SToRe3D: Sparse Token Relevance in ViTs for Efficient Multi-View 3D Object Detection

• URL: http://arxiv.org/abs/2605.14110v1
• Date: Wed, 13 May 2026 20:53:03 GMT
• Title: SToRe3D: Sparse Token Relevance in ViTs for Efficient Multi-View 3D Object Detection
• Abstract summary: Vision Transformers (ViTs) enable strong multi-view 3D detection but are limited by high inference latency from dense token and query processing across multiple views and large 3D regions.<n>We introduce SToRe3D, a relevance-aligned sparsity framework that jointly selects 2D image tokens and 3D object queries while storing filtered features for reactivation.
• Score: 2.148411555253816
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision Transformers (ViTs) enable strong multi-view 3D detection but are limited by high inference latency from dense token and query processing across multiple views and large 3D regions. Existing sparsity methods, designed mainly for 2D vision, prune or merge image tokens but do not extend to full-model sparsity or address 3D object queries. We introduce SToRe3D, a relevance-aligned sparsity framework that jointly selects 2D image tokens and 3D object queries while storing filtered features for reactivation. Mutual 2D-3D relevance heads allocate compute to driving-critical content and preserve other embeddings. Evaluated on nuScenes and our new nuScenes-Relevance benchmark, SToRe3D achieves up to 3x faster inference with marginal accuracy loss, establishing real-time large-scale ViT-based 3D detection while maintaining accuracy on planning-critical agents.

Related papers

• Map-Det3D: Metric Feed-Forward 3D Reconstruction Prior for Multi-view 3D Object Detection from Streaming Inputs [62.865932175477035]
  Metric 3D object detection is a core capability for embodied agents, yet most reliable systems lean on depth sensors.<n>We propose Map-Det3D, an online multi-view 3D object detection model that brings detection directly into a 3D space reconstructed from RGB.
  arXiv  Detail & Related papers  (2026-08-12T15:33:42Z)
• StereoMV2D: A Sparse Temporal Stereo-Enhanced Framework for Robust Multi-View 3D Object Detection [31.8104389684728]
  We propose StereoMV2D, a unified framework that integrates temporal stereo modeling into the 2D detection-guided multi-view 3D detector.<n>By exploiting cross-temporal disparities of the same object across adjacent frames, StereoMV2D enhances depth perception and refines the query priors.<n>Experiments on the nuScenes and Argoverse 2 datasets demonstrate that StereoMV2D achieves superior detection performance without incurring significant computational overhead.
  arXiv  Detail & Related papers  (2025-12-19T14:25:46Z)
• Sparse Multiview Open-Vocabulary 3D Detection [27.57172918603858]
  3D object detection has traditionally been solved by training to detect a fixed set of categories.<n>In this work, we investigate open-vocabulary 3D object detection in the challenging yet practical sparse-view setting.<n>Our approach is training-free, relying on pre-trained, off-the-shelf 2D foundation models instead of employing computationally expensive 3D feature fusion.
  arXiv  Detail & Related papers  (2025-09-19T12:22:24Z)
• Make Your ViT-based Multi-view 3D Detectors Faster via Token Compression [78.93023152602525]
  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.
  arXiv  Detail & Related papers  (2024-09-01T06:58:08Z)
• DatasetNeRF: Efficient 3D-aware Data Factory with Generative Radiance Fields [68.94868475824575]
  This paper introduces a novel approach capable of generating infinite, high-quality 3D-consistent 2D annotations alongside 3D point cloud segmentations. We leverage the strong semantic prior within a 3D generative model to train a semantic decoder. Once trained, the decoder efficiently generalizes across the latent space, enabling the generation of infinite data.
  arXiv  Detail & Related papers  (2023-11-18T21:58:28Z)
• 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)
• 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)
• CMR3D: Contextualized Multi-Stage Refinement for 3D Object Detection [57.44434974289945]
  We propose Contextualized Multi-Stage Refinement for 3D Object Detection (CMR3D) framework. Our framework takes a 3D scene as input and strives to explicitly integrate useful contextual information of the scene. In addition to 3D object detection, we investigate the effectiveness of our framework for the problem of 3D object counting.
  arXiv  Detail & Related papers  (2022-09-13T05:26:09Z)
• 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)
• Graph-DETR3D: Rethinking Overlapping Regions for Multi-View 3D Object Detection [17.526914782562528]
  We propose Graph-DETR3D to automatically aggregate multi-view imagery information through graph structure learning (GSL) Our best model achieves 49.5 NDS on the nuScenes test leaderboard, achieving new state-of-the-art in comparison with various published image-view 3D object detectors.
  arXiv  Detail & Related papers  (2022-04-25T12:10:34Z)
• 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)
• CoCoNets: Continuous Contrastive 3D Scene Representations [21.906643302668716]
  This paper explores self-supervised learning of amodal 3D feature representations from RGB and RGB-D posed images and videos. We show the resulting 3D visual feature representations effectively scale across objects and scenes, imagine information occluded or missing from the input viewpoints, track objects over time, align semantically related objects in 3D, and improve 3D object detection.
  arXiv  Detail & Related papers  (2021-04-08T15:50:47Z)

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.