3x2: 3D Object Part Segmentation by 2D Semantic Correspondences

• URL: http://arxiv.org/abs/2407.09648v1
• Date: Fri, 12 Jul 2024 19:08:00 GMT
• Title: 3x2: 3D Object Part Segmentation by 2D Semantic Correspondences
• Authors: Anh Thai, Weiyao Wang, Hao Tang, Stefan Stojanov, Matt Feiszli, James M. Rehg,
• Abstract summary: We propose to leverage a few annotated 3D shapes or richly annotated 2D datasets to perform 3D object part segmentation. We present our novel approach, termed 3-By-2 that achieves SOTA performance on different benchmarks with various granularity levels.
• Score: 33.99493183183571
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 3D object part segmentation is essential in computer vision applications. While substantial progress has been made in 2D object part segmentation, the 3D counterpart has received less attention, in part due to the scarcity of annotated 3D datasets, which are expensive to collect. In this work, we propose to leverage a few annotated 3D shapes or richly annotated 2D datasets to perform 3D object part segmentation. We present our novel approach, termed 3-By-2 that achieves SOTA performance on different benchmarks with various granularity levels. By using features from pretrained foundation models and exploiting semantic and geometric correspondences, we are able to overcome the challenges of limited 3D annotations. Our approach leverages available 2D labels, enabling effective 3D object part segmentation. Our method 3-By-2 can accommodate various part taxonomies and granularities, demonstrating interesting part label transfer ability across different object categories. Project website: \url{https://ngailapdi.github.io/projects/3by2/}.

Related papers

• 3D Part Segmentation via Geometric Aggregation of 2D Visual Features [57.20161517451834]
  Supervised 3D part segmentation models are tailored for a fixed set of objects and parts, limiting their transferability to open-set, real-world scenarios. Recent works have explored vision-language models (VLMs) as a promising alternative, using multi-view rendering and textual prompting to identify object parts. To address these limitations, we propose COPS, a COmprehensive model for Parts that blends semantics extracted from visual concepts and 3D geometry to effectively identify object parts.
  arXiv  Detail & Related papers  (2024-12-05T15:27:58Z)
• SAMPart3D: Segment Any Part in 3D Objects [23.97392239910013]
  3D part segmentation is a crucial and challenging task in 3D perception, playing a vital role in applications such as robotics, 3D generation, and 3D editing. Recent methods harness the powerful Vision Language Models (VLMs) for 2D-to-3D knowledge distillation, achieving zero-shot 3D part segmentation. In this work, we introduce SAMPart3D, a scalable zero-shot 3D part segmentation framework that segments any 3D object into semantic parts at multiple granularities.
  arXiv  Detail & Related papers  (2024-11-11T17:59:10Z)
• 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)
• SAM-guided Graph Cut for 3D Instance Segmentation [60.75119991853605]
  This paper addresses the challenge of 3D instance segmentation by simultaneously leveraging 3D geometric and multi-view image information. We introduce a novel 3D-to-2D query framework to effectively exploit 2D segmentation models for 3D instance segmentation. Our method achieves robust segmentation performance and can generalize across different types of scenes.
  arXiv  Detail & Related papers  (2023-12-13T18:59:58Z)
• PartSLIP++: Enhancing Low-Shot 3D Part Segmentation via Multi-View Instance Segmentation and Maximum Likelihood Estimation [32.2861030554128]
  PartSLIP, a recent advancement, has made significant strides in zero- and few-shot 3D part segmentation. We introduce PartSLIP++, an enhanced version designed to overcome the limitations of its predecessor. We show that PartSLIP++ demonstrates better performance over PartSLIP in both low-shot 3D semantic and instance-based object part segmentation tasks.
  arXiv  Detail & Related papers  (2023-12-05T01:33:04Z)
• Segment Any 3D Gaussians [85.93694310363325]
  This paper presents SAGA, a highly efficient 3D promptable segmentation method based on 3D Gaussian Splatting (3D-GS) Given 2D visual prompts as input, SAGA can segment the corresponding 3D target represented by 3D Gaussians within 4 ms. We show that SAGA achieves real-time multi-granularity segmentation with quality comparable to state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-12-01T17:15:24Z)
• DatasetNeRF: Efficient 3D-aware Data Factory with Generative Radiance Fields [68.94868475824575]
  This paper introduces a novel approach capable of generating infinite, high-quality 3D-consistent 2D annotations alongside 3D point cloud segmentations. We leverage the strong semantic prior within a 3D generative model to train a semantic decoder. Once trained, the decoder efficiently generalizes across the latent space, enabling the generation of infinite data.
  arXiv  Detail & Related papers  (2023-11-18T21:58:28Z)
• Tracking Objects with 3D Representation from Videos [57.641129788552675]
  We propose a new 2D Multiple Object Tracking paradigm, called P3DTrack. With 3D object representation learning from Pseudo 3D object labels in monocular videos, we propose a new 2D MOT paradigm, called P3DTrack.
  arXiv  Detail & Related papers  (2023-06-08T17:58:45Z)
• MvDeCor: Multi-view Dense Correspondence Learning for Fine-grained 3D Segmentation [91.6658845016214]
  We propose to utilize self-supervised techniques in the 2D domain for fine-grained 3D shape segmentation tasks. We render a 3D shape from multiple views, and set up a dense correspondence learning task within the contrastive learning framework. As a result, the learned 2D representations are view-invariant and geometrically consistent.
  arXiv  Detail & Related papers  (2022-08-18T00:48:15Z)

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.