mlsanityData to 14 Oct 2026

Multi-task 3D building understanding with multi-modal pretraining

arXiv 2306.10146 ↗First posted 16 Jun 2023cs.CV eess.IVcited by 1

Not on the map. Why?

Abstract (arXiv)

This paper explores various learning strategies for 3D building type classification and part segmentation on the BuildingNet dataset. ULIP with PointNeXt and PointNeXt segmentation are extended for the classification and segmentation task on BuildingNet dataset. The best multi-task PointNeXt-s model with multi-modal pretraining achieves 59.36 overall accuracy for 3D building type classification, and 31.68 PartIoU for 3D building part segmentation on validation split. The final PointNeXt XL model achieves 31.33 PartIoU and 22.78 ShapeIoU on test split for BuildingNet-Points segmentation, which significantly improved over PointNet++ model reported from BuildingNet paper, and it won the 1st place in the BuildingNet challenge at CVPR23 StruCo3D workshop.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 19 of its 22 references that are in the map. First posted on arXiv 16 Jun 2023.

Builds on

19 of 22 references.

References · 19

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  3. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  4. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  5. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,451
  6. 2020Point Transformercited by 1,470
  7. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,208
  8. 2021Open-vocabulary Object Detection via Vision and Language Knowledge Distillationcited by 906
  9. 2021KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3Dcited by 575
  10. 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 526
  11. 2021SLIP: Self-supervision meets Language-Image Pre-trainingcited by 436
  12. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 436
7 more
  1. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 379
  2. 2017Submanifold Sparse Convolutional Networkscited by 223
  3. 2023ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understandingcited by 202
  4. 2016What makes ImageNet good for transfer learning?cited by 192
  5. 2021BuildingNet: Learning to Label 3D Buildingscited by 33
  6. 2021Synthetic 3D Data Generation Pipeline for Geometric Deep Learning in Architecturecited by 7
  7. 2022Vitruvio: 3D Building Meshes via Single Perspective Sketchescited by 5

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024DC3DO: Diffusion Classifier for 3D Objectscited by 0