Weakly-Supervised 3D Scene Graph Generation via Visual-Linguistic Assisted Pseudo-labeling

• URL: http://arxiv.org/abs/2404.02527v1
• Date: Wed, 3 Apr 2024 07:30:09 GMT
• Title: Weakly-Supervised 3D Scene Graph Generation via Visual-Linguistic Assisted Pseudo-labeling
• Authors: Xu Wang, Yifan Li, Qiudan Zhang, Wenhui Wu, Mark Junjie Li, Jianmin Jinag,
• Abstract summary: We propose a weakly-supervised 3D scene graph generation method via Visual-Linguistic Assisted Pseudo-labeling. Our 3D-VLAP exploits the superior ability of current large-scale visual-linguistic models to align the semantics between texts and 2D images. We design an edge self-attention based graph neural network to generate scene graphs of 3D point cloud scenes.
• Score: 9.440800948514449
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Learning to build 3D scene graphs is essential for real-world perception in a structured and rich fashion. However, previous 3D scene graph generation methods utilize a fully supervised learning manner and require a large amount of entity-level annotation data of objects and relations, which is extremely resource-consuming and tedious to obtain. To tackle this problem, we propose 3D-VLAP, a weakly-supervised 3D scene graph generation method via Visual-Linguistic Assisted Pseudo-labeling. Specifically, our 3D-VLAP exploits the superior ability of current large-scale visual-linguistic models to align the semantics between texts and 2D images, as well as the naturally existing correspondences between 2D images and 3D point clouds, and thus implicitly constructs correspondences between texts and 3D point clouds. First, we establish the positional correspondence from 3D point clouds to 2D images via camera intrinsic and extrinsic parameters, thereby achieving alignment of 3D point clouds and 2D images. Subsequently, a large-scale cross-modal visual-linguistic model is employed to indirectly align 3D instances with the textual category labels of objects by matching 2D images with object category labels. The pseudo labels for objects and relations are then produced for 3D-VLAP model training by calculating the similarity between visual embeddings and textual category embeddings of objects and relations encoded by the visual-linguistic model, respectively. Ultimately, we design an edge self-attention based graph neural network to generate scene graphs of 3D point cloud scenes. Extensive experiments demonstrate that our 3D-VLAP achieves comparable results with current advanced fully supervised methods, meanwhile significantly alleviating the pressure of data annotation.

Related papers

• Cross-Modal Self-Training: Aligning Images and Pointclouds to Learn Classification without Labels [69.55622471172941]
  Large-scale vision 2D vision language models, such as CLIP can be aligned with a 3D encoder to learn generalizable (open-vocabulary) 3D vision models. We propose an optimization framework: Cross-MoST: Cross-Modal Self-Training, to improve the label-free classification performance of a zero-shot 3D vision model.
  arXiv  Detail & Related papers  (2024-04-15T21:30:50Z)
• View Selection for 3D Captioning via Diffusion Ranking [54.78058803763221]
  Cap3D method renders 3D objects into 2D views for captioning using pre-trained models. Some rendered views of 3D objects are atypical, deviating from the training data of standard image captioning models and causing hallucinations. We present DiffuRank, a method that leverages a pre-trained text-to-3D model to assess the alignment between 3D objects and their 2D rendered views.
  arXiv  Detail & Related papers  (2024-04-11T17:58:11Z)
• Weakly-Supervised 3D Visual Grounding based on Visual Linguistic Alignment [26.858034573776198]
  Existing 3D visual grounding approaches require a substantial number of bounding box annotations for text queries. We propose textbf3D-VLA, a weakly supervised approach for textbf3D visual grounding based on textbfVisual textbfLinguistic textbfAlignment. Our 3D-VLA exploits the superior ability of current large-scale vision-language models (VLMs) on aligning the semantics between texts and 2D images.
  arXiv  Detail & Related papers  (2023-12-15T09:08:14Z)
• Weakly Supervised 3D Object Detection via Multi-Level Visual Guidance [72.6809373191638]
  We propose a framework to study how to leverage constraints between 2D and 3D domains without requiring any 3D labels. Specifically, we design a feature-level constraint to align LiDAR and image features based on object-aware regions. Second, the output-level constraint is developed to enforce the overlap between 2D and projected 3D box estimations. Third, the training-level constraint is utilized by producing accurate and consistent 3D pseudo-labels that align with the visual data.
  arXiv  Detail & Related papers  (2023-12-12T18:57:25Z)
• CLIP$^2$: Contrastive Language-Image-Point Pretraining from Real-World Point Cloud Data [80.42480679542697]
  We propose Contrastive Language-Image-Point Cloud Pretraining (CLIP$2$) to learn the transferable 3D point cloud representation in realistic scenarios. Specifically, we exploit naturally-existed correspondences in 2D and 3D scenarios, and build well-aligned and instance-based text-image-point proxies from those complex scenarios.
  arXiv  Detail & Related papers  (2023-03-22T09:32:45Z)
• 3D-TOGO: Towards Text-Guided Cross-Category 3D Object Generation [107.46972849241168]
  3D-TOGO model generates 3D objects in the form of the neural radiance field with good texture. Experiments on the largest 3D object dataset (i.e., ABO) are conducted to verify that 3D-TOGO can better generate high-quality 3D objects.
  arXiv  Detail & Related papers  (2022-12-02T11:31:49Z)
• CoCoNets: Continuous Contrastive 3D Scene Representations [21.906643302668716]
  This paper explores self-supervised learning of amodal 3D feature representations from RGB and RGB-D posed images and videos. We show the resulting 3D visual feature representations effectively scale across objects and scenes, imagine information occluded or missing from the input viewpoints, track objects over time, align semantically related objects in 3D, and improve 3D object detection.
  arXiv  Detail & Related papers  (2021-04-08T15:50:47Z)
• Joint Deep Multi-Graph Matching and 3D Geometry Learning from Inhomogeneous 2D Image Collections [57.60094385551773]
  We propose a trainable framework for learning a deformable 3D geometry model from inhomogeneous image collections. We in addition obtain the underlying 3D geometry of the objects depicted in the 2D images.
  arXiv  Detail & Related papers  (2021-03-31T17:25:36Z)

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.