Secad-net: Self-supervised cad reconstruction by learning sketch-extrude operations
Reverse engineering CAD models from raw geometry is a classic but strenuous research
problem. Previous learning-based methods rely heavily on labels due to the supervised …
problem. Previous learning-based methods rely heavily on labels due to the supervised …
Neurosymbolic models for computer graphics
Procedural models (ie symbolic programs that output visual data) are a historically‐popular
method for representing graphics content: vegetation, buildings, textures, etc. They offer …
method for representing graphics content: vegetation, buildings, textures, etc. They offer …
DCSG: Unsupervised Learning of Compact CSG Trees with Dual Complements and Dropouts
Abstract We present D $^ 2$ CSG, a neural model composed of two dual and
complementary network branches, with dropouts, for unsupervised learning of compact …
complementary network branches, with dropouts, for unsupervised learning of compact …
Surface and edge detection for primitive fitting of point clouds
Fitting primitives for point cloud data to obtain a structural representation has been widely
adopted for reverse engineering and other graphics applications. Existing segmentation …
adopted for reverse engineering and other graphics applications. Existing segmentation …
Solidgen: An autoregressive model for direct b-rep synthesis
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 …
computer-aided design (CAD) to model solid and sheet objects. Recent approaches to …
Sketch-a-shape: Zero-shot sketch-to-3d shape generation
Significant progress has recently been made in creative applications of large pre-trained
models for downstream tasks in 3D vision, such as text-to-shape generation. This motivates …
models for downstream tasks in 3D vision, such as text-to-shape generation. This motivates …
Transcad: A hierarchical transformer for cad sequence inference from point clouds
Abstract 3D reverse engineering, in which a CAD model is inferred given a 3D scan of a
physical object, is a research direction that offers many promising practical applications. This …
physical object, is a research direction that offers many promising practical applications. This …
Hierarchical neural coding for controllable cad model generation
This paper presents a novel generative model for Computer Aided Design (CAD) that 1)
represents high-level design concepts of a CAD model as a three-level hierarchical tree of …
represents high-level design concepts of a CAD model as a three-level hierarchical tree of …
SHARP Challenge 2023: Solving CAD History and pArameters Recovery from Point clouds and 3D scans. Overview, Datasets, Metrics, and Baselines.
Recent breakthroughs in geometric deep learning (DL) and the availability of large computer-
aided design (CAD) datasets have advanced the research on learning CAD modeling …
aided design (CAD) datasets have advanced the research on learning CAD modeling …
Split-and-fit: Learning b-reps via structure-aware voronoi partitioning
We introduce a novel method for acquiring boundary representations (B-Reps) of 3D CAD
models which involves a two-step process: it first applies a spatial partitioning, referred to as …
models which involves a two-step process: it first applies a spatial partitioning, referred to as …