Any3DIS: Class-Agnostic 3D Instance Segmentation by 2D Mask Tracking

• URL: http://arxiv.org/abs/2411.16183v1
• Date: Mon, 25 Nov 2024 08:26:31 GMT
• Title: Any3DIS: Class-Agnostic 3D Instance Segmentation by 2D Mask Tracking
• Authors: Phuc Nguyen, Minh Luu, Anh Tran, Cuong Pham, Khoi Nguyen,
• Abstract summary: Existing 3D instance segmentation methods frequently encounter issues with over-segmentation, leading to redundant and inaccurate 3D proposals that complicate downstream tasks. This challenge arises from their unsupervised merging approach, where dense 2D masks are lifted across frames into point clouds to form 3D candidate proposals without direct supervision. We propose a 3D-Aware 2D Mask Tracking module that uses robust 3D priors from a 2D mask segmentation and tracking foundation model (SAM-2) to ensure consistent object masks across video frames.
• Score: 6.599971425078935
• License:
• Abstract: Existing 3D instance segmentation methods frequently encounter issues with over-segmentation, leading to redundant and inaccurate 3D proposals that complicate downstream tasks. This challenge arises from their unsupervised merging approach, where dense 2D instance masks are lifted across frames into point clouds to form 3D candidate proposals without direct supervision. These candidates are then hierarchically merged based on heuristic criteria, often resulting in numerous redundant segments that fail to combine into precise 3D proposals. To overcome these limitations, we propose a 3D-Aware 2D Mask Tracking module that uses robust 3D priors from a 2D mask segmentation and tracking foundation model (SAM-2) to ensure consistent object masks across video frames. Rather than merging all visible superpoints across views to create a 3D mask, our 3D Mask Optimization module leverages a dynamic programming algorithm to select an optimal set of views, refining the superpoints to produce a final 3D proposal for each object. Our approach achieves comprehensive object coverage within the scene while reducing unnecessary proposals, which could otherwise impair downstream applications. Evaluations on ScanNet200 and ScanNet++ confirm the effectiveness of our method, with improvements across Class-Agnostic, Open-Vocabulary, and Open-Ended 3D Instance Segmentation tasks.

Related papers

• XMask3D: Cross-modal Mask Reasoning for Open Vocabulary 3D Semantic Segmentation [72.12250272218792]
  We propose a more meticulous mask-level alignment between 3D features and the 2D-text embedding space through a cross-modal mask reasoning framework, XMask3D. We integrate 3D global features as implicit conditions into the pre-trained 2D denoising UNet, enabling the generation of segmentation masks. The generated 2D masks are employed to align mask-level 3D representations with the vision-language feature space, thereby augmenting the open vocabulary capability of 3D geometry embeddings.
  arXiv  Detail & Related papers  (2024-11-20T12:02:12Z)
• MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation [7.400926717561454]
  MSTA3D is a novel framework for superpoint-based 3D instance segmentation. It exploits multi-scale feature representation and introduces a twin-attention mechanism to effectively capture them. Our approach surpasses state-of-the-art 3D instance segmentation methods.
  arXiv  Detail & Related papers  (2024-11-04T04:14:39Z)
• EmbodiedSAM: Online Segment Any 3D Thing in Real Time [61.2321497708998]
  Embodied tasks require the agent to fully understand 3D scenes simultaneously with its exploration. An online, real-time, fine-grained and highly-generalized 3D perception model is desperately needed.
  arXiv  Detail & Related papers  (2024-08-21T17:57:06Z)
• MaskClustering: View Consensus based Mask Graph Clustering for Open-Vocabulary 3D Instance Segmentation [11.123421412837336]
  Open-vocabulary 3D instance segmentation is cutting-edge for its ability to segment 3D instances without predefined categories. Recent works first generate 2D open-vocabulary masks through 2D models and then merge them into 3D instances based on metrics calculated between two neighboring frames. We propose a novel metric, view consensus rate, to enhance the utilization of multi-view observations.
  arXiv  Detail & Related papers  (2024-01-15T14:56:15Z)
• Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask Guidance [49.14140194332482]
  We introduce Open3DIS, a novel solution designed to tackle the problem of Open-Vocabulary Instance within 3D scenes. Objects within 3D environments exhibit diverse shapes, scales, and colors, making precise instance-level identification a challenging task.
  arXiv  Detail & Related papers  (2023-12-17T10:07:03Z)
• 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)
• Segment Anything in 3D with Radiance Fields [83.14130158502493]
  This paper generalizes the Segment Anything Model (SAM) to segment 3D objects. We refer to the proposed solution as SA3D, short for Segment Anything in 3D. We show in experiments that SA3D adapts to various scenes and achieves 3D segmentation within seconds.
  arXiv  Detail & Related papers  (2023-04-24T17:57:15Z)
• Mask3D: Mask Transformer for 3D Semantic Instance Segmentation [89.41640045953378]
  We show that we can leverage generic Transformer building blocks to directly predict instance masks from 3D point clouds. Using Transformer decoders, the instance queries are learned by iteratively attending to point cloud features at multiple scales. Mask3D sets a new state-of-the-art on ScanNet test (+6.2 mAP), S3DIS 6-fold (+10.1 mAP),LS3D (+11.2 mAP) and ScanNet200 test (+12.4 mAP)
  arXiv  Detail & Related papers  (2022-10-06T17:55:09Z)

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.