Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection
University of Science and Technology of China（中国科学技术大学）；The Chinese University of Hong Kong（香港中文大学）；Hefei Comprehensive National Science Center（合肥综合性国家科学中心）
Recent advances on 3D object detection heavily rely on how the 3D data are represented, \emph{i.e.}, voxel-based or point-based representation. Many existing high performance 3D detectors are point-based because this structure can better retain precise point positions. Nevertheless, point-level features lead to high computation overheads due to unordered storage. In contrast, the voxel-based structure is better suited for feature extraction but often yields lower accuracy because the input data are divided into grids. In this paper, we take a slightly different viewpoint -- we find that precise positioning of raw points is not essential for high performance 3D object detection and that the coarse voxel granularity can also offer sufficient detection accuracy. Bearing this view in mind, we devise a simple but effective voxel-based framework, named Voxel R-CNN. By taking full advantage of voxel features in a two stage approach, our method achieves comparable detection accuracy with state-of-the-art point-based models, but at a fraction of the computation cost. Voxel R-CNN consists of a 3D backbone network, a 2D bird-eye-view (BEV) Region Proposal Network and a detect head. A voxel RoI pooling is devised to extract RoI features directly from voxel features for further refinement. Extensive experiments are conducted on the widely used KITTI Dataset and the more recent Waymo Open Dataset. Our results show that compared to existing voxel-based methods, Voxel R-CNN delivers a higher detection accuracy while maintaining a real-time frame processing rate, \emph{i.e}., at a speed of 25 FPS on an NVIDIA RTX 2080 Ti GPU. The code is available at \url{https://github.com/djiajunustc/Voxel-R-CNN}.
Tsinghua University（清华大学）；Microsoft Research Asia（微软亚洲研究院）
Sparse voxel-based 3D convolutional neural networks (CNNs) are widely used for various 3D vision tasks. Sparse voxel-based 3D CNNs create sparse non-empty voxels from the 3D input and perform 3D convolution operations on them only. We propose a simple yet effective padding scheme --- interpolation-aware padding to pad a few empty voxels adjacent to the non-empty voxels and involve them in the 3D CNN computation so that all neighboring voxels exist when computing point-wise features via the trilinear interpolation. For fine-grained 3D vision tasks where point-wise features are essential, like s…
We present Point-Voxel CNN (PVCNN) for efficient, fast 3D deep learning. Previous work processes 3D data using either voxel-based or point-based NN models. However, both approaches are computationally inefficient. The computation cost and memory footprints of the voxel-based models grow cubically with the input resolution, making it memory-prohibitive to scale up the resolution. As for point-based networks, up to 80% of the time is wasted on structuring the sparse data which have rather poor memory locality, not on the actual feature extraction. In this paper, we propose PVCNN that represents …
Harbin Institute of Technology（哈尔滨工业大学）；Shanghai Jiao Tong University（上海交通大学）
The performance of point cloud 3D object detection hinges on effectively representing raw points, grid-based voxels or pillars. Recent two-stage 3D detectors typically take the point-voxel-based R-CNN paradigm, i.e., the first stage resorts to the 3D voxel-based backbone for 3D proposal generation on bird-eye-view (BEV) representation and the second stage refines them via the intermediate point representation. Their primary mechanisms involve the utilization of intermediary keypoints to restore the substantial 3D structure context from the converted BEV representation. The skilled point-voxel …
Seoul National University（首尔大学）；Kwangwoon University（光云大学）
Most of the existing deep learning-based methods for 3D hand and human pose estimation from a single depth map are based on a common framework that takes a 2D depth map and directly regresses the 3D coordinates of keypoints, such as hand or human body joints, via 2D convolutional neural networks (CNNs). The first weakness of this approach is the presence of perspective distortion in the 2D depth map. While the depth map is intrinsically 3D data, many previous methods treat depth maps as 2D images that can distort the shape of the actual object through projection from 3D to 2D space. This compe…
Two-stage detectors have gained much popularity in 3D object detection. Most two-stage 3D detectors utilize grid points, voxel grids, or sampled keypoints for RoI feature extraction in the second stage. Such methods, however, are inefficient in handling unevenly distributed and sparse outdoor points. This paper solves this problem in three aspects. 1) Dynamic Point Aggregation. We propose the patch search to quickly search points in a local region for each 3D proposal. The dynamic farthest voxel sampling is then applied to evenly sample the points. Especially, the voxel size varies along the d…
The Chinese University of Hong Kong（香港中文大学）；The University of Hong Kong（香港大学）；MEGVII Technology（旷视科技）
3D object detectors usually rely on hand-crafted proxies, e.g., anchors or centers, and translate well-studied 2D frameworks to 3D. Thus, sparse voxel features need to be densified and processed by dense prediction heads, which inevitably costs extra computation. In this paper, we instead propose VoxelNext for fully sparse 3D object detection. Our core insight is to predict objects directly based on sparse voxel features, without relying on hand-crafted proxies. Our strong sparse convolutional network VoxelNeXt detects and tracks 3D objects through voxel features entirely. It is an elegant and…
CUHK-SenseTime Joint Laboratory, The Chinese University of Hong Kong（香港中文大学-商汤科技联合实验室，香港中文大学）；SenseTime Research（商汤科技研究院）；NLPR, CASIA（中国科学院自动化研究所模式识别国家重点实验室）；CSE, CUHK（香港中文大学计算机科学与工程学系）
We present a novel and high-performance 3D object detection framework, named PointVoxel-RCNN (PV-RCNN), for accurate 3D object detection from point clouds. Our proposed method deeply integrates both 3D voxel Convolutional Neural Network (CNN) and PointNet-based set abstraction to learn more discriminative point cloud features. It takes advantages of efficient learning and high-quality proposals of the 3D voxel CNN and the flexible receptive fields of the PointNet-based networks. Specifically, the proposed framework summarizes the 3D scene with a 3D voxel CNN into a small set of keypoints via a…
The Chinese University of Hong Kong（香港中文大学）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；HKUST（香港科技大学）
We present Voxel Transformer (VoTr), a novel and effective voxel-based Transformer backbone for 3D object detection from point clouds. Conventional 3D convolutional backbones in voxel-based 3D detectors cannot efficiently capture large context information, which is crucial for object recognition and localization, owing to the limited receptive fields. In this paper, we resolve the problem by introducing a Transformer-based architecture that enables long-range relationships between voxels by self-attention. Given the fact that non-empty voxels are naturally sparse but numerous, directly applyin…
Zhejiang University（浙江大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Inception Institute of Artificial Intelligence（Inception人工智能研究院）
In this paper, we present an Intersection-over-Union (IoU) guided two-stage 3D object detector with a voxel-to-point decoder. To preserve the necessary information from all raw points and maintain the high box recall in voxel based Region Proposal Network (RPN), we propose a residual voxel-to-point decoder to extract the point features in addition to the map-view features from the voxel based RPN. We use a 3D Region of Interest (RoI) alignment to crop and align the features with the proposal boxes for accurately perceiving the object position. The RoI-Aligned features are finally aggregated wi…
Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；Lingnan University（岭南大学）；Hong Kong Metropolitan University（香港都会大学）；The Education University of Hong Kong（香港教育大学）；Shenzhen Research Institute, Nanjing University of Aeronautics and Astronautics（南京航空航天大学深圳研究院）
Large imbalance often exists between the foreground points (i.e., objects) and the background points in outdoor LiDAR point clouds. It hinders cutting-edge detectors from focusing on informative areas to produce accurate 3D object detection results. This paper proposes a novel object detection network by semantical point-voxel feature interaction, dubbed PV-RCNN++. Unlike most of existing methods, PV-RCNN++ explores the semantic information to enhance the quality of object detection. First, a semantic segmentation module is proposed to retain more discriminative foreground keypoints. Such a mo…
Accurate detection of objects in 3D point clouds is a central problem in many applications, such as autonomous navigation, housekeeping robots, and augmented/virtual reality. To interface a highly sparse LiDAR point cloud with a region proposal network (RPN), most existing efforts have focused on hand-crafted feature representations, for example, a bird's eye view projection. In this work, we remove the need of manual feature engineering for 3D point clouds and propose VoxelNet, a generic 3D detection network that unifies feature extraction and bounding box prediction into a single stage, end-…
Peking University（北京大学）；Microsoft Research Asia（微软亚洲研究院）
While the voxel-based methods have achieved promising results for multi-person 3D pose estimation from multi-cameras, they suffer from heavy computation burdens, especially for large scenes. We present Faster VoxelPose to address the challenge by re-projecting the feature volume to the three two-dimensional coordinate planes and estimating X, Y, Z coordinates from them separately. To that end, we first localize each person by a 3D bounding box by estimating a 2D box and its height based on the volume features projected to the xy-plane and z-axis, respectively. Then for each person, we estimate…
We present a novel lightweight convolutional neural network for point cloud analysis. In contrast to many current CNNs which increase receptive field by downsampling point cloud, our method directly operates on the entire point sets without sampling and achieves good performances efficiently. Our network consists of point voxel convolution (PVC) layer as building block. Each layer has two parallel branches, namely the voxel branch and the point branch. For the voxel branch specifically, we aggregate local features on non-empty voxel centers to reduce geometric information loss caused by voxeli…
University of Electronic Science and Technology of China（电子科技大学）
Accurate 3D object detection from point clouds has become a crucial component in autonomous driving. However, the volumetric representations and the projection methods in previous works fail to establish the relationships between the local point sets. In this paper, we propose Sparse Voxel-Graph Attention Network (SVGA-Net), a novel end-to-end trainable network which mainly contains voxel-graph module and sparse-to-dense regression module to achieve comparable 3D detection tasks from raw LIDAR data. Specifically, SVGA-Net constructs the local complete graph within each divided 3D spherical vox…
Hong Kong University of Science and Technology（香港科技大学）
In this work, we propose a novel two-stage framework for the efficient 3D point cloud object detection. Instead of transforming point clouds into 2D bird eye view projections, we parse the raw point cloud data directly in the 3D space yet achieve impressive efficiency and accuracy. To achieve this goal, we propose dynamic voxelization, a method that voxellizes points at local scale on-the-fly. By doing so, we preserve the point cloud geometry with 3D voxels, and therefore waive the dependence on expensive MLPs to learn from point coordinates. On the other hand, we inherently still follow the s…
We address the problem of 3D object detection, that is, estimating 3D object bounding boxes from point clouds. 3D object detection methods exploit either voxel-based or point-based features to represent 3D objects in a scene. Voxel-based features are efficient to extract, while they fail to preserve fine-grained 3D structures of objects. Point-based features, on the other hand, represent the 3D structures more accurately, but extracting these features is computationally expensive. We introduce in this paper a novel single-stage 3D detection method having the merit of both voxel-based and point…
LiDAR has become one of the primary 3D object detection sensors in autonomous driving. However, LiDAR's diverging point pattern with increasing distance results in a non-uniform sampled point cloud ill-suited to discretized volumetric feature extraction. Current methods either rely on voxelized point clouds or use inefficient farthest point sampling to mitigate detrimental effects caused by density variation but largely ignore point density as a feature and its predictable relationship with distance from the LiDAR sensor. Our proposed solution, Point Density-Aware Voxel network (PDV), is an en…
The Chinese University of Hong Kong（香港中文大学）；The University of Hong Kong（香港大学）；MEGVII Technology（旷视科技）；SmartMore（思谋科技）
In this work, we present a conceptually simple yet effective framework for cross-modality 3D object detection, named voxel field fusion. The proposed approach aims to maintain cross-modality consistency by representing and fusing augmented image features as a ray in the voxel field. To this end, the learnable sampler is first designed to sample vital features from the image plane that are projected to the voxel grid in a point-to-ray manner, which maintains the consistency in feature representation with spatial context. In addition, ray-wise fusion is conducted to fuse features with the supple…
Fully-connected Conditional Random Field (CRF) is often used as post-processing to refine voxel classification results by encouraging spatial coherence. In this paper, we propose a new end-to-end training method called Posterior-CRF. In contrast with previous approaches which use the original image intensity in the CRF, our approach applies 3D, fully connected CRF to the posterior probabilities from a CNN and optimizes both CNN and CRF together. The experiments on white matter hyperintensities segmentation demonstrate that our method outperforms CNN, post-processing CRF and different end-to-en…
In this article, we look into some essential aspects of convolutional neural networks (CNNs) with the focus on medical image segmentation. First, we discuss the CNN architecture, thereby highlighting the spatial origin of the data, voxel-wise classification and the receptive field. Second, we discuss the sampling of input-output pairs, thereby highlighting the interaction between voxel-wise classification, patch size and the receptive field. Finally, we give a historical overview of crucial changes to CNN architectures for classification and segmentation, giving insights in the relation betwee…
Camera and LiDAR sensor modalities provide complementary appearance and geometric information useful for detecting 3D objects for autonomous vehicle applications. However, current end-to-end fusion methods are challenging to train and underperform state-of-the-art LiDAR-only detectors. Sequential fusion methods suffer from a limited number of pixel and point correspondences due to point cloud sparsity, or their performance is strictly capped by the detections of one of the modalities. Our proposed solution, Dense Voxel Fusion (DVF) is a sequential fusion method that generates multi-scale dense…
MsSVT++: Mixed-scale Sparse Voxel Transformer with Center Voting for 3D Object Detection
Beijing Institute of Technology（北京理工大学）；Key Laboratory of Photoelectronic Imaging Technology and System, Ministry of Education of China（光电成像技术与系统教育部重点实验室）；Beijing Institute of Technology Chongqing Innovation Center（北京理工大学重庆创新中心）
Transformer has demonstrated promising performance in many 2D vision tasks. However, it is cumbersome to compute the self-attention on large-scale point cloud data because point cloud is a long sequence and unevenly distributed in 3D space. To solve this issue, existing methods usually compute self-attention locally by grouping the points into clusters of the same size, or perform convolutional self-attention on a discretized representation. However, the former results in stochastic point dropout, while the latter typically has narrow attention fields. In this paper, we propose a novel voxel-b…
A unified neural network structure is presented for joint 3D object detection and point cloud segmentation in this paper. We leverage rich supervision from both detection and segmentation labels rather than using just one of them. In addition, an extension based on single-stage object detectors is proposed based on the implicit function widely used in 3D scene and object understanding. The extension branch takes the final feature map from the object detection module as input, and produces an implicit function that generates semantic distribution for each point for its corresponding voxel cente…
The Chinese University of Hong Kong（香港中文大学）；The University of Hong Kong（香港大学）；MEGVII Technology（旷视科技）；SmartMore（思谋科技）
In this work, we present a unified framework for multi-modality 3D object detection, named UVTR. The proposed method aims to unify multi-modality representations in the voxel space for accurate and robust single- or cross-modality 3D detection. To this end, the modality-specific space is first designed to represent different inputs in the voxel feature space. Different from previous work, our approach preserves the voxel space without height compression to alleviate semantic ambiguity and enable spatial connections. To make full use of the inputs from different sensors, the cross-modality inte…
Hong Kong University of Science and Technology（香港科技大学）；Tencent Lightspeed & Quantum Studios（腾讯光子工作室群）；City University of Hong Kong（香港城市大学）
In recent years, sparse voxel-based methods have become the state-of-the-arts for 3D semantic segmentation of indoor scenes, thanks to the powerful 3D CNNs. Nevertheless, being oblivious to the underlying geometry, voxel-based methods suffer from ambiguous features on spatially close objects and struggle with handling complex and irregular geometries due to the lack of geodesic information. In view of this, we present Voxel-Mesh Network (VMNet), a novel 3D deep architecture that operates on the voxel and mesh representations leveraging both the Euclidean and geodesic information. Intuitively, …
Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；The University of Sydney（悉尼大学）；SenseTime Research（商汤科技研究院）；The Chinese University of Hong Kong（香港中文大学）
3D object detection is receiving increasing attention from both industry and academia thanks to its wide applications in various fields. In this paper, we propose Point-Voxel Region-based Convolution Neural Networks (PV-RCNNs) for 3D object detection on point clouds. First, we propose a novel 3D detector, PV-RCNN, which boosts the 3D detection performance by deeply integrating the feature learning of both point-based set abstraction and voxel-based sparse convolution through two novel steps, i.e., the voxel-to-keypoint scene encoding and the keypoint-to-grid RoI feature abstraction. Second, we…
PVAFN: Point-Voxel Attention Fusion Network with Multi-Pooling Enhancing for 3D Object Detection
College of Computer Science and Technology, Taiyuan University of Technology（太原理工大学计算机科学与技术学院）；Key Laboratory of Machine Perception, Peking University（北京大学机器感知实验室）；University of Pisa（比萨大学）；University of Trento（特伦托大学）
Many recent works on 3D object detection have focused on designing neural network architectures that can consume point cloud data. While these approaches demonstrate encouraging performance, they are typically based on a single modality and are unable to leverage information from other modalities, such as a camera. Although a few approaches fuse data from different modalities, these methods either use a complicated pipeline to process the modalities sequentially, or perform late-fusion and are unable to learn interaction between different modalities at early stages. In this work, we present Po…
Recent work on 3D object detection advocates point cloud voxelization in birds-eye view, where objects preserve their physical dimensions and are naturally separable. When represented in this view, however, point clouds are sparse and have highly variable point density, which may cause detectors difficulties in detecting distant or small objects (pedestrians, traffic signs, etc.). On the other hand, perspective view provides dense observations, which could allow more favorable feature encoding for such cases. In this paper, we aim to synergize the birds-eye view and the perspective view and pr…
College of Information Science and Engineering, Northeastern University（东北大学信息科学与工程学院）
In this paper, we investigate the combination of voxel-based methods and point-based methods, and propose a novel end-to-end two-stage 3D object detector named SGNet for point clouds scenes. The voxel-based methods voxelize the scene to regular grids, which can be processed with the current advanced feature learning frameworks based on convolutional layers for semantic feature learning. Whereas the point-based methods can better extract the geometric feature of the point due to the coordinate reservations. The combination of the two is an effective solution for 3D object detection from point c…
Real-time detection of objects in the 3D scene is one of the tasks an autonomous agent needs to perform for understanding its surroundings. While recent Deep Learning-based solutions achieve satisfactory performance, their high computational cost renders their application in real-life settings in which computations need to be performed on embedded platforms intractable. In this paper, we analyze the efficiency of two popular voxel-based 3D object detection methods providing a good compromise between high performance and speed based on two aspects, their ability to detect objects located at lar…
Samsung AI Center Moscow（三星人工智能中心莫斯科）；Lomonosov Moscow State University（罗蒙诺索夫莫斯科国立大学）
In this paper, we introduce the task of multi-view RGB-based 3D object detection as an end-to-end optimization problem. To address this problem, we propose ImVoxelNet, a novel fully convolutional method of 3D object detection based on monocular or multi-view RGB images. The number of monocular images in each multi-view input can variate during training and inference; actually, this number might be unique for each multi-view input. ImVoxelNet successfully handles both indoor and outdoor scenes, which makes it general-purpose. Specifically, it achieves state-of-the-art results in car detection o…
Hangzhou Hikvision Digital Technology Co. Ltd（杭州海康威视数字技术股份有限公司）
Object detection in point cloud data is one of the key components in computer vision systems, especially for autonomous driving applications. In this work, we present Voxel-FPN, a novel one-stage 3D object detector that utilizes raw data from LIDAR sensors only. The core framework consists of an encoder network and a corresponding decoder followed by a region proposal network. Encoder extracts multi-scale voxel information in a bottom-up manner while decoder fuses multiple feature maps from various scales in a top-down way. Extensive experiments show that the proposed method has better perform…
Moscow Institute of Physics and Technology（莫斯科物理技术学院）；Artificial Intelligence Research Institute（人工智能研究院）
The main challenge in 3D object detection from LiDAR point clouds is achieving real-time performance without affecting the reliability of the network. In other words, the detecting network must be confident enough about its predictions. In this paper, we present a solution to improve network inference speed and precision at the same time by implementing a fast dynamic voxelizer that works on fast pillar-based models in the same way a voxelizer works on slow voxel-based models. In addition, we propose a lightweight detection sub-head model for classifying predicted objects and filter out false …
We present Hybrid Voxel Network (HVNet), a novel one-stage unified network for point cloud based 3D object detection for autonomous driving. Recent studies show that 2D voxelization with per voxel PointNet style feature extractor leads to accurate and efficient detector for large 3D scenes. Since the size of the feature map determines the computation and memory cost, the size of the voxel becomes a parameter that is hard to balance. A smaller voxel size gives a better performance, especially for small objects, but a longer inference time. A larger voxel can cover the same area with a smaller f…
CUHK（香港中文大学）；Shun Hing Institute of Advanced Engineering, CUHK（香港中文大学信兴高等工程研究所）；Max Planck Institute（马克斯·普朗克研究所）
This paper presents a new approach to boost a single-modality (LiDAR) 3D object detector by teaching it to simulate features and responses that follow a multi-modality (LiDAR-image) detector. The approach needs LiDAR-image data only when training the single-modality detector, and once well-trained, it only needs LiDAR data at inference. We design a novel framework to realize the approach: response distillation to focus on the crucial response samples and avoid the background samples; sparse-voxel distillation to learn voxel semantics and relations from the estimated crucial voxels; a fine-grai…
LiDAR-based 3D detection in point cloud is essential in the perception system of autonomous driving. In this paper, we present LiDAR R-CNN, a second stage detector that can generally improve any existing 3D detector. To fulfill the real-time and high precision requirement in practice, we resort to point-based approach other than the popular voxel-based approach. However, we find an overlooked issue in previous work: Naively applying point-based methods like PointNet could make the learned features ignore the size of proposals. To this end, we analyze this problem in detail and propose several …
Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object Detection
The Hong Kong Polytechnic University（香港理工大学）；Center for Artificial Intelligence and Robotics, HKISI, CAS（中国科学院香港智能科学研究所人工智能与机器人中心）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
The Chinese University of Hong Kong（香港中文大学）；Shanghai AI Laboratory（上海人工智能实验室）；The University of Hong Kong（香港大学）；Carnegie Mellon University（卡内基梅隆大学）
This paper introduces the Masked Voxel Jigsaw and Reconstruction (MV-JAR) method for LiDAR-based self-supervised pre-training and a carefully designed data-efficient 3D object detection benchmark on the Waymo dataset. Inspired by the scene-voxel-point hierarchy in downstream 3D object detectors, we design masking and reconstruction strategies accounting for voxel distributions in the scene and local point distributions within the voxel. We employ a Reversed-Furthest-Voxel-Sampling strategy to address the uneven distribution of LiDAR points and propose MV-JAR, which combines two techniques for …
East China Normal University（华东师范大学）；Shanghai AI Lab（上海人工智能实验室）；Fudan University（复旦大学）
Multi-modal 3D object detection has been an active research topic in autonomous driving. Nevertheless, it is non-trivial to explore the cross-modal feature fusion between sparse 3D points and dense 2D pixels. Recent approaches either fuse the image features with the point cloud features that are projected onto the 2D image plane or combine the sparse point cloud with dense image pixels. These fusion approaches often suffer from severe information loss, thus causing sub-optimal performance. To address these problems, we construct the homogeneous structure between the point cloud and images to a…
Many LiDAR-based methods for detecting large objects, single-class object detection, or under easy situations were claimed to perform quite well. However, their performances of detecting small objects or under hard situations did not surpass those of the fusion-based ones due to failure to leverage the image semantics. In order to elevate the detection performance in a complicated environment, this paper proposes a deep learning (DL)-embedded fusion-based multi-class 3D object detection network which admits both LiDAR and camera sensor data streams, named Voxel-Pixel Fusion Network (VPFNet). I…
