3D-AVS: LiDAR-based 3D Auto-Vocabulary Segmentation

• URL: http://arxiv.org/abs/2406.09126v3
• Date: Sun, 30 Mar 2025 19:24:42 GMT
• Title: 3D-AVS: LiDAR-based 3D Auto-Vocabulary Segmentation
• Authors: Weijie Wei, Osman Ülger, Fatemeh Karimi Nejadasl, Theo Gevers, Martin R. Oswald,
• Abstract summary: 3D-AVS is a method for Auto-Vocabulary of 3D point clouds for which the vocabulary is unknown and auto-generated for each input at runtime.<n>3D-AVS first recognizes semantic entities from image or point cloud data and then segments all points with the automatically generated vocabulary.<n>Our method incorporates both image-based and point-based recognition, enhancing robustness under challenging lighting conditions.
• Score: 20.7179907935644
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Open-Vocabulary Segmentation (OVS) methods offer promising capabilities in detecting unseen object categories, but the category must be known and needs to be provided by a human, either via a text prompt or pre-labeled datasets, thus limiting their scalability. We propose 3D-AVS, a method for Auto-Vocabulary Segmentation of 3D point clouds for which the vocabulary is unknown and auto-generated for each input at runtime, thus eliminating the human in the loop and typically providing a substantially larger vocabulary for richer annotations. 3D-AVS first recognizes semantic entities from image or point cloud data and then segments all points with the automatically generated vocabulary. Our method incorporates both image-based and point-based recognition, enhancing robustness under challenging lighting conditions where geometric information from LiDAR is especially valuable. Our point-based recognition features a Sparse Masked Attention Pooling (SMAP) module to enrich the diversity of recognized objects. To address the challenges of evaluating unknown vocabularies and avoid annotation biases from label synonyms, hierarchies, or semantic overlaps, we introduce the annotation-free Text-Point Semantic Similarity (TPSS) metric for assessing generated vocabulary quality. Our evaluations on nuScenes and ScanNet200 demonstrate 3D-AVS's ability to generate semantic classes with accurate point-wise segmentations. Codes will be released at https://github.com/ozzyou/3D-AVS

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)
• LESS: Label-Efficient and Single-Stage Referring 3D Segmentation [55.06002976797879]
  Referring 3D is a visual-language task that segments all points of the specified object from a 3D point cloud described by a sentence of query. We propose a novel Referring 3D pipeline, Label-Efficient and Single-Stage, dubbed LESS, which is only under the supervision of efficient binary mask. We achieve state-of-the-art performance on ScanRefer dataset by surpassing the previous methods about 3.7% mIoU using only binary labels.
  arXiv  Detail & Related papers  (2024-10-17T07:47:41Z)
• Auto-Vocabulary Semantic Segmentation [13.410217680999462]
  We introduce textitAuto-Vocabulary Semantics (AVS), advancing open-ended image understanding. Our framework autonomously identifies relevant class names using enhanced BLIP embedding. Our method sets new benchmarks on datasets such as PASCAL VOC and Context, ADE20K, and Cityscapes for AVS.
  arXiv  Detail & Related papers  (2023-12-07T18:55:52Z)
• 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)
• Open-Vocabulary Point-Cloud Object Detection without 3D Annotation [62.18197846270103]
  The goal of open-vocabulary 3D point-cloud detection is to identify novel objects based on arbitrary textual descriptions. We develop a point-cloud detector that can learn a general representation for localizing various objects. We also propose a novel de-biased triplet cross-modal contrastive learning to connect the modalities of image, point-cloud and text.
  arXiv  Detail & Related papers  (2023-04-03T08:22:02Z)
• Three ways to improve feature alignment for open vocabulary detection [88.65076922242184]
  Key problem in zero-shot open vocabulary detection is how to align visual and text features, so that the detector performs well on unseen classes. Previous approaches train the feature pyramid and detection head from scratch, which breaks the vision-text feature alignment established during pretraining. We propose three methods to alleviate these issues. Firstly, a simple scheme is used to augment the text embeddings which prevents overfitting to a small number of classes seen during training. Secondly, the feature pyramid network and the detection head are modified to include trainable shortcuts. Finally, a self-training approach is used to leverage a larger corpus of
  arXiv  Detail & Related papers  (2023-03-23T17:59:53Z)
• ALSO: Automotive Lidar Self-supervision by Occupancy estimation [70.70557577874155]
  We propose a new self-supervised method for pre-training the backbone of deep perception models operating on point clouds. The core idea is to train the model on a pretext task which is the reconstruction of the surface on which the 3D points are sampled. The intuition is that if the network is able to reconstruct the scene surface, given only sparse input points, then it probably also captures some fragments of semantic information.
  arXiv  Detail & Related papers  (2022-12-12T13:10:19Z)
• EDA: Explicit Text-Decoupling and Dense Alignment for 3D Visual Grounding [4.447173454116189]
  3D visual grounding aims to find the object within point clouds mentioned by free-form natural language descriptions with rich semantic cues. We present EDA that Explicitly Decouples the textual attributes in a sentence. We further introduce a new visual grounding task, locating objects without object names, which can thoroughly evaluate the model's dense alignment capacity.
  arXiv  Detail & Related papers  (2022-09-29T17:00:22Z)
• Point2Seq: Detecting 3D Objects as Sequences [58.63662049729309]
  We present a simple and effective framework, named Point2Seq, for 3D object detection from point clouds. We view each 3D object as a sequence of words and reformulate the 3D object detection task as decoding words from 3D scenes in an auto-regressive manner.
  arXiv  Detail & Related papers  (2022-03-25T00:20:31Z)
• Box2Seg: Learning Semantics of 3D Point Clouds with Box-Level Supervision [65.19589997822155]
  We introduce a neural architecture, termed Box2Seg, to learn point-level semantics of 3D point clouds with bounding box-level supervision. We show that the proposed network can be trained with cheap, or even off-the-shelf bounding box-level annotations and subcloud-level tags.
  arXiv  Detail & Related papers  (2022-01-09T09:07:48Z)
• Learning to Detect Instance-level Salient Objects Using Complementary Image Labels [55.049347205603304]
  We present the first weakly-supervised approach to the salient instance detection problem. We propose a novel weakly-supervised network with three branches: a Saliency Detection Branch leveraging class consistency information to locate candidate objects; a Boundary Detection Branch exploiting class discrepancy information to delineate object boundaries; and a Centroid Detection Branch using subitizing information to detect salient instance centroids.
  arXiv  Detail & Related papers  (2021-11-19T10:15:22Z)
• Video Class Agnostic Segmentation Benchmark for Autonomous Driving [13.312978643938202]
  In certain safety-critical robotics applications, it is important to segment all objects, including those unknown at training time. We formalize the task of video class segmentation from monocular video sequences in autonomous driving to account for unknown objects.
  arXiv  Detail & Related papers  (2021-03-19T20:41:40Z)
• LRGNet: Learnable Region Growing for Class-Agnostic Point Cloud Segmentation [19.915593390338337]
  This research proposes a learnable region growing method for class-agnostic point cloud segmentation. The proposed method is able to segment any class of objects using a single deep neural network without any assumptions about their shapes and sizes.
  arXiv  Detail & Related papers  (2021-03-16T15:58:01Z)
• 4D Panoptic LiDAR Segmentation [27.677435778317054]
  We propose 4D panoptic LiDAR segmentation to assign a semantic class and a temporally-consistent instance ID to a sequence of 3D points. Inspired by recent advances in benchmarking of multi-object tracking, we propose to adopt a new evaluation metric that separates the semantic and point-to-instance association of the task.
  arXiv  Detail & Related papers  (2021-02-24T18:56:16Z)
• Synthesizing the Unseen for Zero-shot Object Detection [72.38031440014463]
  We propose to synthesize visual features for unseen classes, so that the model learns both seen and unseen objects in the visual domain. We use a novel generative model that uses class-semantics to not only generate the features but also to discriminatively separate them.
  arXiv  Detail & Related papers  (2020-10-19T12:36:11Z)
• Few-shot 3D Point Cloud Semantic Segmentation [138.80825169240302]
  We propose a novel attention-aware multi-prototype transductive few-shot point cloud semantic segmentation method. Our proposed method shows significant and consistent improvements compared to baselines in different few-shot point cloud semantic segmentation settings.
  arXiv  Detail & Related papers  (2020-06-22T08:05:25Z)

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.