Towards Visual Query Localization in the 3D World

• URL: http://arxiv.org/abs/2605.01498v1
• Date: Sat, 02 May 2026 15:41:54 GMT
• Title: Towards Visual Query Localization in the 3D World
• Abstract summary: We make the first attempt to address visual query localization in the 3D world by introducing a novel benchmark, dubbed 3DVQL.<n>3DVQL contains 2,002 sequences with around 170,000 frames and 6.4K response segments from 38 object categories.<n>To the best of our knowledge, 3DVQL is the first benchmark for 3D multimodal visual query localization.
• Score: 44.67762623020334
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Visual query localization (VQL) aims to predict the spatio-temporal response of the most recent occurrence in a sequence given a query. Currently, most research focuses on visual query localization in 2D videos, while its counterpart in 3D space has received little attention. In this paper, we make the first attempt to address visual query localization in the 3D world by introducing a novel benchmark, dubbed 3DVQL. Specifically, 3DVQL contains 2,002 sequences with around 170,000 frames and 6.4K response track segments from 38 object categories. Each sequence in 3DVQL is provided with multiple modalities, including point clouds, RGB images, and depth images, to support flexible research. To ensure high-quality annotations, each sequence is manually annotated with multiple rounds of verification and refinement. To the best of our knowledge, 3DVQL is the first benchmark for 3D multimodal visual query localization. To facilitate comparison in subsequent research, we implement a series of representative 3D multimodal VQL baselines using point clouds and RGB images. The experimental results show that existing methods exhibit significant performance variations across different fusion modules. To encourage future research, we propose a lift-and-attention fusion algorithm named LaF, which significantly outperforms existing baseline models. Our benchmark and model will be publicly released at https://github.com/wuhengliangliang/3DVQL.

Related papers

• ForeSea: AI Forensic Search with Multi-modal Queries for Video Surveillance [56.15563109738998]
  ForeSea is an AI forensic search system with a 3-stage, plug-and-play pipeline.<n>ForeSea improves accuracy by 3.5% and temporal IoU by 11.0 over prior VideoRAG models.
  arXiv  Detail & Related papers  (2026-03-24T07:15:28Z)
• HMR3D: Hierarchical Multimodal Representation for 3D Scene Understanding with Large Vision-Language Model [14.277165215664425]
  Large vision-language models (VLMs) have shown significant promise for 3D scene understanding.<n>Existing VLM-based approaches typically align 3D scene features with the VLM's embedding space.<n>We propose a novel hierarchical multimodal representation for 3D scene reasoning.
  arXiv  Detail & Related papers  (2025-11-28T08:06:20Z)
• MMScan: A Multi-Modal 3D Scene Dataset with Hierarchical Grounded Language Annotations [55.022519020409405]
  This paper builds the first largest ever multi-modal 3D scene dataset and benchmark with hierarchical grounded language annotations, MMScan.<n>The resulting multi-modal 3D dataset encompasses 1.4M meta-annotated captions on 109k objects and 7.7k regions as well as over 3.04M diverse samples for 3D visual grounding and question-answering benchmarks.
  arXiv  Detail & Related papers  (2024-06-13T17:59:30Z)
• Unifying 3D Vision-Language Understanding via Promptable Queries [39.55438547712157]
  unified model for 3D vision-language (3D-VL) understanding. PQ3D is capable of using Promptable Queries to tackle a wide range of 3D-VL tasks. Tested across ten diverse 3D-VL datasets, PQ3D demonstrates impressive performance on these tasks.
  arXiv  Detail & Related papers  (2024-05-19T04:35:05Z)
• PoIFusion: Multi-Modal 3D Object Detection via Fusion at Points of Interest [65.48057241587398]
  PoIFusion is a framework to fuse information of RGB images and LiDAR point clouds at the points of interest (PoIs) Our approach maintains the view of each modality and obtains multi-modal features by computation-friendly projection and computation. We conducted extensive experiments on nuScenes and Argoverse2 datasets to evaluate our approach.
  arXiv  Detail & Related papers  (2024-03-14T09:28:12Z)
• V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detection [73.37781484123536]
  We introduce a highly performant 3D object detector for point clouds using the DETR framework. To address the limitation, we introduce a novel 3D Relative Position (3DV-RPE) method. We show exceptional results on the challenging ScanNetV2 benchmark.
  arXiv  Detail & Related papers  (2023-08-08T17:14:14Z)
• Single-Stage Visual Query Localization in Egocentric Videos [79.71065005161566]
  We propose a single-stage VQL framework that is end-to-end trainable. We establish the query-video relationship by considering query-to-frame correspondences between the query and each video frame. Our experiments demonstrate that our approach outperforms prior VQL methods by 20% accuracy while obtaining a 10x improvement in inference speed.
  arXiv  Detail & Related papers  (2023-06-15T17:57:28Z)
• NAVI: Category-Agnostic Image Collections with High-Quality 3D Shape and Pose Annotations [64.95582364215548]
  NAVI is a new dataset of category-agnostic image collections with high-quality 3D scans and per-image 2D-3D alignments. These 2D-3D alignments allow us to extract accurate derivative annotations such as dense pixel correspondences, depth and segmentation maps.
  arXiv  Detail & Related papers  (2023-06-15T13:11:30Z)

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.