View-Consistent Hierarchical 3D Segmentation Using Ultrametric Feature Fields

• URL: http://arxiv.org/abs/2405.19678v2
• Date: Thu, 18 Jul 2024 02:28:14 GMT
• Title: View-Consistent Hierarchical 3D Segmentation Using Ultrametric Feature Fields
• Authors: Haodi He, Colton Stearns, Adam W. Harley, Leonidas J. Guibas,
• Abstract summary: We learn a novel feature field within a Neural Radiance Field (NeRF) representing a 3D scene. Our method takes view-inconsistent multi-granularity 2D segmentations as input and produces a hierarchy of 3D-consistent segmentations as output. We evaluate our method and several baselines on synthetic datasets with multi-view images and multi-granular segmentation, showcasing improved accuracy and viewpoint-consistency.
• Score: 52.08335264414515
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large-scale vision foundation models such as Segment Anything (SAM) demonstrate impressive performance in zero-shot image segmentation at multiple levels of granularity. However, these zero-shot predictions are rarely 3D-consistent. As the camera viewpoint changes in a scene, so do the segmentation predictions, as well as the characterizations of "coarse" or "fine" granularity. In this work, we address the challenging task of lifting multi-granular and view-inconsistent image segmentations into a hierarchical and 3D-consistent representation. We learn a novel feature field within a Neural Radiance Field (NeRF) representing a 3D scene, whose segmentation structure can be revealed at different scales by simply using different thresholds on feature distance. Our key idea is to learn an ultrametric feature space, which unlike a Euclidean space, exhibits transitivity in distance-based grouping, naturally leading to a hierarchical clustering. Put together, our method takes view-inconsistent multi-granularity 2D segmentations as input and produces a hierarchy of 3D-consistent segmentations as output. We evaluate our method and several baselines on synthetic datasets with multi-view images and multi-granular segmentation, showcasing improved accuracy and viewpoint-consistency. We additionally provide qualitative examples of our model's 3D hierarchical segmentations in real world scenes. The code and dataset are available at https://github.com/hardyho/ultrametric_feature_fields

Related papers

• Open-Vocabulary Octree-Graph for 3D Scene Understanding [54.11828083068082]
  Octree-Graph is a novel scene representation for open-vocabulary 3D scene understanding. An adaptive-octree structure is developed that stores semantics and depicts the occupancy of an object adjustably according to its shape.
  arXiv  Detail & Related papers  (2024-11-25T10:14:10Z)
• SAI3D: Segment Any Instance in 3D Scenes [68.57002591841034]
  We introduce SAI3D, a novel zero-shot 3D instance segmentation approach. Our method partitions a 3D scene into geometric primitives, which are then progressively merged into 3D instance segmentations. Empirical evaluations on ScanNet, Matterport3D and the more challenging ScanNet++ datasets demonstrate the superiority of our approach.
  arXiv  Detail & Related papers  (2023-12-17T09:05:47Z)
• 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)
• OmniSeg3D: Omniversal 3D Segmentation via Hierarchical Contrastive Learning [31.234212614311424]
  We propose OmniSeg3D, an omniversal segmentation method for segmenting anything in 3D all at once. In tackling the challenges posed by inconsistent 2D segmentations, this framework yields a global consistent 3D feature field. Experiments demonstrate the effectiveness of our method on high-quality 3D segmentation and accurate hierarchical structure understanding.
  arXiv  Detail & Related papers  (2023-11-20T11:04:59Z)
• 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)
• PanDepth: Joint Panoptic Segmentation and Depth Completion [19.642115764441016]
  We propose a multi-task model for panoptic segmentation and depth completion using RGB images and sparse depth maps. Our model successfully predicts fully dense depth maps and performs semantic segmentation, instance segmentation, and panoptic segmentation for every input frame.
  arXiv  Detail & Related papers  (2022-12-29T05:37:38Z)
• 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)
• 3D Instance Segmentation of MVS Buildings [5.2517244720510305]
  We present a novel framework for instance segmentation of 3D buildings from Multi-view Stereo (MVS) urban scenes. The emphasis of this work lies in detecting and segmenting 3D building instances even if they are attached and embedded in a large and imprecise 3D surface model.
  arXiv  Detail & Related papers  (2021-12-18T11:12:38Z)
• Learning Hyperbolic Representations for Unsupervised 3D Segmentation [3.516233423854171]
  We propose learning effective representations of 3D patches for unsupervised segmentation through a variational autoencoder (VAE) with a hyperbolic latent space and a proposed gyroplane convolutional layer. We demonstrate the effectiveness of our hyperbolic representations for unsupervised 3D segmentation on a hierarchical toy dataset, BraTS whole tumor dataset, and cryogenic electron microscopy data.
  arXiv  Detail & Related papers  (2020-12-03T02:15:31Z)

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.