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

TL;DR

This paper introduces a new benchmark and a robust framework for 3D semantic occupancy prediction under label noise, demonstrating improved reliability in noisy real-world scenarios for robotic perception.

Contribution

It establishes the first benchmark for 3D occupancy with label noise and proposes DPR-Occ, a novel noise-robust method combining temporal memory and structural affinity.

Findings

DPR-Occ prevents geometric and semantic collapse under extreme noise.

Even at 90% label noise, DPR-Occ significantly outperforms existing methods.

State-of-the-art noise learning strategies fail in sparse 3D voxel spaces.

Abstract

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.