Frequency-domain learning draws attention due to its superior tradeoff between inference accuracy and input data size. Frequency-domain learning in 2D computer vision tasks has shown that 2D convolutional neural networks (CNN) have a stationary spectral bias towards low-frequency channels so that high-frequency channels can be pruned with no or little accuracy degradation. However, frequency-domain learning has not been studied in the context of 3D CNNs with 3D volumetric data. In this paper, we study frequency-domain learning for volumetric-based 3D data perception to reveal the spectral bias and the accuracy-input-data-size tradeoff of 3D CNNs. Our study finds that 3D CNNs are sensitive to a limited number of critical frequency channels, especially low-frequency channels. Experiment results show that frequency-domain learning can significantly reduce the size of volumetric-based 3D inputs (based on spectral bias) while achieving comparable accuracy with conventional spatial-domain learning approaches. Specifically, frequency-domain learning is able to reduce the input data size by 98% in 3D shape classification while limiting the average accuracy drop within 2%, and by 98% in the 3D point cloud semantic segmentation with a 1.48% mean-class accuracy improvement while limiting the mean-class IoU loss within 1.55%. Moreover, by learning from higher-resolution 3D data (i.e., 2x of the original image in the spatial domain), frequency-domain learning improves the mean-class accuracy and mean-class IoU by 3.04% and 0.63%, respectively, while achieving an 87.5% input data size reduction in 3D point cloud semantic segmentation.
One at a Time: Progressive Multi-step Volumetric Probability Learning for Reliable 3D Scene Perception
Shanghai Jiao Tong University（上海交通大学）；Ningbo Institute of Digital Twin, Eastern Institute of Technology（宁波数字孪生研究院，东方理工）；Tokyo Institute of Technology（东京工业大学）；PhiGent Robotics（PhiGent机器人公司）
GP-NeRF: Generalized Perception NeRF for Context-Aware 3D Scene Understanding
Northwestern Polytechnical University（西北工业大学）；Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（合肥综合性国家科学中心人工智能研究院）；Nanyang Technological University（南洋理工大学）；MBZUAI（穆罕默德·本·扎耶德人工智能大学）；Hefei University of Technology（合肥工业大学）；Baidu, Inc.（百度公司）
Rethinking Local Perception in Lightweight Vision Transformer
Tsinghua University（清华大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
VoxShield: Protecting 3D Medical Datasets from Unauthorized Training via Frequency-Aware Inter-Slice Disruption
Westlake University（西拉雅大学）；Dalian University of Technology（大连理工大学）；Hokkaido University（北海道大学）；The Chinese University of Hong Kong（香港中文大学）；RIKEN（理化学研究所）
Temporal and volumetric denoising via quantile sparse image prior
Friedrich-Alexander-Universität Erlangen-Nürnberg（弗里德里希-亚历山大大学埃尔朗根-纽伦堡分校）；Universitätsklinikum Erlangen（埃尔朗根大学医院）；Massachusetts Institute of Technology（麻省理工学院）；e.solutions GmbH（e.solutions有限公司）
FOAM: A General Frequency-Optimized Anti-Overlapping Framework for Overlapping Object Perception
State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, 110819, Liaoning, China（合成过程工业系统综合自动化重点实验室，东北大学，沈阳，110819，辽宁，中国）；College of Information Science and Engineering, Northeastern University, Shenyang, 110819, Liaoning, China（信息科学与工程学院，东北大学，沈阳，110819，辽宁，中国）；Key Laboratory of Data Analytics and Optimization for Smart Industry, Ministry of Education, Northeastern University, Shenyang, 110819, Liaoning, China（智能产业数据解析与优化重点实验室，教育部，东北大学，沈阳，110819，辽宁，中国）
DifferSeg: Towards Diverse Multimodal Binary Segmentation via Differential Perception and Frequency Guidance
School of Artificial Intelligence, Jiangxi Normal University（江西师范大学人工智能学院）；Institute of AI Education, East China Normal University（华东师范大学人工智能教育研究所）；Yale School of Medicine, Yale University（耶鲁大学医学院）
Rethinking Barely-Supervised Volumetric Medical Image Segmentation from an Unsupervised Domain Adaptation Perspective
School of Computer Science and Engineering, Northeastern University（东北大学计算机科学与工程学院）；Alberta Machine Intelligence Institute, University of Alberta（阿尔伯塔大学阿尔伯塔机器智能研究所）
FaSDiff: Balancing Perception and Semantics in Face Compression via Stable Diffusion Priors
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Research Center of Artificial Intelligence, Pengcheng Laboratory（人工智能研究中心，鹏城实验室）；Harbin Institute of Technology（哈尔滨工业大学）；Huawei Manufacturing（华为制造）
Efficient Dual-domain Image Dehazing with Haze Prior Perception
Institute of Intelligent Information Processing, Guangdong Provincial Key Laboratory of Intelligent Information Processing, Shenzhen Key Laboratory of Modern Communications and Information Processing, Shenzhen University（智能信息处理研究院）；College of Engineering and Computer Science, Australian National University（工程与计算机科学学院）
UAV-CB: A Complex-Background RGB-T Dataset and Local Frequency Bridge Network for UAV Detection
Pengcheng Laboratory（鹏城实验室）；South China University of Technology（南方科技大学）；Peking University（北京大学）；Xinjiang University（新疆大学）；Harbin Institute of Technology（哈尔滨工业大学）
