Can we Trust Unreliable Voxels? Exploring 3D Semantic Occupancy Prediction under Label Noise

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Wenxin, Peng, Kunyu, Wen, Di, Zheng, Junwei, Wei, Jiale, Duan, Mengfei, Zhang, Yuheng, Fan, Rui, Yang, Kailun
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917318432391168
author Li, Wenxin
Peng, Kunyu
Wen, Di
Zheng, Junwei
Wei, Jiale
Duan, Mengfei
Zhang, Yuheng
Fan, Rui
Yang, Kailun
author_facet Li, Wenxin
Peng, Kunyu
Wen, Di
Zheng, Junwei
Wei, Jiale
Duan, Mengfei
Zhang, Yuheng
Fan, Rui
Yang, Kailun
contents 3D semantic occupancy prediction is a cornerstone of robotic perception, yet real-world voxel annotations are inherently corrupted by structural artifacts and dynamic trailing effects. This raises a critical but underexplored question: can autonomous systems safely rely on such unreliable occupancy supervision? To systematically investigate this issue, we establish OccNL, the first benchmark dedicated to 3D occupancy under occupancy-asymmetric and dynamic trailing noise. Our analysis reveals a fundamental domain gap: state-of-the-art 2D label noise learning strategies collapse catastrophically in sparse 3D voxel spaces, exposing a critical vulnerability in existing paradigms. To address this challenge, we propose DPR-Occ, a principled label noise-robust framework that constructs reliable supervision through dual-source partial label reasoning. By synergizing temporal model memory with representation-level structural affinity, DPR-Occ dynamically expands and prunes candidate label sets to preserve true semantics while suppressing noise propagation. Extensive experiments on SemanticKITTI demonstrate that DPR-Occ prevents geometric and semantic collapse under extreme corruption. Notably, even at 90% label noise, our method achieves significant performance gains (up to 2.57% mIoU and 13.91% IoU) over existing label noise learning baselines adapted to the 3D occupancy prediction task. By bridging label noise learning and 3D perception, OccNL and DPR-Occ provide a reliable foundation for safety-critical robotic perception in dynamic environments. The benchmark and source code will be made publicly available at https://github.com/mylwx/OccNL.
format Preprint
id arxiv_https___arxiv_org_abs_2603_06279
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Can we Trust Unreliable Voxels? Exploring 3D Semantic Occupancy Prediction under Label Noise
Li, Wenxin
Peng, Kunyu
Wen, Di
Zheng, Junwei
Wei, Jiale
Duan, Mengfei
Zhang, Yuheng
Fan, Rui
Yang, Kailun
Computer Vision and Pattern Recognition
Robotics
Image and Video Processing
3D semantic occupancy prediction is a cornerstone of robotic perception, yet real-world voxel annotations are inherently corrupted by structural artifacts and dynamic trailing effects. This raises a critical but underexplored question: can autonomous systems safely rely on such unreliable occupancy supervision? To systematically investigate this issue, we establish OccNL, the first benchmark dedicated to 3D occupancy under occupancy-asymmetric and dynamic trailing noise. Our analysis reveals a fundamental domain gap: state-of-the-art 2D label noise learning strategies collapse catastrophically in sparse 3D voxel spaces, exposing a critical vulnerability in existing paradigms. To address this challenge, we propose DPR-Occ, a principled label noise-robust framework that constructs reliable supervision through dual-source partial label reasoning. By synergizing temporal model memory with representation-level structural affinity, DPR-Occ dynamically expands and prunes candidate label sets to preserve true semantics while suppressing noise propagation. Extensive experiments on SemanticKITTI demonstrate that DPR-Occ prevents geometric and semantic collapse under extreme corruption. Notably, even at 90% label noise, our method achieves significant performance gains (up to 2.57% mIoU and 13.91% IoU) over existing label noise learning baselines adapted to the 3D occupancy prediction task. By bridging label noise learning and 3D perception, OccNL and DPR-Occ provide a reliable foundation for safety-critical robotic perception in dynamic environments. The benchmark and source code will be made publicly available at https://github.com/mylwx/OccNL.
title Can we Trust Unreliable Voxels? Exploring 3D Semantic Occupancy Prediction under Label Noise
topic Computer Vision and Pattern Recognition
Robotics
Image and Video Processing
url https://arxiv.org/abs/2603.06279