Focal-PETR: Embracing Foreground for Efficient Multi-Camera 3D Object Detection

• URL: http://arxiv.org/abs/2212.05505v2
• Date: Tue, 13 Dec 2022 09:28:01 GMT
• Title: Focal-PETR: Embracing Foreground for Efficient Multi-Camera 3D Object Detection
• Authors: Shihao Wang, Xiaohui Jiang, Ying Li
• Abstract summary: The dominant multi-camera 3D detection paradigm is based on explicit 3D feature construction. Other methods implicitly introduce geometric positional encoding to build the relationship between image tokens and 3D objects. We propose Focal-PETR with instance-guided supervision and spatial alignment module.
• Score: 11.13693561702228
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The dominant multi-camera 3D detection paradigm is based on explicit 3D feature construction, which requires complicated indexing of local image-view features via 3D-to-2D projection. Other methods implicitly introduce geometric positional encoding and perform global attention (e.g., PETR) to build the relationship between image tokens and 3D objects. The 3D-to-2D perspective inconsistency and global attention lead to a weak correlation between foreground tokens and queries, resulting in slow convergence. We propose Focal-PETR with instance-guided supervision and spatial alignment module to adaptively focus object queries on discriminative foreground regions. Focal-PETR additionally introduces a down-sampling strategy to reduce the consumption of global attention. Due to the highly parallelized implementation and down-sampling strategy, our model, without depth supervision, achieves leading performance on the large-scale nuScenes benchmark and a superior speed of 30 FPS on a single RTX3090 GPU. Extensive experiments show that our method outperforms PETR while consuming 3x fewer training hours. The code will be made publicly available.

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)
• EP2P-Loc: End-to-End 3D Point to 2D Pixel Localization for Large-Scale Visual Localization [44.05930316729542]
  We propose EP2P-Loc, a novel large-scale visual localization method for 3D point clouds. To increase the number of inliers, we propose a simple algorithm to remove invisible 3D points in the image. For the first time in this task, we employ a differentiable for end-to-end training.
  arXiv  Detail & Related papers  (2023-09-14T07:06:36Z)
• 3D Small Object Detection with Dynamic Spatial Pruning [62.72638845817799]
  We propose an efficient feature pruning strategy for 3D small object detection. We present a multi-level 3D detector named DSPDet3D which benefits from high spatial resolution. It takes less than 2s to directly process a whole building consisting of more than 4500k points while detecting out almost all objects.
  arXiv  Detail & Related papers  (2023-05-05T17:57:04Z)
• SRCN3D: Sparse R-CNN 3D for Compact Convolutional Multi-View 3D Object Detection and Tracking [12.285423418301683]
  This paper proposes Sparse R-CNN 3D (SRCN3D), a novel two-stage fully-sparse detector that incorporates sparse queries, sparse attention with box-wise sampling, and sparse prediction. Experiments on nuScenes dataset demonstrate that SRCN3D achieves competitive performance in both 3D object detection and multi-object tracking tasks.
  arXiv  Detail & Related papers  (2022-06-29T07:58:39Z)
• Improving 3D Object Detection with Channel-wise Transformer [58.668922561622466]
  We propose a two-stage 3D object detection framework (CT3D) with minimal hand-crafted design. CT3D simultaneously performs proposal-aware embedding and channel-wise context aggregation. It achieves the AP of 81.77% in the moderate car category on the KITTI test 3D detection benchmark.
  arXiv  Detail & Related papers  (2021-08-23T02:03:40Z)
• Shape Prior Non-Uniform Sampling Guided Real-time Stereo 3D Object Detection [59.765645791588454]
  Recently introduced RTS3D builds an efficient 4D Feature-Consistency Embedding space for the intermediate representation of object without depth supervision. We propose a shape prior non-uniform sampling strategy that performs dense sampling in outer region and sparse sampling in inner region. Our proposed method has 2.57% improvement on AP3d almost without extra network parameters.
  arXiv  Detail & Related papers  (2021-06-18T09:14:55Z)
• IAFA: Instance-aware Feature Aggregation for 3D Object Detection from a Single Image [37.83574424518901]
  3D object detection from a single image is an important task in Autonomous Driving. We propose an instance-aware approach to aggregate useful information for improving the accuracy of 3D object detection.
  arXiv  Detail & Related papers  (2021-03-05T05:47:52Z)
• 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)
• Lightweight Multi-View 3D Pose Estimation through Camera-Disentangled Representation [57.11299763566534]
  We present a solution to recover 3D pose from multi-view images captured with spatially calibrated cameras. We exploit 3D geometry to fuse input images into a unified latent representation of pose, which is disentangled from camera view-points. Our architecture then conditions the learned representation on camera projection operators to produce accurate per-view 2d detections.
  arXiv  Detail & Related papers  (2020-04-05T12:52:29Z)

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.