Point Cloud Learning

Follow this topic Ask about this topic

Point cloud learning studies how to extract shape, spatial relationships, and motion from unordered, irregular 3D samples that may be sparse, noisy, or incomplete. Methods range from point and graph networks to sparse convolutions, transformers, state-space models, and geometrically equivariant architectures; self-supervised and multimodal pretraining aim to make their representations useful across tasks and sensors. Applications include classification, segmentation, reconstruction, registration, tracking, robotics, and 4D motion understanding, with benchmarks spanning objects, indoor scenes, and large-scale LiDAR. A central challenge is balancing accuracy and transfer across changes in density, viewpoint, and sensor with the memory, computation, and data needed for practical deployment.

Latest papers

159 papers14 papers in the last four weeks, down 12% on the four weeks before. 0.1% of all new papers.

Efficient Encoder-Free Fourier-based 3D Large Multimodal Model
Feb 26, 2026Guofeng Mei, Wei Lin, Luigi Riz +33D VLMs Efficient Multimodal Inference
Fondazione Bruno Kessler, Italy · JKU Linz, Austria · CSIRO, Australia
Align then Adapt: Rethinking Parameter-Efficient Transfer Learning in 4D Perception
Feb 26, 2026Yiding Sun, Jihua Zhu, Haozhe Cheng +4Transfer Learning Point Cloud Learning
the School of Software Engineering, Xi’an Jiaotong University, Xi’an 710048, China · the State Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi’an Jiaotong University, Xi’an 710048, China · the School of Electrical and Information Engineering, Hunan University, Changsha, 410082, China +1
SoPE: Spherical Coordinate-Based Positional Embedding for Enhancing Spatial Perception of 3D LVLMs
Feb 26, 2026Guanting Ye, Qiyan Zhao, Wenhao Yu +7Positional Encoding 3D VLMs
University of Macau · Shanghai Jiaotong University · University of Science and Technology of China +2
SD4R: Sparse-to-Dense Learning for 3D Object Detection with 4D Radar
Feb 24, 2026Xiaokai Bai, Jiahao Cheng, Songkai Wang +53D Object Detection Point Cloud Learning
College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou 310027, China · School of Automotive Studies, Tongji University, Shanghai 201804, China · Ningbo Global Innovation Center, Zhejiang University, Ningbo 315100, China
4D-RaDiff: Latent Point Diffusion for 4D Radar Point Cloud Generation
Dec 16, 2025Jimmie Kwok, Holger Caesar, Andras PalffySynthetic Data Augmentation Point Cloud Learning
Delft University of Technology, Netherlands · Perciv AI, Netherlands
LitePT: Lighter Yet Stronger Point Transformer
Dec 15, 2025Yuanwen Yue, Damien Robert, Jianyuan Wang +4Point Cloud Learning Point Transformer
ETH Zurich · University of Oxford · University of Zurich
UniFlow: Zero-Shot LiDAR Scene Flow for Autonomous Vehicles
Nov 23, 2025Siyi Li, Qingwen Zhang, Ishan Khatri +4Point Cloud Learning Autonomous Driving Perception
University of Pennsylvania · KTH Royal Institute of Technology · StackAV +1
NumGrad-Pull: Numerical Gradient Guided Tri-plane Representation for Surface Reconstruction from Point Clouds
Nov 26, 2024Ruikai Cui, Binzhu Xie, Shi Qiu +3Implicit Neural Representations 3D Reconstruction
School of Computing, The Australian National University, Australia · Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong SAR, China · Department of Computer Science & Software Engineering, the University of Western Australia, Australia
Partial Symmetry Detection for 3D Geometry using Contrastive Learning with Geodesic Point Cloud Patches
Dec 13, 2023Gregor Kobsik, Isaak Lim, Leif KobbeltPoint Cloud Learning Geometric Representation Learning
Visual Computing Institute, RWTH Aachen University, Germany

Feb 26, 2026J/K move · Enter open · S save

Efficient Encoder-Free Fourier-based 3D Large Multimodal Model

Guofeng Mei, Wei Lin, Luigi Riz, Yujiao Wu+2

Fondazione Bruno Kessler, Italy · JKU Linz, Austria · CSIRO, Australia

3D VLMs Efficient Multimodal Inference Point Cloud Learning 3D Scene Representation

Open paper AskPDF arXiv

Large Multimodal Models (LMMs) that process 3D data typically rely on heavy, pre-trained visual encoders to extract geometric features. While recent 2D LMMs have begun to eliminate such encoders for efficiency and scalability, extending this paradigm to 3D remains challenging due to the unordered and large-scale nature of point clouds. This leaves a critical unanswered question: How can we design an LMM that tokenizes unordered 3D data effectively and efficiently without a cumbersome encoder? We propose Fase3D, the first efficient encoder-free Fourier-based 3D scene LMM. Fase3D tackles the challenges of scalability and permutation invariance with a novel tokenizer that combines point cloud serialization and the Fast Fourier Transform (FFT) to approximate self-attention. This design enables an effective and computationally minimal architecture, built upon three key innovations: First, we represent large scenes compactly via structured superpoints. Second, our space-filling curve serialization followed by an FFT enables efficient global context modeling and graph-based token merging. Lastly, our Fourier-augmented LoRA adapters inject global frequency-aware interactions into the LLMs at a negligible cost. Fase3D achieves performance comparable to encoder-based 3D LMMs while being significantly more efficient in computation and parameters. Project website: https://tev-fbk.github.io/Fase3D.