Single-image 3D shape reconstruction is an important and long-standing problem in computer vision. A plethora of existing works is constantly pushing the state-of-the-art performance in the deep learning era. However, there remains a much more difficult and under-explored issue on how to generalize the learned skills over unseen object categories that have very different shape geometry distributions. In this paper, we bring in the concept of compositional generalizability and propose a novel framework that could better generalize to these unseen categories. We factorize the 3D shape reconstruction problem into proper sub-problems, each of which is tackled by a carefully designed neural sub-module with generalizability concerns. The intuition behind our formulation is that object parts (slates and cylindrical parts), their relationships (adjacency and translation symmetry), and shape substructures (T-junctions and a symmetric group of parts) are mostly shared across object categories, even though object geometries may look very different (e.g. chairs and cabinets). Experiments on PartNet show that we achieve superior performance than state-of-the-art. This validates our problem factorization and network designs.
nnMIL: A generalizable multiple instance learning framework for computational pathology
Department of Radiation Oncology, Stanford University School of Medicine, Stanford, CA, USA（放射肿瘤科，斯坦福大学医学院，斯坦福，CA，USA）；Stanford Institute for Human-Centered Artificial Intelligence, Stanford, CA, USA（斯坦福大学人本人工智能研究所，斯坦福，CA，USA）
Stereo-GS: Multi-View Stereo Vision Model for Generalizable 3D Gaussian Splatting Reconstruction
Department of Computer Science, Hong Kong Baptist University（香港 Baptist 大学计算机科学系）；NVIDIA AI Technology Center, NVIDIA（NVIDIA 人工智能技术中心）；School of Control Science and Engineering, Shandong University（控制科学与工程学院，山东大学）
The University of Hong Kong（香港大学）；Tencent Games（腾讯游戏）；Texas A&M University（得克萨斯农工大学）
We introduce SparseNeuS, a novel neural rendering based method for the task of surface reconstruction from multi-view images. This task becomes more difficult when only sparse images are provided as input, a scenario where existing neural reconstruction approaches usually produce incomplete or distorted results. Moreover, their inability of generalizing to unseen new scenes impedes their application in practice. Contrarily, SparseNeuS can generalize to new scenes and work well with sparse images (as few as 2 or 3). SparseNeuS adopts signed distance function (SDF) as the surface representation,…
Deep learning models exhibit limited generalizability across different domains. Specifically, transferring knowledge from available entangled domain features(source/target domain) and categorical features to new unseen categorical features in a target domain is an interesting and difficult problem that is rarely discussed in the current literature. This problem is essential for many real-world applications such as improving diagnostic classification or prediction in medical imaging. To address this problem, we propose Mutual-Information-based Disentangled Neural Networks (MIDNet) to extract ge…
Metis: A Generalizable and Efficient World-Action Model for Autonomous Driving and Urban Navigation
Fudan University（复旦大学）；Shanghai Innovation Institute（上海创新研究院）；The University of Hong Kong（香港大学）；Tongji University（同济大学）；Li Auto Inc.（理想汽车）；Huazhong University of Science and Technology（华中科技大学）；Imperial College London（伦敦帝国理工学院）；University of Surrey（萨里大学）
Southern University of Science and Technology（南方科技大学）；Pengcheng Laboratory（鹏城实验室）
A central challenge in human pose estimation, as well as in many other machine learning and prediction tasks, is the generalization problem. The learned network does not have the capability to characterize the prediction error, generate feedback information from the test sample, and correct the prediction error on the fly for each individual test sample, which results in degraded performance in generalization. In this work, we introduce a self-correctable and adaptable inference (SCAI) method to address the generalization challenge of network prediction and use human pose estimation as an exam…
GLOMIA-Pro: A Generalizable Longitudinal Medical Image Analysis Framework for Disease Progression Prediction
School of Medical Technology, Beijing Institute of Technology（北京理工大学医学技术学院）；Department of Thoracic Surgery, Sun Yat-sen University Cancer Center（中山大学肿瘤医院胸外科部门）；Department of Radiology, The Fifth Affiliated Hospital of Sun Yat-sen University（中山大学第五附属医院放射科部门）；Beijing Duanliu Medical Technology Co., Ltd.（北京杜流医疗科技有限公司）
PostCast: Generalizable Postprocessing for Precipitation Nowcasting via Unsupervised Blurriness Modeling
Shanghai Jiao Tong University（上海交通大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Fudan University（复旦大学）；The Chinese University of Hong Kong（香港中文大学）
Towards a Generalizable Bimanual Foundation Policy via Flow-based Video Prediction
Institute of Artificial intelligence (TeleAI), China Telecom（人工智能研究院（TeleAI），中国电信）；Northwestern Polytechnical University（西北工业大学）；Hong Kong University of Science and Technology（香港科技大学）
Statistics Department, UC Berkeley（加州大学伯克利分校统计系）；Electrical Engineering & Computer Science Department, UC Berkeley（加州大学伯克利分校电气工程与计算机科学系）；Global Policy Laboratory, Goldman School of Public Policy, UC Berkeley（加州大学伯克利分校高盛公共政策学院全球政策实验室）；Center for the Environment and Data Science Initiative, Harvard University（哈佛大学环境中心与数据科学计划）；Bren School of Environmental Science & Management, UC Santa Barbara（加州大学圣塔芭芭拉分校布伦环境科学与管理学院）；Rhodium Group（荣鼎集团）
Combining satellite imagery with machine learning (SIML) has the potential to address global challenges by remotely estimating socioeconomic and environmental conditions in data-poor regions, yet the resource requirements of SIML limit its accessibility and use. We show that a single encoding of satellite imagery can generalize across diverse prediction tasks (e.g. forest cover, house price, road length). Our method achieves accuracy competitive with deep neural networks at orders of magnitude lower computational cost, scales globally, delivers label super-resolution predictions, and facilitat…
TriRelVLA: Triadic Relational Structure for Generalizable Embodied Manipulation
School of Computing, National University of Singapore（新加坡国立大学计算机学院）；School of Artificial Intelligence and Automation, Huazhong University of Science and Technology（华中科技大学人工智能与自动化学院）
Segment-and-Classify: ROI-Guided Generalizable Contrast Phase Classification in CT Using XGBoost
Division of Intramural Research, National Library of Medicine - National Center for Biotechnology Information, National Library of Medicine - Imaging Biomarkers and Computer Aided Diagnosis Lab, Clinical Center - - National Institutes of Health, Bethesda, MD, USA（国家生物技术中心、国家医学图书馆——影像生物标记与计算机辅助诊断实验室、临床中心——美国国家卫生研究院，贝塞斯达，马里兰州，美国）
EvGGS: A Collaborative Learning Framework for Event-based Generalizable Gaussian Splatting
Function Hub, Hong Kong University of Science and Technology（香港科技大学（广州）功能中心）；Faculty of Robot Science and Engineering, Northeastern University（东北大学机器人科学与工程学院）
