Fine-Grained Spatial and Verbal Losses for 3D Visual Grounding

• URL: http://arxiv.org/abs/2411.03405v1
• Date: Tue, 05 Nov 2024 18:39:25 GMT
• Title: Fine-Grained Spatial and Verbal Losses for 3D Visual Grounding
• Authors: Sombit Dey, Ozan Unal, Christos Sakaridis, Luc Van Gool,
• Abstract summary: 3D visual grounding consists of identifying the instance in a 3D scene which is referred by an accompanying language description. Most methods rely on a basic supervised cross-entropy loss on the predicted distribution over candidate instances. We introduce two novel losses for 3D visual grounding: a visual-level offset loss on regressed vector offsets from each instance to the ground-truth referred instance and a language-related span loss on predictions for the word-level span of the referred instance in the description.
• Score: 54.50661247353241
• License:
• Abstract: 3D visual grounding consists of identifying the instance in a 3D scene which is referred by an accompanying language description. While several architectures have been proposed within the commonly employed grounding-by-selection framework, the utilized losses are comparatively under-explored. In particular, most methods rely on a basic supervised cross-entropy loss on the predicted distribution over candidate instances, which fails to model both spatial relations between instances and the internal fine-grained word-level structure of the verbal referral. Sparse attempts to additionally supervise verbal embeddings globally by learning the class of the referred instance from the description or employing verbo-visual contrast to better separate instance embeddings do not fundamentally lift the aforementioned limitations. Responding to these shortcomings, we introduce two novel losses for 3D visual grounding: a visual-level offset loss on regressed vector offsets from each instance to the ground-truth referred instance and a language-related span loss on predictions for the word-level span of the referred instance in the description. In addition, we equip the verbo-visual fusion module of our new 3D visual grounding architecture AsphaltNet with a top-down bidirectional attentive fusion block, which enables the supervisory signals from our two losses to propagate to the respective converse branches of the network and thus aid the latter to learn context-aware instance embeddings and grounding-aware verbal embeddings. AsphaltNet proposes novel auxiliary losses to aid 3D visual grounding with competitive results compared to the state-of-the-art on the ReferIt3D benchmark.

Related papers

• R2G: Reasoning to Ground in 3D Scenes [22.917172452931844]
  Reasoning to Ground (R2G) is a neural symbolic model that grounds the target objects within 3D scenes in a reasoning manner. R2G explicitly models the 3D scene with a semantic concept-based scene graph; recurrently simulates the attention transferring across object entities. Experiments on Sr3D/Nr3D benchmarks show that R2G achieves a comparable result with the prior works while maintaining improved interpretability.
  arXiv  Detail & Related papers  (2024-08-24T06:52:14Z)
• Enhancing Generalizability of Representation Learning for Data-Efficient 3D Scene Understanding [50.448520056844885]
  We propose a generative Bayesian network to produce diverse synthetic scenes with real-world patterns. A series of experiments robustly display our method's consistent superiority over existing state-of-the-art pre-training approaches.
  arXiv  Detail & Related papers  (2024-06-17T07:43:53Z)
• SeCG: Semantic-Enhanced 3D Visual Grounding via Cross-modal Graph Attention [19.23636231942245]
  We propose a semantic-enhanced relational learning model based on a graph network with our designed memory graph attention layer. Our method replaces original language-independent encoding with cross-modal encoding in visual analysis. Experimental results on ReferIt3D and ScanRefer benchmarks show that the proposed method outperforms the existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-03-13T02:11:04Z)
• 2D Feature Distillation for Weakly- and Semi-Supervised 3D Semantic Segmentation [92.17700318483745]
  We propose an image-guidance network (IGNet) which builds upon the idea of distilling high level feature information from a domain adapted synthetically trained 2D semantic segmentation network. IGNet achieves state-of-the-art results for weakly-supervised LiDAR semantic segmentation on ScribbleKITTI, boasting up to 98% relative performance to fully supervised training with only 8% labeled points.
  arXiv  Detail & Related papers  (2023-11-27T07:57:29Z)
• Four Ways to Improve Verbo-visual Fusion for Dense 3D Visual Grounding [56.00186960144545]
  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.
  arXiv  Detail & Related papers  (2023-09-08T19:27:01Z)
• Lowis3D: Language-Driven Open-World Instance-Level 3D Scene Understanding [57.47315482494805]
  Open-world instance-level scene understanding aims to locate and recognize unseen object categories that are not present in the annotated dataset. This task is challenging because the model needs to both localize novel 3D objects and infer their semantic categories. We propose to harness pre-trained vision-language (VL) foundation models that encode extensive knowledge from image-text pairs to generate captions for 3D scenes.
  arXiv  Detail & Related papers  (2023-08-01T07:50:14Z)
• Distilling Coarse-to-Fine Semantic Matching Knowledge for Weakly Supervised 3D Visual Grounding [58.924180772480504]
  3D visual grounding involves finding a target object in a 3D scene that corresponds to a given sentence query. We propose to leverage weakly supervised annotations to learn the 3D visual grounding model. We design a novel semantic matching model that analyzes the semantic similarity between object proposals and sentences in a coarse-to-fine manner.
  arXiv  Detail & Related papers  (2023-07-18T13:49:49Z)
• Image Captioning with Visual Object Representations Grounded in the Textual Modality [14.797241131469486]
  We explore the possibilities of a shared embedding space between textual and visual modality. We propose an approach opposite to the current trend, grounding of the representations in the word embedding space of the captioning system.
  arXiv  Detail & Related papers  (2020-10-19T12:21:38Z)

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.