H3DNet: 3D Object Detection Using Hybrid Geometric Primitives

@inproceedings{Zhang2020H3DNet3O,
  title={H3DNet: 3D Object Detection Using Hybrid Geometric Primitives},
  author={Zaiwei Zhang and Bo Sun and Haitao Yang and Qi-Xing Huang},
  booktitle={ECCV},
  year={2020}
}
We introduce H3DNet, which takes a colorless 3D point cloud as input and outputs a collection of oriented object bounding boxes (or BB) and their semantic labels. The critical idea of H3DNet is to predict a hybrid set of geometric primitives, i.e., BB centers, BB face centers, and BB edge centers. We show how to convert the predicted geometric primitives into object proposals by defining a distance function between an object and the geometric primitives. This distance function enables… Expand
Back-tracing Representative Points for Voting-based 3D Object Detection in Point Clouds
TLDR
This work introduces a new 3D object detection method, named as Back-tracing Representative Points Network (BRNet), which generatively back-traces the representative points from the vote centers and also revisits complementary seed points around these generated points, so as to better capture the fine local structural features surrounding the potential objects from the raw point clouds. Expand
Self-Supervised Pretraining of 3D Features on any Point-Cloud
TLDR
This work presents a simple self-supervised pretraining method that can work with any 3D data — single or multiview, indoor or outdoor, acquired by varied sensors, without 3D registration, and sets a new state-of-the-art for object detection on ScanNet and SUNRGBD. Expand
Interpolation-Aware Padding for 3D Sparse Convolutional Neural Networks
TLDR
This work proposes a simple yet effective padding scheme — interpolation-aware padding to pad a few empty voxel adjacent to the non-empty voxels and involve them in the 3D CNN computation so that all neighboring voxela exist when computing point-wise features via the trilinear interpolation. Expand
An End-to-End Transformer Model for 3D Object Detection
TLDR
It is found that a standard Transformer with non-parametric queries and Fourier positional embeddings is competitive with specialized architectures that employ libraries of 3Dspecific operators with hand-tuned hyperparameters. Expand
PQ-Transformer: Jointly Parsing 3D Objects and Layouts from Point Clouds
TLDR
This work proposes the first transformer architecture that predicts 3D objects and layouts simultaneously, using point cloud inputs, and directly parameterize room layout as a set of quads, termed as P(oint)Q(uad)-Transformer. Expand
SparsePoint: Fully End-to-End Sparse 3D Object Detector
TLDR
This paper proposes SparsePoint, the first sparse method for 3D object detection, which adopts a number of learnable proposals to encode most likely potential positions of 3D objects and a foreground embedding to encode shared semantic features of all objects. Expand
Group-Free 3D Object Detection via Transformers
TLDR
This paper presents a simple yet effective method for directly detecting 3D objects from the 3D point cloud with the help of an attention mechanism in the Transformers, where the contribution of each point is automatically learned in the network training. Expand
3D Object Detection with Pointformer
TLDR
This paper proposes Pointformer, a Transformer backbone designed for 3D point clouds to learn features effectively, and introduces an efficient coordinate refinement module to shift down-sampled points closer to object centroids, which improves object proposal generation. Expand
3D Spatial Recognition without Spatially Labeled 3D
TLDR
WyPR is introduced, a Weakly-supervised framework for Point cloud Recognition, requiring only scene-level class tags as supervision, and can detect and segment objects in point cloud data without access to any spatial labels at training time. Expand
3DRM: Pair-wise relation module for 3D object detection
TLDR
It is argued that scene understanding benefits from object relation reasoning, which is capable of mitigating the ambiguity of 3D object detections and thus helps locate and classify the 3D objects more accurately and robustly. Expand
...
1
2
...

References

SHOWING 1-10 OF 62 REFERENCES
Deep Hough Voting for 3D Object Detection in Point Clouds
TLDR
This work proposes VoteNet, an end-to-end 3D object detection network based on a synergy of deep point set networks and Hough voting that achieves state-of-the-art 3D detection on two large datasets of real 3D scans, ScanNet and SUN RGB-D with a simple design, compact model size and high efficiency. Expand
Three-Dimensional Object Detection and Layout Prediction Using Clouds of Oriented Gradients
TLDR
A cloud of oriented gradient (COG) descriptor is proposed that links the 2D appearance and 3D pose of object categories, and thus accurately models how perspective projection affects perceived image boundaries, in 3D object detection and spatial layout prediction in cluttered indoor scenes. Expand
2D-Driven 3D Object Detection in RGB-D Images
TLDR
The approach makes best use of the 2D information to quickly reduce the search space in 3D, benefiting from state-of-the-art 2D object detection techniques. Expand
PointRCNN: 3D Object Proposal Generation and Detection From Point Cloud
TLDR
Extensive experiments on the 3D detection benchmark of KITTI dataset show that the proposed architecture outperforms state-of-the-art methods with remarkable margins by using only point cloud as input. Expand
Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Images
  • Shuran Song, J. Xiao
  • Computer Science
  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
TLDR
This work proposes the first 3D Region Proposal Network (RPN) to learn objectness from geometric shapes and the first joint Object Recognition Network (ORN) to extract geometric features in 3D and color features in 2D. Expand
Frustum PointNets for 3D Object Detection from RGB-D Data
TLDR
This work directly operates on raw point clouds by popping up RGBD scans and leverages both mature 2D object detectors and advanced 3D deep learning for object localization, achieving efficiency as well as high recall for even small objects. Expand
Sliding Shapes for 3D Object Detection in Depth Images
TLDR
This paper proposes to use depth maps for object detection and design a 3D detector to overcome the major difficulties for recognition, namely the variations of texture, illumination, shape, viewpoint, clutter, occlusion, self-occlusion and sensor noises. Expand
VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection
  • Yin Zhou, Oncel Tuzel
  • Computer Science
  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2018
TLDR
VoxelNet is proposed, a generic 3D detection network that unifies feature extraction and bounding box prediction into a single stage, end-to-end trainable deep network and learns an effective discriminative representation of objects with various geometries, leading to encouraging results in3D detection of pedestrians and cyclists. Expand
Extreme Relative Pose Network Under Hybrid Representations
TLDR
A novel RGB-D based relative pose estimation approach that is suitable for small-overlapping or non- overlapping scans and can output multiple relative poses and considerably boosts the performance of multi-scan reconstruction in few-view reconstruction settings. Expand
3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans
TLDR
3D-SIS is introduced, a novel neural network architecture for 3D semantic instance segmentation in commodity RGB-D scans that leverages high-resolution RGB input by associating 2D images with the volumetric grid based on the pose alignment of the 3D reconstruction. Expand
...
1
2
3
4
5
...