Mono3DVG: 3D Visual Grounding in Monocular Images

• URL: http://arxiv.org/abs/2312.08022v1
• Date: Wed, 13 Dec 2023 09:49:59 GMT
• Title: Mono3DVG: 3D Visual Grounding in Monocular Images
• Authors: Yang Zhan, Yuan Yuan, Zhitong Xiong
• Abstract summary: We introduce a novel task of 3D visual grounding in monocular RGB images using language descriptions with both appearance and geometry information. We build a large-scale dataset, Mono3DRefer, which contains 3D object targets with corresponding geometric text descriptions. We propose Mono3DVG-TR, an end-to-end transformer-based network, which takes advantage of both the appearance and geometry information in text embeddings.
• Score: 12.191320182791483
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We introduce a novel task of 3D visual grounding in monocular RGB images using language descriptions with both appearance and geometry information. Specifically, we build a large-scale dataset, Mono3DRefer, which contains 3D object targets with their corresponding geometric text descriptions, generated by ChatGPT and refined manually. To foster this task, we propose Mono3DVG-TR, an end-to-end transformer-based network, which takes advantage of both the appearance and geometry information in text embeddings for multi-modal learning and 3D object localization. Depth predictor is designed to explicitly learn geometry features. The dual text-guided adapter is proposed to refine multiscale visual and geometry features of the referred object. Based on depth-text-visual stacking attention, the decoder fuses object-level geometric cues and visual appearance into a learnable query. Comprehensive benchmarks and some insightful analyses are provided for Mono3DVG. Extensive comparisons and ablation studies show that our method significantly outperforms all baselines. The dataset and code will be publicly available at: https://github.com/ZhanYang-nwpu/Mono3DVG.

Related papers

• RefMask3D: Language-Guided Transformer for 3D Referring Segmentation [32.11635464720755]
  RefMask3D aims to explore the comprehensive multi-modal feature interaction and understanding. RefMask3D outperforms previous state-of-the-art method by a large margin of 3.16% mIoU on the challenging ScanRefer dataset.
  arXiv  Detail & Related papers  (2024-07-25T17:58:03Z)
• TeMO: Towards Text-Driven 3D Stylization for Multi-Object Meshes [67.5351491691866]
  We present a novel framework, dubbed TeMO, to parse multi-object 3D scenes and edit their styles. Our method can synthesize high-quality stylized content and outperform the existing methods over a wide range of multi-object 3D meshes.
  arXiv  Detail & Related papers  (2023-12-07T12:10:05Z)
• ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and Prototype Guidance [48.748738590964216]
  We propose ViewRefer, a multi-view framework for 3D visual grounding. For the text branch, ViewRefer expands a single grounding text to multiple geometry-consistent descriptions. In the 3D modality, a transformer fusion module with inter-view attention is introduced to boost the interaction of objects across views.
  arXiv  Detail & Related papers  (2023-03-29T17:59:10Z)
• Viewpoint Equivariance for Multi-View 3D Object Detection [35.4090127133834]
  State-of-the-art methods focus on reasoning and decoding object bounding boxes from multi-view camera input. We introduce VEDet, a novel 3D object detection framework that exploits 3D multi-view geometry.
  arXiv  Detail & Related papers  (2023-03-25T19:56:41Z)
• PointMCD: Boosting Deep Point Cloud Encoders via Multi-view Cross-modal Distillation for 3D Shape Recognition [55.38462937452363]
  We propose a unified multi-view cross-modal distillation architecture, including a pretrained deep image encoder as the teacher and a deep point encoder as the student. By pair-wise aligning multi-view visual and geometric descriptors, we can obtain more powerful deep point encoders without exhausting and complicated network modification.
  arXiv  Detail & Related papers  (2022-07-07T07:23:20Z)
• MonoDETR: Depth-guided Transformer for Monocular 3D Object Detection [61.89277940084792]
  We introduce the first DETR framework for Monocular DEtection with a depth-guided TRansformer, named MonoDETR. We formulate 3D object candidates as learnable queries and propose a depth-guided decoder to conduct object-scene depth interactions. On KITTI benchmark with monocular images as input, MonoDETR achieves state-of-the-art performance and requires no extra dense depth annotations.
  arXiv  Detail & Related papers  (2022-03-24T19:28:54Z)
• Learning Geometry-Guided Depth via Projective Modeling for Monocular 3D Object Detection [70.71934539556916]
  We learn geometry-guided depth estimation with projective modeling to advance monocular 3D object detection. Specifically, a principled geometry formula with projective modeling of 2D and 3D depth predictions in the monocular 3D object detection network is devised. Our method remarkably improves the detection performance of the state-of-the-art monocular-based method without extra data by 2.80% on the moderate test setting.
  arXiv  Detail & Related papers  (2021-07-29T12:30:39Z)
• Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloud [50.56461318879761]
  We propose Geometry-Disentangled Attention Network (GDANet) for 3D image processing. GDANet disentangles point clouds into contour and flat part of 3D objects, respectively denoted by sharp and gentle variation components. Experiments on 3D object classification and segmentation benchmarks demonstrate that GDANet achieves the state-of-the-arts with fewer parameters.
  arXiv  Detail & Related papers  (2020-12-20T13:35:00Z)
• RISA-Net: Rotation-Invariant Structure-Aware Network for Fine-Grained 3D Shape Retrieval [46.02391761751015]
  Fine-grained 3D shape retrieval aims to retrieve 3D shapes similar to a query shape in a repository with models belonging to the same class. We introduce a novel deep architecture, RISA-Net, which learns rotation invariant 3D shape descriptors. Our method is able to learn the importance of geometric and structural information of all the parts when generating the final compact latent feature of a 3D shape.
  arXiv  Detail & Related papers  (2020-10-02T13:06:12Z)

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.