PillarHist: A Quantization-aware Pillar Feature Encoder based on Height-aware Histogram

• URL: http://arxiv.org/abs/2405.18734v1
• Date: Wed, 29 May 2024 03:28:16 GMT
• Title: PillarHist: A Quantization-aware Pillar Feature Encoder based on Height-aware Histogram
• Abstract summary: Real-time and high-performance 3D object detection plays a critical role in autonomous driving and robotics. Recent pillar-based 3D object detectors have gained significant attention due to their compact representation and low computational overhead. However, existing pillar-based detectors still suffer from information loss along height dimension and large numerical distribution difference.
• Score: 21.812058381531212
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Real-time and high-performance 3D object detection plays a critical role in autonomous driving and robotics. Recent pillar-based 3D object detectors have gained significant attention due to their compact representation and low computational overhead, making them suitable for onboard deployment and quantization. However, existing pillar-based detectors still suffer from information loss along height dimension and large numerical distribution difference during pillar feature encoding (PFE), which severely limits their performance and quantization potential. To address above issue, we first unveil the importance of different input information during PFE and identify the height dimension as a key factor in enhancing 3D detection performance. Motivated by this observation, we propose a height-aware pillar feature encoder named PillarHist. Specifically, PillarHist statistics the discrete distribution of points at different heights within one pillar. This simple yet effective design greatly preserves the information along the height dimension while significantly reducing the computation overhead of the PFE. Meanwhile, PillarHist also constrains the arithmetic distribution of PFE input to a stable range, making it quantization-friendly. Notably, PillarHist operates exclusively within the PFE stage to enhance performance, enabling seamless integration into existing pillar-based methods without introducing complex operations. Extensive experiments show the effectiveness of PillarHist in terms of both efficiency and performance.

Related papers

• Multi-scale Feature Fusion with Point Pyramid for 3D Object Detection [18.41721888099563]
  This paper proposes the Point Pyramid RCNN (POP-RCNN), a feature pyramid-based framework for 3D object detection on point clouds. The proposed method can be applied to a variety of existing frameworks to increase feature richness, especially for long-distance detection.
  arXiv  Detail & Related papers  (2024-09-06T20:13:14Z)
• PVAFN: Point-Voxel Attention Fusion Network with Multi-Pooling Enhancing for 3D Object Detection [59.355022416218624]
  integration of point and voxel representations is becoming more common in LiDAR-based 3D object detection. We propose a novel two-stage 3D object detector, called Point-Voxel Attention Fusion Network (PVAFN) PVAFN uses a multi-pooling strategy to integrate both multi-scale and region-specific information effectively.
  arXiv  Detail & Related papers  (2024-08-26T19:43:01Z)
• PillarTrack:Boosting Pillar Representation for Transformer-based 3D Single Object Tracking on Point Clouds [6.478734561409898]
  LiDAR-based 3D single object tracking (3D SOT) is a critical issue in robotics and autonomous driving.<n>We propose PillarTrack, a novel pillar-based 3D SOT framework.<n>Our method achieves comparable performance on the KITTI and NuScenes datasets.
  arXiv  Detail & Related papers  (2024-04-11T06:06:56Z)
• Fine-Grained Pillar Feature Encoding Via Spatio-Temporal Virtual Grid for 3D Object Detection [11.798670216671631]
  Fine-Grained Pillar Feature (FG-PFE) is a novel encoding architecture for LiDAR-based 3D object detectors. FG-PFE achieves significant performance improvements over baseline models such as PointPillar, CenterPoint-Pillar, and PillarNet.
  arXiv  Detail & Related papers  (2024-03-11T04:58:36Z)
• Cross-Cluster Shifting for Efficient and Effective 3D Object Detection in Autonomous Driving [69.20604395205248]
  We present a new 3D point-based detector model, named Shift-SSD, for precise 3D object detection in autonomous driving. We introduce an intriguing Cross-Cluster Shifting operation to unleash the representation capacity of the point-based detector. We conduct extensive experiments on the KITTI, runtime, and nuScenes datasets, and the results demonstrate the state-of-the-art performance of Shift-SSD.
  arXiv  Detail & Related papers  (2024-03-10T10:36:32Z)
• FlashOcc: Fast and Memory-Efficient Occupancy Prediction via Channel-to-Height Plugin [32.172269679513285]
  FlashOCC consolidates rapid and memory-efficient occupancy prediction. Channel-to-height transformation is introduced to lift the output logits from the BEV into the 3D space. Results substantiate the superiority of our plug-and-play paradigm over previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-11-18T15:28:09Z)
• PointHPS: Cascaded 3D Human Pose and Shape Estimation from Point Clouds [99.60575439926963]
  We propose a principled framework, PointHPS, for accurate 3D HPS from point clouds captured in real-world settings. PointHPS iteratively refines point features through a cascaded architecture. Extensive experiments demonstrate that PointHPS, with its powerful point feature extraction and processing scheme, outperforms State-of-the-Art methods.
  arXiv  Detail & Related papers  (2023-08-28T11:10:14Z)
• Centralized Feature Pyramid for Object Detection [53.501796194901964]
  Visual feature pyramid has shown its superiority in both effectiveness and efficiency in a wide range of applications. In this paper, we propose a OLO Feature Pyramid for object detection, which is based on a globally explicit centralized feature regulation.
  arXiv  Detail & Related papers  (2022-10-05T08:32:54Z)
• PiFeNet: Pillar-Feature Network for Real-Time 3D Pedestrian Detection from Point Cloud [64.12626752721766]
  We present PiFeNet, an efficient real-time 3D detector for pedestrian detection from point clouds. We address two challenges that 3D object detection frameworks encounter when detecting pedestrians: low of pillar features and small occupation areas of pedestrians in point clouds. Our approach is ranked 1st in KITTI pedestrian BEV and 3D leaderboards while running at 26 frames per second (FPS), and achieves state-of-the-art performance on Nuscenes detection benchmark.
  arXiv  Detail & Related papers  (2021-12-31T13:41:37Z)
• Improved Pillar with Fine-grained Feature for 3D Object Detection [23.348710029787068]
  3D object detection with LiDAR point clouds plays an important role in autonomous driving perception module. Existing point-based methods are challenging to reach the speed requirements because of too many raw points. The 2D grid-based methods, such as PointPillar, can easily achieve a stable and efficient speed based on simple 2D convolution.
  arXiv  Detail & Related papers  (2021-10-12T14:53:14Z)
• Reinforced Axial Refinement Network for Monocular 3D Object Detection [160.34246529816085]
  Monocular 3D object detection aims to extract the 3D position and properties of objects from a 2D input image. Conventional approaches sample 3D bounding boxes from the space and infer the relationship between the target object and each of them, however, the probability of effective samples is relatively small in the 3D space. We propose to start with an initial prediction and refine it gradually towards the ground truth, with only one 3d parameter changed in each step. This requires designing a policy which gets a reward after several steps, and thus we adopt reinforcement learning to optimize it.
  arXiv  Detail & Related papers  (2020-08-31T17:10:48Z)
• PAM:Point-wise Attention Module for 6D Object Pose Estimation [2.4815579733050153]
  6D pose estimation refers to object recognition and estimation of 3D rotation and 3D translation. Previous methods utilized depth information in the refinement process or were designed as a heterogeneous architecture for each data space to extract feature. This paper proposes a Point Attention Module that can efficiently extract powerful feature from RGB-D.
  arXiv  Detail & Related papers  (2020-08-12T11:29:48Z)
• InfoFocus: 3D Object Detection for Autonomous Driving with Dynamic Information Modeling [65.47126868838836]
  We propose a novel 3D object detection framework with dynamic information modeling. Coarse predictions are generated in the first stage via a voxel-based region proposal network. Experiments are conducted on the large-scale nuScenes 3D detection benchmark.
  arXiv  Detail & Related papers  (2020-07-16T18:27:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.