Exploring Recurrent Long-term Temporal Fusion for Multi-view 3D Perception

• URL: http://arxiv.org/abs/2303.05970v3
• Date: Tue, 9 Apr 2024 07:49:55 GMT
• Title: Exploring Recurrent Long-term Temporal Fusion for Multi-view 3D Perception
• Authors: Chunrui Han, Jinrong Yang, Jianjian Sun, Zheng Ge, Runpei Dong, Hongyu Zhou, Weixin Mao, Yuang Peng, Xiangyu Zhang,
• Abstract summary: Long-term temporal fusion is a crucial but often overlooked technique in camera-based Bird's-Eye-View 3D perception. Existing methods are mostly in a parallel manner. We name this simple but effective fusing pipeline VideoBEV.
• Score: 27.598461348452343
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Long-term temporal fusion is a crucial but often overlooked technique in camera-based Bird's-Eye-View (BEV) 3D perception. Existing methods are mostly in a parallel manner. While parallel fusion can benefit from long-term information, it suffers from increasing computational and memory overheads as the fusion window size grows. Alternatively, BEVFormer adopts a recurrent fusion pipeline so that history information can be efficiently integrated, yet it fails to benefit from longer temporal frames. In this paper, we explore an embarrassingly simple long-term recurrent fusion strategy built upon the LSS-based methods and find it already able to enjoy the merits from both sides, i.e., rich long-term information and efficient fusion pipeline. A temporal embedding module is further proposed to improve the model's robustness against occasionally missed frames in practical scenarios. We name this simple but effective fusing pipeline VideoBEV. Experimental results on the nuScenes benchmark show that VideoBEV obtains strong performance on various camera-based 3D perception tasks, including object detection (55.4\% mAP and 62.9\% NDS), segmentation (48.6\% vehicle mIoU), tracking (54.8\% AMOTA), and motion prediction (0.80m minADE and 0.463 EPA).

Related papers

• CRT-Fusion: Camera, Radar, Temporal Fusion Using Motion Information for 3D Object Detection [9.509625131289429]
  We introduce CRT-Fusion, a novel framework that integrates temporal information into radar-camera fusion. CRT-Fusion achieves state-of-the-art performance for radar-camera-based 3D object detection.
  arXiv  Detail & Related papers  (2024-11-05T11:25:19Z)
• Progressive Multi-Modal Fusion for Robust 3D Object Detection [12.048303829428452]
  Existing methods perform sensor fusion in a single view by projecting features from both modalities either in Bird's Eye View (BEV) or Perspective View (PV) We propose ProFusion3D, a progressive fusion framework that combines features in both BEV and PV at both intermediate and object query levels. Our architecture hierarchically fuses local and global features, enhancing the robustness of 3D object detection.
  arXiv  Detail & Related papers  (2024-10-09T22:57:47Z)
• SparseFusion: Efficient Sparse Multi-Modal Fusion Framework for Long-Range 3D Perception [47.000734648271006]
  We introduce SparseFusion, a novel multi-modal fusion framework built upon sparse 3D features to facilitate efficient long-range perception. The proposed module introduces sparsity from both semantic and geometric aspects which only fill grids that foreground objects potentially reside in. On the long-range Argoverse2 dataset, SparseFusion reduces memory footprint and accelerates the inference by about two times compared to dense detectors.
  arXiv  Detail & Related papers  (2024-03-15T05:59:10Z)
• PTT: Point-Trajectory Transformer for Efficient Temporal 3D Object Detection [66.94819989912823]
  We propose a point-trajectory transformer with long short-term memory for efficient temporal 3D object detection. We use point clouds of current-frame objects and their historical trajectories as input to minimize the memory bank storage requirement. We conduct extensive experiments on the large-scale dataset to demonstrate that our approach performs well against state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-12-13T18:59:13Z)
• FusionFormer: A Multi-sensory Fusion in Bird's-Eye-View and Temporal Consistent Transformer for 3D Object Detection [14.457844173630667]
  We propose a novel end-to-end multi-modal fusion transformer-based framework, dubbed FusionFormer. By developing a uniform sampling strategy, our method can easily sample from 2D image and 3D voxel features spontaneously. Our method achieves state-of-the-art single model performance of 72.6% mAP and 75.1% NDS in the 3D object detection task without test time augmentation.
  arXiv  Detail & Related papers  (2023-09-11T06:27:25Z)
• Fully Sparse Fusion for 3D Object Detection [69.32694845027927]
  Currently prevalent multimodal 3D detection methods are built upon LiDAR-based detectors that usually use dense Bird's-Eye-View feature maps. Fully sparse architecture is gaining attention as they are highly efficient in long-range perception. In this paper, we study how to effectively leverage image modality in the emerging fully sparse architecture.
  arXiv  Detail & Related papers  (2023-04-24T17:57:43Z)
• DETR4D: Direct Multi-View 3D Object Detection with Sparse Attention [50.11672196146829]
  3D object detection with surround-view images is an essential task for autonomous driving. We propose DETR4D, a Transformer-based framework that explores sparse attention and direct feature query for 3D object detection in multi-view images.
  arXiv  Detail & Related papers  (2022-12-15T14:18:47Z)
• Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detection [63.809086864530784]
  Current 3D detection methods use limited history to improve object perception. Our framework sets new state-of-the-art on nuScenes, achieving first place on the test set and outperforming previous best art by 5.2% mAP and 3.7% NDS on the validation set.
  arXiv  Detail & Related papers  (2022-10-05T17:59:51Z)
• BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation [105.96557764248846]
  We introduce BEVFusion, a generic multi-task multi-sensor fusion framework. It unifies multi-modal features in the shared bird's-eye view representation space. It achieves 1.3% higher mAP and NDS on 3D object detection and 13.6% higher mIoU on BEV map segmentation, with 1.9x lower cost.
  arXiv  Detail & Related papers  (2022-05-26T17:59:35Z)

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.