Four Ways to Improve Verbo-visual Fusion for Dense 3D Visual Grounding

• URL: http://arxiv.org/abs/2309.04561v3
• Date: Tue, 16 Jul 2024 08:14:11 GMT
• Title: Four Ways to Improve Verbo-visual Fusion for Dense 3D Visual Grounding
• Authors: Ozan Unal, Christos Sakaridis, Suman Saha, Luc Van Gool,
• Abstract summary: 3D visual grounding is the task of localizing the object in a 3D scene which is referred by a description in natural language. We propose a dense 3D grounding network, featuring four novel stand-alone modules that aim to improve grounding performance.
• Score: 56.00186960144545
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 3D visual grounding is the task of localizing the object in a 3D scene which is referred by a description in natural language. With a wide range of applications ranging from autonomous indoor robotics to AR/VR, the task has recently risen in popularity. A common formulation to tackle 3D visual grounding is grounding-by-detection, where localization is done via bounding boxes. However, for real-life applications that require physical interactions, a bounding box insufficiently describes the geometry of an object. We therefore tackle the problem of dense 3D visual grounding, i.e. referral-based 3D instance segmentation. We propose a dense 3D grounding network ConcreteNet, featuring four novel stand-alone modules that aim to improve grounding performance for challenging repetitive instances, i.e. instances with distractors of the same semantic class. First, we introduce a bottom-up attentive fusion module that aims to disambiguate inter-instance relational cues, next, we construct a contrastive training scheme to induce separation in the latent space, we then resolve view-dependent utterances via a learned global camera token, and finally we employ multi-view ensembling to improve referred mask quality. ConcreteNet ranks 1st on the challenging ScanRefer online benchmark and has won the ICCV 3rd Workshop on Language for 3D Scenes "3D Object Localization" challenge. Our code is available at ouenal.github.io/concretenet/.

Related papers

• Multi-Object 3D Grounding with Dynamic Modules and Language-Informed Spatial Attention [12.203336176170982]
  D-LISA is a two-stage approach incorporating three innovations. First, a dynamic vision module that enables a variable and learnable number of box proposals. Second, a dynamic camera positioning that extracts features for each proposal. Third, a language-informed spatial attention module that better reasons over the proposals to output the final prediction.
  arXiv  Detail & Related papers  (2024-10-29T17:52:20Z)
• Reasoning3D -- Grounding and Reasoning in 3D: Fine-Grained Zero-Shot Open-Vocabulary 3D Reasoning Part Segmentation via Large Vision-Language Models [20.277479473218513]
  We introduce a new task: Zero-Shot 3D Reasoning for parts searching and localization for objects. We design a simple baseline method, Reasoning3D, with the capability to understand and execute complex commands. We show that Reasoning3D can effectively localize and highlight parts of 3D objects based on implicit textual queries.
  arXiv  Detail & Related papers  (2024-05-29T17:56:07Z)
• SUGAR: Pre-training 3D Visual Representations for Robotics [85.55534363501131]
  We introduce a novel 3D pre-training framework for robotics named SUGAR. SUGAR captures semantic, geometric and affordance properties of objects through 3D point clouds. We show that SUGAR's 3D representation outperforms state-of-the-art 2D and 3D representations.
  arXiv  Detail & Related papers  (2024-04-01T21:23:03Z)
• Dense Object Grounding in 3D Scenes [28.05720194887322]
  Localizing objects in 3D scenes according to the semantics of a given natural language is a fundamental yet important task in the field of multimedia understanding. We introduce 3D Dense Object Grounding (3D DOG), to jointly localize multiple objects described in a more complicated paragraph rather than a single sentence. Our proposed 3DOGSFormer outperforms state-of-the-art 3D single-object grounding methods and their dense-object variants by significant margins.
  arXiv  Detail & Related papers  (2023-09-05T13:27:19Z)
• 3DRP-Net: 3D Relative Position-aware Network for 3D Visual Grounding [58.924180772480504]
  3D visual grounding aims to localize the target object in a 3D point cloud by a free-form language description. We propose a relation-aware one-stage framework, named 3D Relative Position-aware Network (3-Net)
  arXiv  Detail & Related papers  (2023-07-25T09:33:25Z)
• NeurOCS: Neural NOCS Supervision for Monocular 3D Object Localization [80.3424839706698]
  We present NeurOCS, a framework that uses instance masks 3D boxes as input to learn 3D object shapes by means of differentiable rendering. Our approach rests on insights in learning a category-level shape prior directly from real driving scenes. We make critical design choices to learn object coordinates more effectively from an object-centric view.
  arXiv  Detail & Related papers  (2023-05-28T16:18:41Z)
• Grounding 3D Object Affordance from 2D Interactions in Images [128.6316708679246]
  Grounding 3D object affordance seeks to locate objects' ''action possibilities'' regions in the 3D space. Humans possess the ability to perceive object affordances in the physical world through demonstration images or videos. We devise an Interaction-driven 3D Affordance Grounding Network (IAG), which aligns the region feature of objects from different sources.
  arXiv  Detail & Related papers  (2023-03-18T15:37:35Z)
• Looking Outside the Box to Ground Language in 3D Scenes [27.126171549887232]
  We propose a model for grounding language in 3D scenes with three main innovations. Iterative attention across the language stream, the point cloud feature stream and 3D box proposals. Joint supervision from 3D object annotations and language grounding annotations. When applied on language grounding on 2D images with minor changes, it performs on par with the state-of-the-art while converges in half of the GPU time.
  arXiv  Detail & Related papers  (2021-12-16T13:50:23Z)
• LanguageRefer: Spatial-Language Model for 3D Visual Grounding [72.7618059299306]
  We develop a spatial-language model for a 3D visual grounding problem. We show that our model performs competitively on visio-linguistic datasets proposed by ReferIt3D.
  arXiv  Detail & Related papers  (2021-07-07T18:55:03Z)

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.