Zero-shot point cloud segmentation by transferring geometric primitives
We investigate transductive zero-shot point cloud semantic segmentation, where the network is trained on seen objects and able to segment unseen objects. The 3D geometric elements are essential cues to imply a novel 3D object type. However, previous methods neglect the fine-grained relationship between the language and the 3D geometric elements. To this end, we propose a novel framework to learn the geometric primitives shared in seen and unseen categories' objects and employ a fine-grained alignment between language and the learned geometric primitives. Therefore, guided by language, the network recognizes the novel objects represented with geometric primitives. Specifically, we formulate a novel point visual representation, the similarity vector of the point's feature to the learnable prototypes, where the prototypes automatically encode geometric primitives via back-propagation. Besides, we propose a novel Unknown-aware InfoNCE Loss to fine-grained align the visual representation with language. Extensive experiments show that our method significantly outperforms other state-of-the-art methods in the harmonic mean-intersection-over-union (hIoU), with the improvement of 17.8\%, 30.4\%, 9.2\% and 7.9\% on S3DIS, ScanNet, SemanticKITTI and nuScenes datasets, respectively. Codes are available (https://github.com/runnanchen/Zero-Shot-Point-Cloud-Segmentation)
Code (0)
등록된 구현이 없습니다.
Tasks
Point Cloud SegmentationSemantic SegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Transferring CLIP's Knowledge into Zero-Shot Point Cloud Semantic Segmentation
Traditional 3D segmentation methods can only recognize a fixed range of classes that appear in the training set, which limits their application in real-world scenarios due to the lack of generalization ability. Large-sca…
3D Semantic SegmentationPoint Cloud SegmentationSegmentationSemantic Segmentation+1Prototype Adaption and Projection for Few- and Zero-shot 3D Point Cloud Semantic Segmentation
In this work, we address the challenging task of few-shot and zero-shot 3D point cloud semantic segmentation. The success of few-shot semantic segmentation in 2D computer vision is mainly driven by the pre-training on la…
Few-shot 3D semantic segmentationSegmentationGZSL-MoE: Apprentissage G{é}n{é}ralis{é} Z{é}ro-Shot bas{é} sur le M{é}lange d'Experts pour la Segmentation S{é}mantique de Nuages de Points 3DAppliqu{é} {à} un Jeu de Donn{é}es d'Environnement de Collaboration Humain-Robot
Generative Zero-Shot Learning approach (GZSL) has demonstrated significant potential in 3D point cloud semantic segmentation tasks. GZSL leverages generative models like GANs or VAEs to synthesize realistic features (rea…
Generalized Zero-Shot Learning3D Semantic SegmentationSee More and Know More: Zero-shot Point Cloud Segmentation via Multi-modal Visual Data
Zero-shot point cloud segmentation aims to make deep models capable of recognizing novel objects in point cloud that are unseen in the training phase. Recent trends favor the pipeline which transfers knowledge from seen …
Point Cloud SegmentationZero-Shot Learning3D-PointZshotS: Geometry-Aware 3D Point Cloud Zero-Shot Semantic Segmentation Narrowing the Visual-Semantic Gap
Existing zero-shot 3D point cloud segmentation methods often struggle with limited transferability from seen classes to unseen classes and from semantic to visual space. To alleviate this, we introduce 3D-PointZshotS, a …
Point Cloud SegmentationSemantic SegmentationTransfer LearningZero Shot Segmentation+1