Pith. sign in

REVIEW 2 cited by

OctFormer: Octree-based Transformers for 3D Point Clouds

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2305.03045 v2 pith:QZ55NIJF submitted 2023-05-04 cs.CV cs.GR

classification cs.CVcs.GR
keywords pointoctformercloudsattentionattentionscloudoctreetransformers
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We propose octree-based transformers, named OctFormer, for 3D point cloud learning. OctFormer can not only serve as a general and effective backbone for 3D point cloud segmentation and object detection but also have linear complexity and is scalable for large-scale point clouds. The key challenge in applying transformers to point clouds is reducing the quadratic, thus overwhelming, computation complexity of attentions. To combat this issue, several works divide point clouds into non-overlapping windows and constrain attentions in each local window. However, the point number in each window varies greatly, impeding the efficient execution on GPU. Observing that attentions are robust to the shapes of local windows, we propose a novel octree attention, which leverages sorted shuffled keys of octrees to partition point clouds into local windows containing a fixed number of points while permitting shapes of windows to change freely. And we also introduce dilated octree attention to expand the receptive field further. Our octree attention can be implemented in 10 lines of code with open-sourced libraries and runs 17 times faster than other point cloud attentions when the point number exceeds 200k. Built upon the octree attention, OctFormer can be easily scaled up and achieves state-of-the-art performances on a series of 3D segmentation and detection benchmarks, surpassing previous sparse-voxel-based CNNs and point cloud transformers in terms of both efficiency and effectiveness. Notably, on the challenging ScanNet200 dataset, OctFormer outperforms sparse-voxel-based CNNs by 7.3 in mIoU. Our code and trained models are available at https://wang-ps.github.io/octformer.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. High-quality Pseudo-labeling for Point Cloud Segmentation with Scene-level Annotation

    cs.CV 2025-06 conditional novelty 4.0 of 10

    A scene-level annotated point cloud segmentation framework combining contrastive 2D-3D feature alignment with region-point consistency improves pseudo-label quality and achieves SOTA on ScanNet and S3DIS.

  2. Vuyko Mistral: Adapting LLMs for Low-Resource Dialectal Translation

    cs.CL 2025-06 reject novelty 4.0 of 10

    The authors release a Hutsul-Ukrainian corpus and show LoRA-fine-tuned 7B models beat GPT-4o on automated and LLM-based metrics, but the evaluation is contaminated by overlapping training and test sources.

Pith tools