Point Cloud Classification

Follow this topic Ask about this topic

Point cloud classification studies how to recognize objects or scenes from unordered, irregular 3D samples, which may come from CAD models, depth cameras, or LiDAR. Methods range from permutation-invariant networks such as PointNet to local graph and convolutional models, hierarchical sampling, and transformers that capture geometry at multiple scales. Researchers evaluate these approaches on benchmarks such as ModelNet40 and ScanObjectNN, and increasingly study corruption robustness, few-shot adaptation, and applications in settings like forestry and medical imaging. A central challenge is balancing accuracy and efficiency with reliable performance on noisy sensor data and across domains, since strong results on clean synthetic shapes do not always transfer to real-world scans.

Latest papers

40 papers0 papers in the last four weeks, down 100% on the four weeks before. 0.0% of all new papers.

Topo-ADV: Generating Topology-Driven Imperceptible Adversarial Point Clouds
Apr 10, 2026Gayathry Chandramana Krishnan Nampoothiry, Raghuram Venkatapuram, Anirban Ghosh +1Adversarial Attacks Adversarial Examples
University of North Florida, Jacksonville, USA
A Persistent Homology Design Space for 3D Point Cloud Deep Learning
Apr 5, 2026Prachi Kudeshia, Jiju Poovvancheri, Amr Ghoneim +1Persistent Homology Topological Representation Learning
Saint Mary’s University, Halifax, Canada · Nanjing Forestry University, China
PointRFT: Explicit Reinforcement Fine-tuning for Point Cloud Few-shot Learning
Mar 25, 2026Yankai Wang, Yiding Sun, Qirui Wang +3Point Cloud Learning RL Fine-Tuning
School of Software Engineering, Xi’an Jiaotong University, Xi’an 710048, China · International School, Beijing University of Posts and Telecommunications, Beijing 100876, China
Layered Quantum Architecture Search for 3D Point Cloud Classification
Mar 20, 2026Natacha Kuete Meli, Jovita Lukasik, Vladislav Golyanik +1Quantum Architecture Search Quantum Neural Networks
University of Siegen · MPI for Informatics, SIC
Learning Geometric and Photometric Features from Panoramic LiDAR Scans for Outdoor Place Categorization
Mar 13, 2026Kazuto Nakashima, Hojung Jung, Yuki Oto +3Visual Place Recognition 3D Scene Understanding
Graduate School of Information Science and Electrical Engineering, Kyushu University, Fukuoka, Japan · Jet Propulsion Laboratory, California Institute of Technology, Pasadena, CA, USA · Faculty of Information Science and Electrical Engineering, Kyushu University, Fukuoka, Japan +1
Fast Attention-Based Simplification of LiDAR Point Clouds for Object Detection and Classification
Mar 8, 2026Z. Rozsa, Á. Madaras, Q. Wei +5Lidar-Based 3D Object Detection Point Cloud Classification
Institute for Computer Science and Control (SZTAKI), Budapest, Hungary · School of Information Engineering, Nanchang University, Nanchang, China · Faculty of Technology, Arts, and Culture, De Montfort University, Leicester, U.K. +1
SLNet: A Super-Lightweight Geometry-Adaptive Network for 3D Point Cloud Recognition
Mar 8, 2026Mohammad Saeid, Amir Salarpour, Pedram MohajerAnsari +1Point Cloud Learning Point Cloud Classification
Sirjan University of Technology, Sirjan, Iran · Clemson University, Clemson, SC, USA
Efficient Point Cloud Processing with High-Dimensional Positional Encoding and Non-Local MLPs
Mar 4, 2026Yanmei Zou, Hongshan Yu, Yaonan Wang +4Point Cloud Learning Point Cloud Classification
the School of Artificial Intelligence and Robotics, Quanzhou Institute of Industrial Design and Machine Intelligence Innovation, Hunan University, Changsha 410082, China. · the College of Engineering and Design, Hunan Normal University, Changsha 410081, China. · the College of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, China. +1
A novel network for classification of cuneiform tablet metadata
Mar 4, 2026Frederik HagelskjærPoint Cloud Classification Point Cloud Learning
SDU Robotics · The Mærsk Mc-Kinney Møller Institute · University of Southern Denmark +1
Structure-First Point Cloud Learning with Mapper Region Graphs
Feb 5, 2026Jeongbin You, Donggun Kim, Sejun Park +1Point Cloud Classification
Department of Mathematics Korea University

Apr 10, 2026J/K move · Enter open · S save

Topo-ADV: Generating Topology-Driven Imperceptible Adversarial Point Clouds

Gayathry Chandramana Krishnan Nampoothiry, Raghuram Venkatapuram, Anirban Ghosh, Ayan Dutta

University of North Florida, Jacksonville, USA

Adversarial Attacks Adversarial Examples Adversarial Perturbations Point Cloud Classification

Open paper AskPDF arXiv

Deep neural networks for 3D point cloud understanding have achieved remarkable success in object classification and recognition, yet recent work shows that these models remain highly vulnerable to adversarial perturbations. Existing 3D attacks predominantly manipulate geometric properties such as point locations, curvature, or surface structure, implicitly assuming that preserving global shape fidelity preserves semantic content. In this work, we challenge this assumption and introduce the first topology-driven adversarial attack for point cloud deep learning. Our key insight is that the homological structure of a 3D object constitutes a previously unexplored vulnerability surface. We propose Topo-ADV, an end-to-end differentiable framework that incorporates persistent homology as an explicit optimization objective, enabling gradient-based manipulation of topological features during adversarial example generation. By embedding persistence diagrams through differentiable topological representations, our method jointly optimizes (i) a topology divergence loss that alters persistence, (ii) a misclassification objective, and (iii) geometric imperceptibility constraints that preserve visual plausibility. Experiments demonstrate that subtle topology-driven perturbations consistently achieve up to 100% attack success rates on benchmark datasets such as ModelNet40, ShapeNet Part, and ScanObjectNN using PointNet and DGCNN classifiers, while remaining geometrically indistinguishable from the original point clouds, beating state-of-the-art methods on various perceptibility metrics.