Transformer-based stereo-aware 3D object detection from binocular images

• URL: http://arxiv.org/abs/2304.11906v4
• Date: Sun, 15 Sep 2024 14:42:27 GMT
• Title: Transformer-based stereo-aware 3D object detection from binocular images
• Authors: Hanqing Sun, Yanwei Pang, Jiale Cao, Jin Xie, Xuelong Li,
• Abstract summary: We explore the model design of Transformers in binocular 3D object detection. To achieve this goal, we present TS3D, a Stereo-aware 3D object detector. Our proposed TS3D achieves a 41.29% Moderate Car detection average precision on the KITTI test set and takes 88 ms to detect objects from each binocular image pair.
• Score: 82.85433941479216
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Transformers have shown promising progress in various visual object detection tasks, including monocular 2D/3D detection and surround-view 3D detection. More importantly, the attention mechanism in the Transformer model and the 3D information extraction in binocular stereo are both similarity-based. However, directly applying existing Transformer-based detectors to binocular stereo 3D object detection leads to slow convergence and significant precision drops. We argue that a key cause of that defect is that existing Transformers ignore the binocular-stereo-specific image correspondence information. In this paper, we explore the model design of Transformers in binocular 3D object detection, focusing particularly on extracting and encoding task-specific image correspondence information. To achieve this goal, we present TS3D, a Transformer-based Stereo-aware 3D object detector. In the TS3D, a Disparity-Aware Positional Encoding (DAPE) module is proposed to embed the image correspondence information into stereo features. The correspondence is encoded as normalized sub-pixel-level disparity and is used in conjunction with sinusoidal 2D positional encoding to provide the 3D location information of the scene. To enrich multi-scale stereo features, we propose a Stereo Preserving Feature Pyramid Network (SPFPN). The SPFPN is designed to preserve the correspondence information while fusing intra-scale and aggregating cross-scale stereo features. Our proposed TS3D achieves a 41.29% Moderate Car detection average precision on the KITTI test set and takes 88 ms to detect objects from each binocular image pair. It is competitive with advanced counterparts in terms of both precision and inference speed.

Related papers

• 3DiffTection: 3D Object Detection with Geometry-Aware Diffusion Features [70.50665869806188]
  3DiffTection is a state-of-the-art method for 3D object detection from single images. We fine-tune a diffusion model to perform novel view synthesis conditioned on a single image. We further train the model on target data with detection supervision.
  arXiv  Detail & Related papers  (2023-11-07T23:46:41Z)
• Perspective-aware Convolution for Monocular 3D Object Detection [2.33877878310217]
  We propose a novel perspective-aware convolutional layer that captures long-range dependencies in images. By enforcing convolutional kernels to extract features along the depth axis of every image pixel, we incorporates perspective information into network architecture. We demonstrate improved performance on the KITTI3D dataset, achieving a 23.9% average precision in the easy benchmark.
  arXiv  Detail & Related papers  (2023-08-24T17:25:36Z)
• Viewpoint Equivariance for Multi-View 3D Object Detection [35.4090127133834]
  State-of-the-art methods focus on reasoning and decoding object bounding boxes from multi-view camera input. We introduce VEDet, a novel 3D object detection framework that exploits 3D multi-view geometry.
  arXiv  Detail & Related papers  (2023-03-25T19:56:41Z)
• Bridged Transformer for Vision and Point Cloud 3D Object Detection [92.86856146086316]
  Bridged Transformer (BrT) is an end-to-end architecture for 3D object detection. BrT learns to identify 3D and 2D object bounding boxes from both points and image patches. We experimentally show that BrT surpasses state-of-the-art methods on SUN RGB-D and ScanNetV2 datasets.
  arXiv  Detail & Related papers  (2022-10-04T05:44:22Z)
• Pseudo-Stereo for Monocular 3D Object Detection in Autonomous Driving [14.582107328849473]
  The gap in image-to-image generation for stereo views is much smaller than that in image-to-LiDAR generation. Motivated by this, we propose a Pseudo-Stereo 3D detection framework with three novel virtual view generation methods. Our framework ranks 1st on car, pedestrian, and cyclist among the monocular 3D detectors with publications on the KITTI-3D benchmark.
  arXiv  Detail & Related papers  (2022-03-04T03:00:34Z)
• LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-based 3D Detector [80.7563981951707]
  We propose LIGA-Stereo to learn stereo-based 3D detectors under the guidance of high-level geometry-aware representations of LiDAR-based detection models. Compared with the state-of-the-art stereo detector, our method has improved the 3D detection performance of cars, pedestrians, cyclists by 10.44%, 5.69%, 5.97% mAP respectively.
  arXiv  Detail & Related papers  (2021-08-18T17:24:40Z)
• M3DSSD: Monocular 3D Single Stage Object Detector [82.25793227026443]
  We propose a Monocular 3D Single Stage object Detector (M3DSSD) with feature alignment and asymmetric non-local attention. The proposed M3DSSD achieves significantly better performance than the monocular 3D object detection methods on the KITTI dataset.
  arXiv  Detail & Related papers  (2021-03-24T13:09:11Z)
• Stereo Object Matching Network [78.35697025102334]
  This paper presents a stereo object matching method that exploits both 2D contextual information from images and 3D object-level information. We present two novel strategies to handle 3D objectness in the cost volume space: selective sampling (RoISelect) and 2D-3D fusion.
  arXiv  Detail & Related papers  (2021-03-23T12:54:43Z)

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.