Make Your ViT-based Multi-view 3D Detectors Faster via Token Compression

• URL: http://arxiv.org/abs/2409.00633v1
• Date: Sun, 1 Sep 2024 06:58:08 GMT
• Title: Make Your ViT-based Multi-view 3D Detectors Faster via Token Compression
• Authors: Dingyuan Zhang, Dingkang Liang, Zichang Tan, Xiaoqing Ye, Cheng Zhang, Jingdong Wang, Xiang Bai,
• Abstract summary: Slow inference speed is one of the most crucial concerns for deploying multi-view 3D detectors to tasks with high real-time requirements like autonomous driving. We propose a simple yet effective method called TokenCompression3D (ToC3D) Our method can nearly maintain the performance of recent SOTA with up to 30% inference speedup, and the improvements are consistent after scaling up the ViT and input resolution.
• Score: 78.93023152602525
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Slow inference speed is one of the most crucial concerns for deploying multi-view 3D detectors to tasks with high real-time requirements like autonomous driving. Although many sparse query-based methods have already attempted to improve the efficiency of 3D detectors, they neglect to consider the backbone, especially when using Vision Transformers (ViT) for better performance. To tackle this problem, we explore the efficient ViT backbones for multi-view 3D detection via token compression and propose a simple yet effective method called TokenCompression3D (ToC3D). By leveraging history object queries as foreground priors of high quality, modeling 3D motion information in them, and interacting them with image tokens through the attention mechanism, ToC3D can effectively determine the magnitude of information densities of image tokens and segment the salient foreground tokens. With the introduced dynamic router design, ToC3D can weigh more computing resources to important foreground tokens while compressing the information loss, leading to a more efficient ViT-based multi-view 3D detector. Extensive results on the large-scale nuScenes dataset show that our method can nearly maintain the performance of recent SOTA with up to 30% inference speedup, and the improvements are consistent after scaling up the ViT and input resolution. The code will be made at https://github.com/DYZhang09/ToC3D.

Related papers

• CT3D++: Improving 3D Object Detection with Keypoint-induced Channel-wise Transformer [42.68740105997167]
  We introduce two frameworks for 3D object detection with minimal hand-crafted design. Firstly, we propose CT3D, which sequentially performs raw-point-based embedding, a standard Transformer encoder, and a channel-wise decoder for point features within each proposal. Secondly, we present an enhanced network called CT3D++, which incorporates geometric and semantic fusion-based embedding to extract more valuable and comprehensive proposal-aware information.
  arXiv  Detail & Related papers  (2024-06-12T12:40:28Z)
• FastOcc: Accelerating 3D Occupancy Prediction by Fusing the 2D Bird's-Eye View and Perspective View [46.81548000021799]
  In autonomous driving, 3D occupancy prediction outputs voxel-wise status and semantic labels for more comprehensive understandings of 3D scenes. Recent researchers have extensively explored various aspects of this task, including view transformation techniques, ground-truth label generation, and elaborate network design. A new method, dubbed FastOcc, is proposed to accelerate the model while keeping its accuracy. Experiments on the Occ3D-nuScenes benchmark demonstrate that our FastOcc achieves a fast inference speed.
  arXiv  Detail & Related papers  (2024-03-05T07:01:53Z)
• Instant3D: Instant Text-to-3D Generation [101.25562463919795]
  We propose a novel framework for fast text-to-3D generation, dubbed Instant3D. Instant3D is able to create a 3D object for an unseen text prompt in less than one second with a single run of a feedforward network.
  arXiv  Detail & Related papers  (2023-11-14T18:59:59Z)
• 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)
• Cross Modal Transformer: Towards Fast and Robust 3D Object Detection [34.920322396476934]
  We propose a robust 3D detector, named Cross Modal Transformer (CMT), for end-to-end 3D multi-modal detection. CMT takes the image and point clouds tokens as inputs and directly outputs accurate 3D bounding boxes. It achieves 74.1% NDS on nuScenes test set while maintaining fast inference speed.
  arXiv  Detail & Related papers  (2023-01-03T18:36:52Z)
• Exploiting More Information in Sparse Point Cloud for 3D Single Object Tracking [9.693724357115762]
  3D single object tracking is a key task in 3D computer vision. The sparsity of point clouds makes it difficult to compute the similarity and locate the object. We propose a sparse-to-dense and transformer-based framework for 3D single object tracking.
  arXiv  Detail & Related papers  (2022-10-02T13:38:30Z)
• Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild [32.05421669957098]
  Large datasets and scalable solutions have led to unprecedented advances in 2D recognition. We revisit the task of 3D object detection by introducing a large benchmark, called Omni3D. We show that Cube R-CNN outperforms prior works on the larger Omni3D and existing benchmarks.
  arXiv  Detail & Related papers  (2022-07-21T17:56:22Z)
• 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)
• Monocular Quasi-Dense 3D Object Tracking [99.51683944057191]
  A reliable and accurate 3D tracking framework is essential for predicting future locations of surrounding objects and planning the observer's actions in numerous applications such as autonomous driving. We propose a framework that can effectively associate moving objects over time and estimate their full 3D bounding box information from a sequence of 2D images captured on a moving platform.
  arXiv  Detail & Related papers  (2021-03-12T15:30:02Z)
• Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Net [93.51773847125014]
  We propose a novel deep neural network that is able to jointly reason about 3D detection, tracking and motion forecasting given data captured by a 3D sensor. Our approach performs 3D convolutions across space and time over a bird's eye view representation of the 3D world.
  arXiv  Detail & Related papers  (2020-12-22T22:43:35Z)

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.