PointCubeNet: 3D Part-level Reasoning with 3x3x3 Point Cloud Blocks

2025/11/10 by Kim, Da-Yeong, Cho, Yeong-Jun
Engineering · #3D Shape Modeling and Analysis #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Robot Manipulation and Learning #Robotics and Sensor-Based Localization

paper · doi:10.48550/arxiv.2511.06744

openalex publication_date 2025/11/10 · openalex created_date 2025/11/12 · openalex updated_date 2026/07/28

Abstract

In this paper, we propose PointCubeNet, a novel multi-modal 3D understanding framework that achieves part-level reasoning without requiring any part annotations. PointCubeNet comprises global and local branches. The proposed local branch, structured into 3x3x3 local blocks, enables part-level analysis of point cloud sub-regions with the corresponding local text labels. Leveraging the proposed pseudo-labeling method and local loss function, PointCubeNet is effectively trained in an unsupervised manner. The experimental results demonstrate that understanding 3D object parts enhances the understanding of the overall 3D object. In addition, this is the first attempt to perform unsupervised 3D part-level reasoning and achieves reliable and meaningful results.

Citations

• PARIS3D: Reasoning-based 3D Part Segmentation Using Large Multimodal Model
• LISA: Reasoning Segmentation via Large Language Model
• ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding
• PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning
• LAION-5B: An open large-scale dataset for training next generation image-text models
• CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-training
• BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
• PointCLIP: Point Cloud Understanding by CLIP
• Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling
• Learning Transferable Visual Models From Natural Language Supervision
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Language Models are Few-Shot Learners
• Representation Learning with Contrastive Predictive Coding
• Point Convolutional Neural Networks by Extension Operators
• PointCNN: Convolution On X-Transformed Points
• PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
• PointNet: Deep Learning on Point Sets for 3D Classification and\n Segmentation
• Volumetric and Multi-View CNNs for Object Classification on 3D Data
• Deep Residual Learning for Image Recognition
• ShapeNet: An Information-Rich 3D Model Repository
• Multi-view Convolutional Neural Networks for 3D Shape Recognition
• Going Deeper with Convolutions

Related

• PARIS3D: Reasoning-based 3D Part Segmentation Using Large Multimodal Model
• CoRe3D: Collaborative Reasoning as a Foundation for 3D Intelligence
• Global-Local Bidirectional Reasoning for Unsupervised Representation Learning of 3D Point Clouds
• Reasoning3D -- Grounding and Reasoning in 3D: Fine-Grained Zero-Shot Open-Vocabulary 3D Reasoning Part Segmentation via Large Vision-Language Models
• Reason3D: Searching and Reasoning 3D Segmentation via Large Language Model