mlsanityData to 14 Oct 2026

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

arXiv 2511.06744 ↗First posted 10 Nov 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 24 of its 30 references that are in the map. First posted on arXiv 10 Nov 2025.

Builds on

24 of 30 references.

References · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  5. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  6. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  7. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  8. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,322
  9. 2014Going Deeper with Convolutionscited by 4,241
  10. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
  11. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,864
  12. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
12 more
  1. 2023LISA: Reasoning Segmentation via Large Language Modelcited by 776
  2. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  3. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 653
  4. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 565
  5. 2021PointCLIP: Point Cloud Understanding by CLIPcited by 463
  6. 2022ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understandingcited by 267
  7. 2016Volumetric and Multi-View CNNs for Object Classification on 3D Datacited by 240
  8. 2023ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understandingcited by 202
  9. 2022PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learningcited by 187
  10. 2022CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-trainingcited by 160
  11. 2018Point Convolutional Neural Networks by Extension Operatorscited by 154
  12. 2024PARIS3D: Reasoning-based 3D Part Segmentation Using Large Multimodal Modelcited by 9

Built on by

Not cited yet.