mlsanityData to 14 Oct 2026

Technical Report for ICRA 2025 GOOSE 3D Semantic Segmentation Challenge: Adaptive Point Cloud Understanding for Heterogeneous Robotic Systems

arXiv 2506.06995 ↗First posted 8 Jun 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

This technical report presents the implementation details of the winning solution for the ICRA 2025 GOOSE 3D Semantic Segmentation Challenge. This challenge focuses on semantic segmentation of 3D point clouds from diverse unstructured outdoor environments collected from multiple robotic platforms. This problem was addressed by implementing Point Prompt Tuning (PPT) integrated with Point Transformer v3 (PTv3) backbone, enabling adaptive processing of heterogeneous LiDAR data through platform-specific conditioning and cross-dataset class alignment strategies. The model is trained without requiring additional external data. As a result, this approach achieved substantial performance improvements with mIoU increases of up to 22.59% on challenging platforms compared to the baseline PTv3 model, demonstrating the effectiveness of adaptive point cloud understanding for field robotics applications.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 21 references that are in the map. First posted on arXiv 8 Jun 2025.

Builds on

15 of 21 references.

References · 15

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  3. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  4. 2020Point Transformercited by 1,470
  5. 2023Point Transformer V3: Simpler, Faster, Strongercited by 589
  6. 2022Point Transformer V2: Grouped Vector Attention and Partition-based Poolingcited by 388
  7. 2022CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understandingcited by 198
  8. 20222DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Cloudscited by 158
  9. 2025Sonata: Self-Supervised Learning of Reliable Point Representationscited by 110
  10. 2023Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Trainingcited by 86
  11. 2023The GOOSE Dataset for Perception in Unstructured Environmentscited by 37
  12. 2025DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentationcited by 31
3 more
  1. 2023LiDAR-Camera Panoptic Segmentation via Geometry-Consistent and Semantic-Aware Alignmentcited by 18
  2. 2024Excavating in the Wild: The GOOSE-Ex Dataset for Semantic Segmentationcited by 13
  3. 2021Person-MinkUNet: 3D Person Detection with LiDAR Point Cloudcited by 3

Built on by

Not cited yet.