arXiv:2511.20636v1 Announce Type: new 
Abstract: Mechanical design and manufacturing workflows conventionally begin with conceptual design, followed by the creation of a computer-aided design (CAD) model and fabrication through material-extrusion (MEX) printing. This process requires converting CAD geometry into machine-readable G-code through slicing and path planning. While each step is well established, dependence on CAD modeling remains a major bottleneck: constructing object-specific 3D geometry is slow and poorly suited to rapid prototyping. Even minor design variations typically necessitate manual updates in CAD software, making iteration time-consuming and difficult to scale. To address this limitation, we introduce Image2Gcode, an end-to-end data-driven framework that bypasses the CAD stage and generates printer-ready G-code directly from images and part drawings. Instead of relying on an explicit 3D model, a hand-drawn or captured 2D image serves as the sole input. The framework first extracts slice-wise structural cues from the image and then employs a denoising diffusion probabilistic model (DDPM) over G-code sequences. Through iterative denoising, the model transforms Gaussian noise into executable print-move trajectories with corresponding extrusion parameters, establishing a direct mapping from visual input to native toolpaths. By producing structured G-code directly from 2D imagery, Image2Gcode eliminates the need for CAD or STL intermediates, lowering the entry barrier for additive manufacturing and accelerating the design-to-fabrication cycle. This approach supports on-demand prototyping from simple sketches or visual references and integrates with upstream 2D-to-3D reconstruction modules to enable an automated pipeline from concept to physical artifact. The result is a flexible, computationally efficient framework that advances accessibility in design iteration, repair workflows, and distributed manufacturing.

تم تقديم Image2Gcode كإطار مبتكر يقوم بتوليد G-code مباشرة من الصور ورسومات الأجزاء، مما يلغي الحاجة إلى نمذجة CAD التقليدية في التصنيع الإضافي. تهدف هذه الطريقة إلى تبسيط عملية التصميم من خلال السماح بالنمذجة السريعة دون الاختناقات المرتبطة ببرامج CAD.

Image2Gcode se ha presentado como un marco innovador que genera G-code directamente a partir de imágenes y dibujos de piezas, eliminando la necesidad de modelado CAD tradicional en la fabricación aditiva. Este enfoque busca agilizar el proceso de diseño al permitir la creación rápida de prototipos sin los cuellos de botella asociados con el software CAD.

Image2Gcode a été introduit comme un cadre innovant qui génère du G-code directement à partir d'images et de dessins de pièces, éliminant ainsi le besoin de modélisation CAD traditionnelle dans la fabrication additive. Cette approche vise à rationaliser le processus de conception en permettant un prototypage rapide sans les goulets d'étranglement associés aux logiciels CAD.

Image2Gcode has been introduced as an innovative framework that generates G-code directly from images and part drawings, eliminating the need for traditional CAD modeling in additive manufacturing. This approach aims to streamline the design process by allowing for rapid prototyping without the bottlenecks associated with CAD software.

Image2Gcode: Image-to-G-code Generation for Additive Manufacturing Using Diffusion-Transformer Model

arXiv:2512.03018v1 Announce Type: new 
Abstract: The boundary representation (B-Rep) is the standard data structure used in Computer-Aided Design (CAD) for defining solid models. Despite recent progress, directly generating B-Reps end-to-end with precise geometry and watertight topology remains a challenge. This paper presents AutoBrep, a novel Transformer model that autoregressively generates B-Reps with high quality and validity. AutoBrep employs a unified tokenization scheme that encodes both geometric and topological characteristics of a B-Rep model as a sequence of discrete tokens. Geometric primitives (i.e., surfaces and curves) are encoded as latent geometry tokens, and their structural relationships are defined as special topological reference tokens. Sequence order in AutoBrep naturally follows a breadth first traversal of the B-Rep face adjacency graph. At inference time, neighboring faces and edges along with their topological structure are progressively generated. Extensive experiments demonstrate the advantages of our unified representation when coupled with next-token prediction for B-Rep generation. AutoBrep outperforms baselines with better quality and watertightness. It is also highly scalable to complex solids with good fidelity and inference speed. We further show that autocompleting B-Reps is natively supported through our unified tokenization, enabling user-controllable CAD generation with minimal changes. Code is available at https://github.com/AutodeskAILab/AutoBrep.

تم تقديم نموذج جديد يسمى AutoBrep، وهو نموذج Transformer يقوم بتوليد تمثيلات الحدود (B-Reps) في التصميم المدعوم بالحاسوب (CAD) بجودة عالية وتوبولوجيا صالحة. يتناول هذا النموذج التحدي المتمثل في توليد B-Reps من البداية إلى النهاية من خلال استخدام مخطط توكين موحد يقوم بتشفير الخصائص الهندسية والتوبولوجية كرموز منفصلة، مما يسهل عملية الاستدلال عبر رسم بياني لجوار الوجوه في B-Rep.

Se ha presentado un nuevo modelo Transformer llamado AutoBrep, que genera representaciones de frontera (B-Reps) en el diseño asistido por computadora (CAD) con alta calidad y topología válida. Este modelo aborda el desafío de la generación de B-Reps de extremo a extremo mediante un esquema de tokenización unificado que codifica características geométricas y topológicas como tokens discretos, facilitando un recorrido en amplitud del grafo de adyacencia de caras de B-Rep durante la inferencia.

Un nouveau modèle Transformer nommé AutoBrep a été introduit pour générer des représentations de frontière (B-Reps) dans la conception assistée par ordinateur (CAO) avec une qualité élevée et une topologie valide. Ce modèle répond au défi de la génération de B-Reps de bout en bout en utilisant un schéma de tokenisation unifié qui encode les caractéristiques géométriques et topologiques en tant que tokens discrets, facilitant un parcours en largeur du graphe d'adjacence des faces de B-Rep lors de l'inférence.

A novel Transformer model named AutoBrep has been introduced to generate boundary representations (B-Reps) in Computer-Aided Design (CAD) with high quality and valid topology. This model addresses the challenge of end-to-end generation of B-Reps by employing a unified tokenization scheme that encodes geometric and topological characteristics as discrete tokens, facilitating a breadth-first traversal of the B-Rep face adjacency graph during inference.

Image2Gcode: Image-to-G-code Generation for Additive Manufacturing Using Diffusion-Transformer Model

Was this article worth reading? Share it

Artefacts.ai

Blunge

CreativeFabrica