OV3D-Bench: A Diagnostic Benchmark for Open-Vocabulary Monocular 3D Detection

• URL: http://arxiv.org/abs/2608.17110v1
• Date: Mon, 17 Aug 2026 20:38:57 GMT
• Title: OV3D-Bench: A Diagnostic Benchmark for Open-Vocabulary Monocular 3D Detection
• Abstract summary: OV3D-Bench is a diagnostic benchmark that compares open-vocabulary monocular 3D detectors under deployment-realistic conditions.<n>We evaluate seven representative detectors and find that (i) they localize objects well yet often mislabel a correctly localized box as a semantically adjacent category.<n>We demonstrate that simply remapping a frozen closed-vocabulary detector's predictions using a contrastive vision-language encoder such as SigLIPv2 performs competitively against recent purpose-built open-vocabulary methods.
• Score: 82.26920986339502
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Open-vocabulary monocular 3D detectors report strong in-domain performance, but each evaluates under a different protocol, several rely on per-image category oracles unavailable at deployment, and all collapse geometry and semantics into a single AP metric. To address this, we introduce OV3D-Bench, a diagnostic benchmark that compares open-vocabulary monocular 3D detectors under deployment-realistic conditions across seven indoor and outdoor datasets. Our benchmark replaces the per-image class name oracle with test-time dataset-level class name prompts, and decouples detection accuracy along three axes: localization, semantic robustness, and cross-domain transfer. We evaluate seven representative detectors and find that (i) they localize objects well yet often mislabel a correctly localized box as a semantically adjacent category; (ii) accuracy is highly sensitive to prompt phrasing (e.g. WildDet3D's performance collapses from 18.6 to 5.4 AP when prompted with "a detailed high-resolution photo of a car" rather than "car"); and (iii) the widely adopted target-aware protocol hides these errors (e.g. inflating DetAny3D's AP by 1.9 $\times$ on ScanNet). Lastly, we demonstrate that simply remapping a frozen closed-vocabulary detector's predictions using a contrastive vision-language encoder such as SigLIPv2 performs competitively against recent purpose-built open-vocabulary methods. This indicates that geometric localization is more mature, while open-vocabulary semantics remains the primary bottleneck.

Related papers

• SP3D: Boosting Sparsely-Supervised 3D Object Detection via Accurate Cross-Modal Semantic Prompts [13.349110509879312]
  sparsely-supervised 3D object detection has gained great attention, achieving performance close to fully-supervised 3D objectors.<n>We propose a boosting strategy, termed SP3D, to boost the 3D detector with robust feature discrimination capability under sparse annotation settings.<n> Experiments have validated that SP3D can enhance the performance of sparsely supervised detectors by a large margin under meager labeling conditions.
  arXiv  Detail & Related papers  (2025-03-09T06:08:04Z)
• Comprehensive Multi-Modal Prototypes are Simple and Effective Classifiers for Vast-Vocabulary Object Detection [68.26282316080558]
  Current open-world detectors can recognize a broader range of vocabularies, despite being trained on limited categories.<n>We introduce Prova, a prototype classifier for vast-vocabulary object detection.
  arXiv  Detail & Related papers  (2024-12-23T18:57:43Z)
• Open Vocabulary Monocular 3D Object Detection [10.424711580213616]
  We pioneer the study of open-vocabulary monocular 3D object detection, a novel task that aims to detect and localize objects in 3D space from a single RGB image. We introduce a class-agnostic approach that leverages open-vocabulary 2D detectors and lifts 2D bounding boxes into 3D space. Our approach decouples the recognition and localization of objects in 2D from the task of estimating 3D bounding boxes, enabling generalization across unseen categories.
  arXiv  Detail & Related papers  (2024-11-25T18:59:17Z)
• DetCLIPv3: Towards Versatile Generative Open-vocabulary Object Detection [111.68263493302499]
  We introduce DetCLIPv3, a high-performing detector that excels at both open-vocabulary object detection and hierarchical labels. DetCLIPv3 is characterized by three core designs: 1) Versatile model architecture; 2) High information density data; and 3) Efficient training strategy. DetCLIPv3 demonstrates superior open-vocabulary detection performance, outperforming GLIPv2, GroundingDINO, and DetCLIPv2 by 18.0/19.6/6.6 AP, respectively.
  arXiv  Detail & Related papers  (2024-04-14T11:01:44Z)
• OV-Uni3DETR: Towards Unified Open-Vocabulary 3D Object Detection via Cycle-Modality Propagation [67.56268991234371]
  OV-Uni3DETR achieves the state-of-the-art performance on various scenarios, surpassing existing methods by more than 6% on average. Code and pre-trained models will be released later.
  arXiv  Detail & Related papers  (2024-03-28T17:05:04Z)
• MS3D++: Ensemble of Experts for Multi-Source Unsupervised Domain Adaptation in 3D Object Detection [12.005805403222354]
  Deploying 3D detectors in unfamiliar domains has been demonstrated to result in a significant 70-90% drop in detection rate. We introduce MS3D++, a self-training framework for multi-source unsupervised domain adaptation in 3D object detection. MS3D++ generates high-quality pseudo-labels, allowing 3D detectors to achieve high performance on a range of lidar types.
  arXiv  Detail & Related papers  (2023-08-11T07:56:10Z)
• GLENet: Boosting 3D Object Detectors with Generative Label Uncertainty Estimation [70.75100533512021]
  In this paper, we formulate the label uncertainty problem as the diversity of potentially plausible bounding boxes of objects. We propose GLENet, a generative framework adapted from conditional variational autoencoders, to model the one-to-many relationship between a typical 3D object and its potential ground-truth bounding boxes with latent variables. The label uncertainty generated by GLENet is a plug-and-play module and can be conveniently integrated into existing deep 3D detectors.
  arXiv  Detail & Related papers  (2022-07-06T06:26:17Z)
• Progressive Coordinate Transforms for Monocular 3D Object Detection [52.00071336733109]
  We propose a novel and lightweight approach, dubbed em Progressive Coordinate Transforms (PCT) to facilitate learning coordinate representations. In this paper, we propose a novel and lightweight approach, dubbed em Progressive Coordinate Transforms (PCT) to facilitate learning coordinate representations.
  arXiv  Detail & Related papers  (2021-08-12T15:22:33Z)

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.