cs.CVNov 6, 2026

FIND: Frequency Invariance Disentanglement for Test-Time Adaptation in LiDAR 3D Detection

Authors: Dongxiao Li, Zixuan Hu, Ling-Yu Duan

Organizations: School of Computer Science, Peking University, Beijing 100871, China

Abstract

LiDAR-based 3D Object Detection (L3OD) is a fundamental 3D perception task, yet its performance is often compromised by domain shifts arising from diverse sensor configurations and environmental conditions. Existing Test-Time Adaptation (TTA) methods primarily leverage self-supervision in the spatial domain, yet they frequently confound semantic content with domain style due to the sparse, non-Euclidean nature of point clouds. To overcome this limitation, we propose FIND (Frequency INvariance Disentanglement), a novel TTA framework that precisely disentangles domain-invariant content from domain-specific interference within the frequency domain. Our methodology utilizes B-Spline fitting to construct locally adaptive filters integrated into a dual-stream architecture: an Invariant Stream extracts robust features to guide pseudo-labeling, while a Specific Stream enforces consistency against domain perturbations. By combining invariance-driven alignment with stability-guided regularization, our approach dynamically extracts robust domain-invariant features while suppressing domain-specific interference. Extensive experiments on cross-dataset adaptation and robust corruption benchmarks demonstrate that FIND significantly outperforms state-of-the-art methods. The source code is publicly available at https://github.com/llldx03/FIND.

Figures & tables

Appendix figures & tables14 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Leveraging 2D Foundation Priors for Generalized Category Discovery under Test-Time Adaptation in 3D LiDAR Segmentation

    Nov 1, 2026Hanqi Chen, Chaoqi Chen, Tian Ji +1Generalized Category Discovery3D Semantic Segmentation

  2. No Adaptation Without Observation: Observability-Constrained Test-Time Prompt Tuning for LiDAR Semantic Segmentation

    Jun 29, 2026Linlian Jiang, Wentao Ju, Sadman Rakib Pinon +4Test-Time Adaptation3D Semantic Segmentation

  3. SimFuse3D: Source-Guided Target Simulation and Confidence-Guided Multi-Stage Localization Reweighting for Cross-Platform 3D Object Detection

    Sep 4, 2026Yongchun Lin, Xinliang Zhang, Yun Zou +7Unsupervised Domain AdaptationLidar-Based 3D Object Detection