ViPA New 3D Detector. Code Will be made public.
Stars: ✭ 29 (-83.8%)
EgoNetOfficial project website for the CVPR 2021 paper "Exploring intermediate representation for monocular vehicle pose estimation"
Stars: ✭ 111 (-37.99%)
nnDetectionnnDetection is a self-configuring framework for 3D (volumetric) medical object detection which can be applied to new data sets without manual intervention. It includes guides for 12 data sets that were used to develop and evaluate the performance of the proposed method.
Stars: ✭ 355 (+98.32%)
FCOSRFCOSR: A Simple Anchor-free Rotated Detector for Aerial Object Detection
Stars: ✭ 59 (-67.04%)
Tools RosBag2KITTIConversion from ROSBAG (.bag) to image (.png) and points cloud (.bin), including ROSBAG decoding, pcd2bin and file directory extraction.
Stars: ✭ 131 (-26.82%)
FrameNetFrameNet: Learning Local Canonical Frames of 3D Surfaces from a Single RGB Image
Stars: ✭ 115 (-35.75%)
K-Net[NeurIPS2021] Code Release of K-Net: Towards Unified Image Segmentation
Stars: ✭ 434 (+142.46%)
learning-topology-synthetic-dataTensorflow implementation of Learning Topology from Synthetic Data for Unsupervised Depth Completion (RAL 2021 & ICRA 2021)
Stars: ✭ 22 (-87.71%)
SASensorProcessingROS node to create pointcloud out of stereo images from the KITTI Vision Benchmark Suite
Stars: ✭ 26 (-85.47%)
StereoNetA customized implementation of the paper "StereoNet: guided hierarchical refinement for real-time edge-aware depth prediction"
Stars: ✭ 107 (-40.22%)
SpinNet[CVPR 2021] SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration
Stars: ✭ 181 (+1.12%)
DSINDeep Image Compression using Decoder Side Information (ECCV 2020)
Stars: ✭ 39 (-78.21%)
kitti-A-LOAMEasy description to run and evaluate A-LOAM with KITTI-data
Stars: ✭ 28 (-84.36%)
continuous-fusion(ROS) Sensor fusion algorithm for camera+lidar.
Stars: ✭ 26 (-85.47%)
Indoor-SfMLearner[ECCV'20] Patch-match and Plane-regularization for Unsupervised Indoor Depth Estimation
Stars: ✭ 115 (-35.75%)
torch-points3dPytorch framework for doing deep learning on point clouds.
Stars: ✭ 1,823 (+918.44%)
BtcDetBehind the Curtain: Learning Occluded Shapes for 3D Object Detection
Stars: ✭ 104 (-41.9%)
M3DETRCode base for M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers
Stars: ✭ 47 (-73.74%)
MonoRUn[CVPR'21] MonoRUn: Monocular 3D Object Detection by Reconstruction and Uncertainty Propagation
Stars: ✭ 85 (-52.51%)
frustum-convnetThe PyTorch Implementation of F-ConvNet for 3D Object Detection
Stars: ✭ 228 (+27.37%)
efficient online learningEfficient Online Transfer Learning for 3D Object Detection in Autonomous Driving
Stars: ✭ 20 (-88.83%)
labelCloudA lightweight tool for labeling 3D bounding boxes in point clouds.
Stars: ✭ 264 (+47.49%)
FLAT[ICCV2021 Oral] Fooling LiDAR by Attacking GPS Trajectory
Stars: ✭ 52 (-70.95%)
From-Voxel-to-Point"From Voxel to Point: IoU-guided 3D Object Detection for Point Cloud with Voxel-to-Point Decoder" and "Anchor-free 3D Single Stage Detector with Mask-Guided Attention for Point Cloud" in ACM MM 2021.
Stars: ✭ 29 (-83.8%)
lidar transferCode for Langer et al. "Domain Transfer for Semantic Segmentation of LiDAR Data using Deep Neural Networks", IROS, 2020.
Stars: ✭ 54 (-69.83%)
parallel mAP evaluationThis repo parallelizes mAP_evaluation using python's multiprocessing module.
Stars: ✭ 18 (-89.94%)
pillar-motionSelf-Supervised Pillar Motion Learning for Autonomous Driving (CVPR 2021)
Stars: ✭ 98 (-45.25%)
QueryInstInstances as Queries (ICCV 2021)
Stars: ✭ 325 (+81.56%)
OrientedRepPoints DOTAOriented Object Detection: Oriented RepPoints + Swin Transformer/ReResNet
Stars: ✭ 62 (-65.36%)
TNCR DatasetDeep learning, Convolutional neural networks, Image processing, Document processing, Table detection, Page object detection, Table classification. https://www.sciencedirect.com/science/article/pii/S0925231221018142
Stars: ✭ 37 (-79.33%)