ProOOD: Prototype-Guided Out-of-Distribution 3D Occupancy Prediction
Yuheng Zhang, Mengfei Duan, Kunyu Peng, Yuhang Wang, Di Wen, Danda Paudel, Luc Van Gool, Kailun Yang
摘要
3D semantic occupancy prediction is central to autonomous driving, yet current methods are vulnerable to long-tailed class bias and out-of-distribution (OOD) inputs, often overconfidently assigning anomalies to rare classes. We present ProOOD, a lightweight, plug-and-play method that couples prototype-guided refinement with training-free OOD scoring. ProOOD comprises (i) prototype-guided semantic imputation that fills occluded regions with class-consistent features, (ii) prototype-guided tail mining that strengthens rare-class representations to curb OOD absorption, and (iii) EchoOOD, which fuses local logit coherence with local and global prototype matching to produce reliable voxel-level OOD scores. Extensive experiments on five datasets demonstrate that ProOOD achieves state-of-the-art performance on both in-distribution 3D occupancy prediction and OOD detection. On SemanticKITTI, it surpasses baselines by +3.57% mIoU overall and +24.80% tail-class mIoU; on VAA-KITTI, it improves AuPRC by +19.34 points, with consistent gains across benchmarks. These improvements yield more calibrated occupancy estimates and more reliable OOD detection in safety-critical urban driving. The source code will be made publicly available.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
它引用的顶会 Paper44
- SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR SequencesJens Behley, Martin Garbade, Andres Milioto, Jan Quenzel 等ICCV 2019 · 被引用 2,345 次
- Scaling Out-of-Distribution Detection for Real-World SettingsDan Hendrycks, Steven Basart, Mantas Mazeika, Andy Zou 等ICML 2022 · 被引用 653 次
- SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous DrivingYi Wei, Linqing Zhao, Wenzhao Zheng, Zheng Zhu 等ICCV 2023 · 被引用 380 次
- OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy PredictionYunpeng Zhang, Zheng Zhu, Dalong DuICCV 2023 · 被引用 354 次
- MonoScene: Monocular 3D Semantic Scene CompletionAnh-Quan Cao, Raoul de CharetteCVPR 2022 · 被引用 251 次
相关 Paper
- SemLT3D: Semantic-Guided Expert Distillation for Camera-only Long-Tailed 3D Object DetectionHao Vo, Khoa Vo, Thinh Phan, Ngo Xuan Cuong 等CVPR 2026 · 被引用 1 次
- OWL: Unsupervised 3D Object Detection by Occupancy Guided Warm-up and Large Model Priors ReasoningXusheng Guo, Wanfa Zhang, Shijia Zhao, Qiming Xia 等AAAI 2026
- ProtoOcc: Accurate, Efficient 3D Occupancy Prediction Using Dual Branch Encoder-Prototype Query DecoderJungho Kim, Changwon Kang, Dongyoung Lee, Sehwan Choi 等AAAI 2025 · 被引用 16 次
- Learning Class Prototypes for Unified Sparse-Supervised 3D Object DetectionYun Zhu, Le Hui, Hang Yang, Jianjun Qian 等CVPR 2025
- ALOcc: Adaptive Lifting-Based 3D Semantic Occupancy and Cost Volume-Based Flow PredictionsDubing Chen, Jin Fang, Wencheng Han, Xinjing Cheng 等ICCV 2025 · 被引用 2 次
