欢迎访问我的个人博客: http://zengzeyu.com
paper | source - |
---|---|
O-CNN : Octree-based Convolutional Neural Networks for 3D Shape Analysis | PDF/video/code |
OctNet: Learning Deep 3D Representations at High Resolutions | PDF/video/code |
Parallel Separable 3D Convolution for Video and Volumetric Data Understanding | PDF/video/code |
PIXOR : Real-time 3D Object Detection from Point Clouds | PDF/video/code |
PointCNN | PDF/video/code |
PointNet : Deep Learning on Point Sets for 3D Classification and Segmentation | PDF/video/code |
PointNet ++ : Deep Hierarchical Feature Learning on Point Sets in a Metric Space | PDF/video/code |
Receptive Field Block Net for Accurate and Fast Object Detection | PDF/video/code |
Deep Residual Learning for Image Recognition(ResNet) | PDF/video/code |
Rethinking Atrous Convolution for Semantic Image Segmentation | PDF/video/code |
Rich feature hierarchies for accurate object detection and semantic segmentation | PDF/video/code |
Sparse 3D convolutional neural networks | PDF/video/code |
SPLATNet : Sparse Lattice Networks for Point Cloud Processing | PDF/video/code |
SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud | PDF/video/code |
The Devil of Face Recognition is in the Noise | PDF/video/code |
Understanding Convolution for Semantic Segmentation | PDF/video/code |
V-Net : Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation | PDF/video/code |
VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection | PDF/video/code |
Xception: Deep Learning with Depthwise Separable Convolutions | PDF/video/code |
PointFusion : Deep Sensor Fusion for 3D Bounding Box Estimation | PDF/video/code |
Efficient Convolutions for Real-Time Semantic Segmentation of 3D Point Clouds | PDF/video/code |
Exploring Spatial Context for 3D Semantic Segmentation of Point Clouds | PDF/video/code |
Factorized Convolutional Neural Networks | PDF/video/code |
Fast Bilateral Solver for Semantic Video Segmentation | PDF/video/code |
Fast LIDAR-based Road Detection Using Fully Convolutional Neural Networks | PDF/video/code |
FishNet : A Versatile Backbone for Image , Region , and Pixel Level Prediction | PDF/video/code |
Flattened Convolutional Neural Networks for Feedforward Acceleration | PDF/video/code |
Focal Loss for Dense Object Detection | PDF/video/code |
Frustum PointNets for 3D Object Detection from RGB-D Data | PDF/video/code |
Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes | PDF/video/code |
Fully Convolutional Networks for Semantic Segmentation | PDF/video/code |
Fully-Convolutional Point Networks for Large-Scale Point Clouds | PDF/video/code |
Fast R-CNN | PDF/video/code |
Going Deeper with Convolutions(GoogLeNet) | PDF/video/code |
Ground Estimation and Point Cloud Segmentation using SpatioTemporal Conditional Random Field | PDF/video/code |
HDNET : Exploiting HD Maps for 3D Object Detection | PDF/video/code |
Inception-V4, Inception-ResNet ad the Impact of Residual Connections on Learning | PDF/video/code |
Instance-aware Semantic Segmentation via Multi-task Network Cascades | PDF/video/code |
Joint 3D Proposal Generation and Object Detection from View Aggregation(AVOD) | PDF/video/code |
Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs | PDF/video/code |
Learning 3D Shape Completion from Laser Scan Data with Weak Supervision | PDF/video/code |
Learning a Real-Time 3D Point Cloud Obstacle Discriminator via Bootstrapping | PDF/video/code |
Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks | PDF/video/code |
Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics | PDF/video/code |
Multi-View 3D Object Detection Network for Autonomous Driving | PDF/video/code |
Not All Pixels Are Equal : Difficulty-Aware Semantic Segmentation via Deep Layer Cascade | PDF/video/code |
3D Fully Convolutional Network for Vehicle Detection in Point Cloud | PDF/video/code |
3D Semantic Segmentation with Submanifold Sparse Convolutional Networks | PDF/video/code |
3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation | PDF/video/code |
Deconvolutional Networks for Point-Cloud Vehicle Detection and Tracking in Driving Scenarios | PDF/video/code |
Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour | PDF/video/code |
Acquisition of Localization Confidence for Accurate Object Detection(IouNet) | PDF/video/code |
A Hybrid Conditional Random Field for Estimating the Underlying Ground Surface from Airborne LiDAR Data | PDF/video/code |
Batch Normalization : Accelerating Deep Network Training by Reducing Internal Covariate Shift | PDF/video/code |
BiSeNet : Bilateral Segmentation Network for Real-time Semantic Segmentation | PDF/video/code |
CNN for Very Fast Ground Segmentation in Velodyne LiDAR Data | PDF/video/code |
Complex-YOLO: An Euler-Region-Proposal for Real-time 3D Object Detection on Point Clouds | PDF/video/code |
CornerNet: Detecting Objects as Paired Keypoints | PDF/video/code |
Conditional Random Fields Meet Deep Neural Networks for Semantic Segmentation | PDF/video/code |
Decoupled Networks | PDF/video/code |
Deep Feature Pyramid Reconfiguration for Object Detection | PDF/video/code |
DropBlock : A regularization method for convolutional networks | PDF/video/code |
RoarNet: A Robust 3D Object Detection based on RegiOn Approximation Refinement | PDF/video/code |
Dropout: A simple way to prevent neural networks from overfitting | PDF/video/code |
SECOND: Sparsely Embedded Convolutional Detection | PDF/video/code |
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks | PDF/video/code |
Bag of Tricks for Image Classification with Convolutional Neural Networks | PDF/video/code |
Deformable ConvNets v2: More Deformable, Better Results | PDF/video/code |
Non-local Neural Networks | PDF/video/code |
PointPillars: Fast Encoders for Object Detection from Point Clouds | PDF/video/code |
Box2Pix : Single-Shot Instance Segmentation by Assigning Pixels to Object Boxes | PDF/video/code |
IPOD: Intensive Point-based Object Detector for Point Cloud | PDF/video/code |
Densely connected convolutional networks | PDF/video/code |
SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud | PDF/video/code |
SSD: Single Shot MultiBox Detector | PDF/video/code |
Residual Networks Behave Like Ensembles of Relatively Shallow Networks | PDF/video/code |
Single-Shot Refinement Neural Network for Object Detection (RefineDet) | PDF/video/code |
MIXED PRECISION TRAINING | PDF/video/code |
Gradient Harmonized Single-stage Detector | PDF/video/code |
Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks | PDF/video/code |
GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks | PDF/video/code |