Deep learning-based 3D object reconstruction has achieved unprecedented results. Among those, the transformer deep neural model showed outstanding performance in many applications of computer vision. We introduce SnakeVoxFormer, a novel, 3D object reconstruction in voxel space from a single image using the transformer. The input to SnakeVoxFormer is a 2D image, and the result is a 3D voxel model. The key novelty of our approach is in using the run-length encoding that traverses (like a snake) the voxel space and encodes wide spatial differences into a 1D structure that is suitable for transformer encoding. We then use dictionary encoding to convert the discovered RLE blocks into tokens that are used for the transformer. The 1D representation is a lossless 3D shape data compression method that converts to 1D data that use only about 1% of the original data size. We show how different voxel traversing strategies affect the effect of encoding and reconstruction. We compare our method with the state-of-the-art for 3D voxel reconstruction from images and our method improves the state-of-the-art methods by at least 2.8% and up to 19.8%.
Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object Detection
The Hong Kong Polytechnic University（香港理工大学）；Center for Artificial Intelligence and Robotics, HKISI, CAS（中国科学院香港智能科学研究所人工智能与机器人中心）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
Fore-Mamba3D: Mamba-based Foreground-Enhanced Encoding for 3D Object Detection
School of Automation and Intelligent Sensing, Shanghai Jiao Tong University（上海交通大学自动化与智能感知学院）；Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University（上海交通大学图像处理与模式识别研究所）；Institute of Medical Robotics, Shanghai Jiao Tong University（上海交通大学医学机器人研究所）；School of Computer Science and Technology, Zhejiang Normal University（浙江师范大学计算机科学与技术学院）；Beijing Geekplus Technology Co., Ltd（北京 Geekplus 技术有限公司）
PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection
Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；The University of Sydney（悉尼大学）；SenseTime Research（商汤科技研究院）；The Chinese University of Hong Kong（香港中文大学）
三维目标检测由于其在各个领域的广泛应用而受到工业界和学术界越来越多的关注。在本文中，我们提出了基于点体素区域卷积神经网络（PV-RCNN）的点云上的三维目标检测。首先，我们提出了一种新的3D检测器PV-RCNN，它通过两个新的步骤，即通过深度集成基于点的集合抽象和基于体素的稀疏卷积的特征学习来提高3D检测性能，体素到关键点场景编码和关键点到网格ROI特征提取。其次，我们提出了一个先进的框架PV-RCNN++，用于更有效和准确的3D目标检测。它包括两个主要的改进：扇区化的以提案为中心的采样，用于有效地产生更具代表性的关键点，以及VectorPool聚合，用于更好地聚合局部点特征，同时减少资源消耗。通过这两种策略，我们的PV-RCNN++比PV-RCNN快约$3\times$，同时也实现了更好的性能。实验表明，我们提出的PV-RCNN++框架在大规模和高度竞争的Waymo开放数据集上实现了最先进的3D检测性能，在150 m * 150 m的检测范围内具有10 FPS的推理速度。
Voxel-wise Cross-Volume Representation Learning for 3D Neuron Reconstruction
Sydney Nano Institute, University of Sydney（悉尼大学悉尼纳米研究所）；School of Computer Science, University of Sydney（悉尼大学计算机科学学院）；School of Computer Science and Engineering, University of New South Wales（新南威尔士大学计算机科学与工程学院）；Paige AI；Sydney Pharmacy School, University of Sydney（悉尼大学药学院）
GrapeSplat: Geometry-Grounded Reconstruction via Amalgamated Pose-Free Encoding for Feed-Forward 3D Gaussian Splatting
National Taiwan University（国立台湾大学）；National Taiwan University of Science and Technology（国立台湾科技大学）；NTU AI Center of Research Excellence (NTU AI-CoRE)（台湾大学人工智能卓越研究中心）；VinUniversity（Vin大学）
Diffusion-Encoding Gaussian Field for Joint k-q dMRI Reconstruction
School of Information Engineering, Nanchang University（南昌大学信息工程学院）；Academy of Medical Engineering and Translational Medicine, Medical School, Faculty of Medicine, Tianjin University（天津大学医学院医学工程与转化医学研究院）；Research Center for Medical AI, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院医学人工智能研究中心）
DeepStationing: Thoracic Lymph Node Station Parsing in CT Scans using Anatomical Context Encoding and Key Organ Auto-Search
PAII Inc.（PAII公司）；The First Affiliated Hospital Zhejiang University（浙江大学附属第一医院）；Johns Hopkins University（约翰斯·霍普金斯大学）；Ping An Insurance Company of China（中国平安保险（集团）股份有限公司）；Zhejiang Provincial People’s Hospital（浙江省人民医院）
Fiber Orientation Estimation Guided by a Deep Network
Johns Hopkins University（约翰霍普金斯大学）；National Laboratory of Pattern Recognition & Brainnetome Center, Institute of Automation, Chinese Academy of Sciences（模式识别国家重点实验室与脑网络组研究中心，中国科学院自动化研究所）
SPOT-Occ: Sparse Prototype-guided Transformer for Camera-based 3D Occupancy Prediction
Artificial Intelligence Thrust, The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学人工智能方向（广州））；Department of Computer Science and Engineering, The Hong Kong University of Science and Technology（香港科学与技术大学计算机科学与工程系）
On the Degrees of Freedom of Gridded Control Points in Learning-Based Medical Image Registration
UCL Hawkes Institute（UCL霍克斯研究所；医学物理与生物医学工程系，伦敦大学学院）；Department of Medical Physics and Biomedical Engineering, University College London（医学成像中心，医学系，伦敦大学学院）；Centre for Medical Imaging, Division of Medicine, University College London（外科与介入科学系，伦敦大学学院）；Division of Surgery and Interventional Science, University College London（癌症研究所，泌尿科，UCL医院，伦敦大学学院）；Cancer Institute, Urology Department, UCL Hospital, University College London（放射科，帝国理工医疗）；Radiology Department, Imperial College Healthcare
