic Segmentation of Histological Tissue Type in Whole Slide Images (ICCV 2019)
Stars: ✭ 65 (-5.8%)
DST-CBCImplementation of our paper "DMT: Dynamic Mutual Training for Semi-Supervised Learning"
Stars: ✭ 98 (+42.03%)
lowshot-shapebiasLearning low-shot object classification with explicit shape bias learned from point clouds
Stars: ✭ 37 (-46.38%)
CurveNetOfficial implementation of "Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis", ICCV 2021
Stars: ✭ 94 (+36.23%)
Lyft-Perception-ChallengeThe 4th place and the fastest solution of the Lyft Perception Challenge (Image semantic segmentation with PyTorch)
Stars: ✭ 69 (+0%)
LightNetLightNet: Light-weight Networks for Semantic Image Segmentation (Cityscapes and Mapillary Vistas Dataset)
Stars: ✭ 710 (+928.99%)
SenseEarth2020-ChangeDetection1st place solution to the Satellite Remote Sensing Image Change Detection Challenge hosted by SenseTime
Stars: ✭ 156 (+126.09%)
EntityEntitySeg Toolbox: Towards Open-World and High-Quality Image Segmentation
Stars: ✭ 313 (+353.62%)
sp segmenterSuperpixel-based semantic segmentation, with object pose estimation and tracking. Provided as a ROS package.
Stars: ✭ 33 (-52.17%)
self-sampleSingle shape Deep Point Cloud Consolidation [TOG 2021]
Stars: ✭ 33 (-52.17%)
M3DETRCode base for M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers
Stars: ✭ 47 (-31.88%)
InstantDLInstantDL: An easy and convenient deep learning pipeline for image segmentation and classification
Stars: ✭ 33 (-52.17%)
RealSenseExtension of RealSense Unity Wrapper [Unofficial]
Stars: ✭ 31 (-55.07%)
urban road filterReal-time LIDAR-based Urban Road and Sidewalk detection for Autonomous Vehicles 🚗
Stars: ✭ 134 (+94.2%)
HugsVisionHugsVision is a easy to use huggingface wrapper for state-of-the-art computer vision
Stars: ✭ 154 (+123.19%)
costmap depth cameraThis is a costmap plugin for costmap_2d pkg. This plugin supports multiple depth cameras and run in real time.
Stars: ✭ 26 (-62.32%)
volumentationsAugmentation package for 3d data based on albumentaitons
Stars: ✭ 26 (-62.32%)
BtcDetBehind the Curtain: Learning Occluded Shapes for 3D Object Detection
Stars: ✭ 104 (+50.72%)
mobilenet segmentationBinary semantic segmentation with UNet based on MobileNetV2 encoder
Stars: ✭ 18 (-73.91%)
LoveDA[NeurIPS2021 Poster] LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation
Stars: ✭ 111 (+60.87%)
FCNN-exampleThis is a fully convolutional neural net exercise to detect houses from aerial images.
Stars: ✭ 28 (-59.42%)
Iterative-Closest-PointImplementation of the iterative closest point algorithm. A point cloud is transformed such that it best matches a reference point cloud.
Stars: ✭ 101 (+46.38%)
torch-points3dPytorch framework for doing deep learning on point clouds.
Stars: ✭ 1,823 (+2542.03%)
lepccPoint Cloud Compression used in i3s Scene Layer Format
Stars: ✭ 22 (-68.12%)
recurrent-decoding-cell[AAAI'20] Segmenting Medical MRI via Recurrent Decoding Cell (Spotlight)
Stars: ✭ 14 (-79.71%)
lvr2Las Vegas Reconstruction 2.0
Stars: ✭ 39 (-43.48%)
DL NotesDL & CV & Neural Network
Stars: ✭ 29 (-57.97%)
night image semantic segmentation[ICIP 2019] : This is the official github repository for the paper "What's There in The Dark" accepted in IEEE International Conference in Image Processing 2019 (ICIP19) , Taipei, Taiwan.
Stars: ✭ 25 (-63.77%)
ObjectNetPyTorch implementation of "Pyramid Scene Parsing Network".
Stars: ✭ 15 (-78.26%)
Dilation-Pytorch-Semantic-SegmentationA PyTorch implementation of semantic segmentation according to Multi-Scale Context Aggregation by Dilated Convolutions by Yu and Koltun.
Stars: ✭ 32 (-53.62%)
Robust-Semantic-SegmentationDynamic Divide-and-Conquer Adversarial Training for Robust Semantic Segmentation (ICCV2021)
Stars: ✭ 25 (-63.77%)
plussegShanghaiTech PLUS Lab Segmentation Toolbox and Benchmark
Stars: ✭ 21 (-69.57%)
pyconvsegnetSemantic Segmentation PyTorch code for our paper: Pyramidal Convolution: Rethinking Convolutional Neural Networks for Visual Recognition (https://arxiv.org/pdf/2006.11538.pdf)
Stars: ✭ 32 (-53.62%)
cloud to mapAlgorithm that converts point cloud data into an occupancy grid
Stars: ✭ 26 (-62.32%)
BMW-Anonymization-APIThis repository allows you to anonymize sensitive information in images/videos. The solution is fully compatible with the DL-based training/inference solutions that we already published/will publish for Object Detection and Semantic Segmentation.
Stars: ✭ 121 (+75.36%)
PixiePixie is a GUI annotation tool which provides the bounding box, polygon, free drawing and semantic segmentation object labelling
Stars: ✭ 52 (-24.64%)