Img2CAD: Conditioned 3D CAD Model Generation from Single Image with Structured Visual Geometry
College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；KOKONI3D, Moxin (Huzhou) Technology Co., LTD（墨芯（湖州）科技有限公司）；School of Software Technology, Zhejiang University（浙江大学软件学院）；School of Information Engineering, Huzhou University（湖州师范学院信息工程学院）
In this paper, we propose Img2CAD, the first approach to our knowledge that uses 2D image inputs to generate CAD models with editable parameters. Unlike existing AI methods for 3D model generation using text or image inputs often rely on mesh-based representations, which are incompatible with CAD tools and lack editability and fine control, Img2CAD enables seamless integration between AI-based 3D reconstruction and CAD software. We have identified an innovative intermediate representation called Structured Visual Geometry (SVG), characterized by vectorized wireframes extracted from objects. This representation significantly enhances the performance of generating conditioned CAD models. Additionally, we introduce two new datasets to further support research in this area: ABC-mono, the largest known dataset comprising over 200,000 3D CAD models with rendered images, and KOCAD, the first dataset featuring real-world captured objects alongside their ground truth CAD models, supporting further research in conditioned CAD model generation.
CMT: A Cascade MAR with Topology Predictor for Multimodal Conditional CAD Generation
Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Shanghai Jiao Tong University（上海交通大学）；The Chinese University of Hong Kong（香港中文大学）；Beihang University（北京航空航天大学）
Autoregressive B-Rep Shape Generation with Parametric Surfaces
The University of Hong Kong（香港大学）；Deemos Technology Co., Ltd.（迪莫斯科技有限公司）；Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）；ShanghaiTech University（上海科技大学）；Texas A&M University（德克萨斯A&M大学）
Hierarchical Error Assessment of CAD Models for Aircraft Manufacturing-and-Measurement
School of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics（南京航空航天大学计算机科学与技术学院）；School of Artificial Intelligence, Taiyuan University of Technology（太原科技大学人工智能学院）；College of Computing and Data Science, Nanyang Technological University (NTU)（南洋理工大学计算机科学与数据科学学院）
Université Paris Est, École des Ponts ParisTech（巴黎东大学，巴黎高科路桥学院）
A number of problems can be formulated as prediction on graph-structured data. In this work, we generalize the convolution operator from regular grids to arbitrary graphs while avoiding the spectral domain, which allows us to handle graphs of varying size and connectivity. To move beyond a simple diffusion, filter weights are conditioned on the specific edge labels in the neighborhood of a vertex. Together with the proper choice of graph coarsening, we explore constructing deep neural networks for graph classification. In particular, we demonstrate the generality of our formulation in point cl…
OpenECAD: An Efficient Visual Language Model for Editable 3D-CAD Design
Software Engineering Institute, East China Normal University（华东师范大学软件工程研究所）；National Trusted Embedded Software Engineering Technology Research Center, Shanghai, China（国家可信嵌入式软件工程技术研究中心）
CADDreamer: CAD Object Generation from Single-view Images
University of Texas at Dallas（德克萨斯大学达拉斯分校）；The University of Hong Kong（香港大学）；Hong Kong University of Science and Technology（香港科技大学）；Nanjing University（南京大学）；ByteDance（字节跳动）；Texas A&M University（德克萨斯农工大学）
GraphBrep: Learning B-Rep in Graph Structure for Efficient CAD Generation
Hunan University（湖南大学）；Beijing Institute of Technology Shenzhen Automotive Research Institute（北京理工大学深圳汽车研究院）；SAIC GM Wuling Automobile Co., Ltd.（上汽通用五菱汽车股份有限公司）
Pointer-CAD v2: Plan-Then-Construct CAD Generation with Dimension-Aware Parametric Precision
The University of Hong Kong（香港大学）；Shenzhen Loop Area Institute（深圳河套学院）；TranscEngram；Monash University（墨尔本大学）；University of California, Berkeley（加州大学伯克利分校）
AULLM++: Structured-Token-Conditioned Large Language Models for Micro-Expression Action Unit Detection
Great Bay University（广东东莞大学）；Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
CADmium: Fine-Tuning Code Language Models for Text-Driven Sequential CAD Design
Chandar Research Lab（昌德拉研究实验室）；Mila – Quebec AI Institute（魁北克人工智能研究所）；Polytechnique Montréal（蒙特利尔理工学院）；Ansys（安世仿真）；Canada CIFAR AI Chair（加拿大CIFAR人工智能主席）
Seek-CAD: A Self-refined Generative Modeling for 3D Parametric CAD Using Local Inference via DeepSeek
College of Computer Science and Artificial Intelligence, Fudan University（计算机科学与人工智能学院，复旦大学）；School of Information and Intelligent Science, Donghua University（信息与智能科学学院，东华大学）
Autodesk Research（欧特克研究院）；University of Toronto（多伦多大学）；Vector Institute（向量研究所）
The Boundary representation (B-rep) format is the de-facto shape representation in computer-aided design (CAD) to model solid and sheet objects. Recent approaches to generating CAD models have focused on learning sketch-and-extrude modeling sequences that are executed by a solid modeling kernel in postprocess to recover a B-rep. In this paper we present a new approach that enables learning from and synthesizing B-reps without the need for supervision through CAD modeling sequence data. Our method SolidGen, is an autoregressive neural network that models the B-rep directly by predicting the ver…
MultiDiffSense: Diffusion-Based Multi-Modal Visuo-Tactile Image Generation Conditioned on Object Shape and Contact Pose
Department of Bioengineering, Imperial-X Initiative, Imperial College London（生物工程系、Imperial-X计划、帝国理工学院伦敦分校）；CAMS-Oxford Institute, University of Oxford（CAMS-牛津研究所、牛津大学）
Microsoft Research（微软研究院）；University of Florida（佛罗里达大学）；JD AI Research（京东人工智能研究院）
We propose a hierarchically structured reinforcement learning approach to address the challenges of planning for generating coherent multi-sentence stories for the visual storytelling task. Within our framework, the task of generating a story given a sequence of images is divided across a two-level hierarchical decoder. The high-level decoder constructs a plan by generating a semantic concept (i.e., topic) for each image in sequence. The low-level decoder generates a sentence for each image using a semantic compositional network, which effectively grounds the sentence generation conditioned on…
