Fusion 360 gallery: A dataset and environment for programmatic cad construction from human design sequences

KDD Willis, Y Pu, J Luo, H Chu, T Du… - ACM Transactions on …, 2021 - dl.acm.org
Parametric computer-aided design (CAD) is a standard paradigm used to design
manufactured objects, where a 3D shape is represented as a program supported by the …

Evaluation metrics for intelligent generation of graphical game assets: a systematic survey-based framework

K Fukaya, D Daylamani-Zad… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Generative systems for graphical assets have the potential to provide users with high quality
assets at the push of a button. However, there are many forms of assets, and many …

3d-aware object goal navigation via simultaneous exploration and identification

J Zhang, L Dai, F Meng, Q Fan… - Proceedings of the …, 2023 - openaccess.thecvf.com
Object goal navigation (ObjectNav) in unseen environments is a fundamental task for
Embodied AI. Agents in existing works learn ObjectNav policies based on 2D maps, scene …

UCSG-NET-unsupervised discovering of constructive solid geometry tree

K Kania, M Zieba… - Advances in neural …, 2020 - proceedings.neurips.cc
Signed distance field (SDF) is a prominent implicit representation of 3D meshes. Methods
that are based on such representation achieved state-of-the-art 3D shape reconstruction …

[HTML][HTML] Deep reinforcement learning for the rapid on-demand design of mechanical metamaterials with targeted nonlinear deformation responses

NK Brown, AP Garland, GM Fadel, G Li - Engineering Applications of …, 2023 - Elsevier
Mechanical metamaterials are artificial materials with unique global properties due to the
structural geometry and material composition of their unit cell. Typically, mechanical …

Part123: part-aware 3d reconstruction from a single-view image

A Liu, C Lin, Y Liu, X Long, Z Dou, HX Guo… - ACM SIGGRAPH 2024 …, 2024 - dl.acm.org
Recently, the emergence of diffusion models has opened up new opportunities for single-
view reconstruction. However, all the existing methods represent the target object as a …

Surface and edge detection for primitive fitting of point clouds

Y Li, S Liu, X Yang, J Guo, J Guo, Y Guo - ACM SIGGRAPH 2023 …, 2023 - dl.acm.org
Fitting primitives for point cloud data to obtain a structural representation has been widely
adopted for reverse engineering and other graphics applications. Existing segmentation …

Deep reinforcement learning for engineering design through topology optimization of elementally discretized design domains

NK Brown, AP Garland, GM Fadel, G Li - Materials & Design, 2022 - Elsevier
Advances in machine learning algorithms and increased computational efficiencies give
engineers new capabilities and tools to apply to engineering design. Machine learning …

3D reconstruction based on hierarchical reinforcement learning with transferability

L Li, F He, R Fan, B Fan, X Yan - Integrated Computer-Aided …, 2023 - content.iospress.com
Abstract 3D reconstruction is extremely important in CAD (computer-aided design)/CAE
(computer-aided Engineering)/CAM (computer-aided manufacturing). For interpretability …

Solidgen: An autoregressive model for direct b-rep synthesis

PK Jayaraman, JG Lambourne, N Desai… - arxiv preprint arxiv …, 2022 - arxiv.org
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 …