Masked Topology Modeling for Self-Supervised Learning on Parametric CAD

• URL: http://arxiv.org/abs/2607.20642v1
• Date: Wed, 22 Jul 2026 18:13:08 GMT
• Title: Masked Topology Modeling for Self-Supervised Learning on Parametric CAD
• Abstract summary: We present a new self-supervised pretraining task, Masked Topology Modeling (MTM)<n>MTM masks a fraction of edges and trains a small head to predict each masked edge's convexity and curve type from the encoder's post-message-passing face features.<n>We show strong performance on a number of benchmarks.
• Score: 8.193080292816559
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Computer aided design (CAD) is ubiquitous: virtually any modern object was designed using editable CAD tools. However, with the shortage of available CAD datasets in its native editable and parametric format, boundary representation (B-Rep), it is ever more important to develop data-efficient methods for this domain. We present a new self-supervised pretraining task, Masked Topology Modeling (MTM), that leverages the face-adjacency graph, an induced structure unique to B-reps that the encoder can be asked to reconstruct. MTM masks a fraction of edges and trains a small head to predict each masked edge's convexity and curve type from the encoder's post-message-passing face features. We combine MTM with a MoCo-style momentum-queue contrastive learning over B-rep-aware augmentations, a BFS-connected face-region masked-reconstruction objective, and pretraining on the ABC dataset and our new procedurally generated dataset to show strong performance on a number of benchmarks.

Related papers

• Autoregressive B-Rep Shape Generation with Parametric Surfaces [83.03418080213359]
  ParaCAD is an autoregressive framework for point-cloud-conditioned B-Rep generation.<n>Our model first generates parametric surfaces with constrained UV domains, and then constructs a valid B-Rep by globally intersecting these surfaces.<n>Extensive experiments demonstrate that ParaCAD produces accurate B-Reps with faithful point-cloud alignment.
  arXiv  Detail & Related papers  (2026-07-19T06:14:50Z)
• Masked BRep Autoencoder via Hierarchical Graph Transformer [13.174300628873057]
  We introduce a novel self-supervised learning framework that automatically learns representations from input computer-aided design (CAD) models for downstream tasks.<n>To train our network, we construct a large-scale, unlabeled dataset of boundary representation (BRep) models.<n>We conduct experiments on various tasks and achieve high performance, even with a small amount of labeled data.
  arXiv  Detail & Related papers  (2026-03-16T07:30:11Z)
• Towards High-Fidelity CAD Generation via LLM-Driven Program Generation and Text-Based B-Rep Primitive Grounding [18.983809090879348]
  We present FutureCAD, a novel text-to-CAD framework for high-fidelity CAD generation.<n>Our method generates executable CadQuery scripts, and introduces a text-based query mechanism.<n>Experiments show that FutureCADGround achieves state-of-the-art CAD generation performance.
  arXiv  Detail & Related papers  (2026-03-12T11:54:29Z)
• AMBER: Adaptive Mesh Generation by Iterative Mesh Resolution Prediction [48.72179728638418]
  We propose Adaptive Meshing By Expert Reconstruction (AMBER), a supervised learning approach to mesh adaptation.<n>AMBER iteratively predicts the sizing field, and uses this prediction to produce a new intermediate mesh using an out-of-the-box mesh generator.<n>We evaluate AMBER on 2D and 3D geometries, datasets including classical physics problems, mechanical components, and real-world industrial designs with human expert meshes.
  arXiv  Detail & Related papers  (2025-05-29T17:10:44Z)
• CMT: A Cascade MAR with Topology Predictor for Multimodal Conditional CAD Generation [59.76687657887415]
  We propose a cascade MAR with topology predictor (CMT), the first multimodal framework for CAD generation based on Boundary Representation (B-Rep)<n>Specifically, the cascade MAR can effectively capture the edge-counters-surface'' priors that are essential in B-Reps.<n>We develop a large-scale multimodal CAD dataset, mmABC, which includes over 1.3 million B-Rep models with multimodal annotations.
  arXiv  Detail & Related papers  (2025-04-29T14:52:28Z)
• Bringing Masked Autoencoders Explicit Contrastive Properties for Point Cloud Self-Supervised Learning [116.75939193785143]
  Contrastive learning (CL) for Vision Transformers (ViTs) in image domains has achieved performance comparable to CL for traditional convolutional backbones. In 3D point cloud pretraining with ViTs, masked autoencoder (MAE) modeling remains dominant.
  arXiv  Detail & Related papers  (2024-07-08T12:28:56Z)
• The Multiscale Surface Vision Transformer [10.833580445244094]
  We introduce the Multiscale Surface Vision Transformer (MS-SiT) as a backbone architecture for surface deep learning. Results demonstrate that the MS-SiT outperforms existing surface deep learning methods for neonatal phenotyping prediction tasks.
  arXiv  Detail & Related papers  (2023-03-21T15:00:17Z)
• Masked Autoencoding for Scalable and Generalizable Decision Making [93.84855114717062]
  MaskDP is a simple and scalable self-supervised pretraining method for reinforcement learning and behavioral cloning. We find that a MaskDP model gains the capability of zero-shot transfer to new BC tasks, such as single and multiple goal reaching.
  arXiv  Detail & Related papers  (2022-11-23T07:04:41Z)
• SolidGen: An Autoregressive Model for Direct B-rep Synthesis [15.599363091502365]
  Boundary representation (B-rep) format is de-facto shape representation in computer-aided design (CAD) Recent approaches to generating CAD models have focused on learning sketch-and-extrude modeling sequences. We present a new approach that enables learning from and synthesizing B-reps without the need for supervision.
  arXiv  Detail & Related papers  (2022-03-26T00:00:45Z)
• Shape My Face: Registering 3D Face Scans by Surface-to-Surface Translation [75.59415852802958]
  Shape-My-Face (SMF) is a powerful encoder-decoder architecture based on an improved point cloud encoder, a novel visual attention mechanism, graph convolutional decoders with skip connections, and a specialized mouth model. Our model provides topologically-sound meshes with minimal supervision, offers faster training time, has orders of magnitude fewer trainable parameters, is more robust to noise, and can generalize to previously unseen datasets.
  arXiv  Detail & Related papers  (2020-12-16T20:02:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.