Differentiable 3D CAD Programs for Bidirectional Editing

被引:16
|
作者
Cascaval, D. [1 ]
Shalah, M. [2 ]
Quinn, P. [1 ]
Bodik, R. [1 ]
Agrawala, M. [2 ]
Schulz, A. [1 ]
机构
[1] Univ Washington, Seattle, WA 98195 USA
[2] Stanford Univ, Stanford, CA 94305 USA
关键词
CCS Concepts; center dot Computing methodologies -> Shape modeling; Graphics systems and interfaces;
D O I
10.1111/cgf.14476
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
Modern CAD tools represent 3D designs not only as geometry, but also as a program composed of geometric operations, each of which depends on a set of parameters. Program representations enable meaningful and controlled shape variations via parameter changes. However, achieving desired modifications solely through parameter editing is challenging when CAD models have not been explicitly authored to expose select degrees of freedom in advance. We introduce a novel bidirectional editing system for 3D CAD programs. In addition to editing the CAD program, users can directly manipulate 3D geometry and our system infers parameter updates to keep both representations in sync. We formulate inverse edits as a set of constrained optimization objectives, returning plausible updates to program parameters that both match user intent and maintain program validity. Our approach implements an automatically differentiable domain-specific language for CAD programs, providing derivatives for this optimization to be performed quickly on any expressed program. Our system enables rapid, interactive exploration of a constrained 3D design space by allowing users to manipulate the program and geometry interchangeably during design iteration. While our approach is not designed to optimize across changes in geometric topology, we show it is expressive and performant enough for users to produce a diverse set of design variants, even when the CAD program contains a relatively large number of parameters.
引用
收藏
页码:309 / 323
页数:15
相关论文
共 50 条
  • [41] Accurate Real-time 3D Gaze Tracking Using a Lightweight Eyeball Calibration
    Wen, Q.
    Bradley, D.
    Beeler, T.
    Park, S.
    Hilliges, O.
    Yong, J.
    Xu, F.
    COMPUTER GRAPHICS FORUM, 2020, 39 (02) : 475 - 485
  • [42] Learning to Generate and Manipulate 3D Radiance Field by a Hierarchical Diffusion Framework with CLIP Latent
    Wang, Jiaxu
    Zhang, Ziyi
    Xu, Renjing
    COMPUTER GRAPHICS FORUM, 2023, 42 (07)
  • [43] Curve Complexity Heuristic KD-trees for Neighborhood-based Exploration of 3D Curves
    Lu, Yucheng
    Cheng, Luyu
    Isenberg, Tobias
    Fu, Chi-Wing
    Chen, Guoning
    Liu, Hui
    Deussen, Oliver
    Wang, Yunhai
    COMPUTER GRAPHICS FORUM, 2021, 40 (02) : 461 - 474
  • [44] Generating Texture for 3D Human Avatar from a Single Image using Sampling and Refinement Networks
    Cha, Sihun
    Seo, Kwanggyoon
    Ashtari, Amirsaman
    Noh, Junyong
    COMPUTER GRAPHICS FORUM, 2023, 42 (02) : 385 - 396
  • [45] Cascaded 3D Full-Body Pose Regression from Single Depth Image at 100 FPS
    Xia, Shihong
    Zhang, Zihao
    Su, Le
    25TH 2018 IEEE CONFERENCE ON VIRTUAL REALITY AND 3D USER INTERFACES (VR), 2018, : 431 - 438
  • [46] GBOT: Graph-Based 3D Object Tracking for Augmented Reality-Assisted Assembly Guidance
    Li, Shiyu
    Schieber, Hannah
    Corell, Niklas
    Egger, Bernhard
    Kreimeier, Julian
    Roth, Daniel
    2024 IEEE CONFERENCE ON VIRTUAL REALITY AND 3D USER INTERFACES, VR 2024, 2024, : 513 - 523
  • [47] Fabricatable 90° Pop-ups: Interactive Transformation of a 3D Model into a Pop-up Structure
    Fujikawa, J.
    Ijiri, T.
    COMPUTER GRAPHICS FORUM, 2023, 42 (07)
  • [48] InstanceFusion: Real-time Instance-level 3D Reconstruction Using a Single RGBD Camera
    Lu, Feixiang
    Peng, Haotian
    Wu, Hongyu
    Yang, Jun
    Yang, Xinhang
    Cao, Ruizhi
    Zhang, Liangjun
    Yang, Ruigang
    Zhou, Bin
    COMPUTER GRAPHICS FORUM, 2020, 39 (07) : 433 - 445
  • [49] An Occlusion-aware Edge-Based Method for Monocular 3D Object Tracking using Edge Confidence
    Huang, Hong
    Zhong, Fan
    Sun, Yuqing
    Qin, Xueying
    COMPUTER GRAPHICS FORUM, 2020, 39 (07) : 399 - 409
  • [50] Weakly Supervised Part-wise 3D Shape Reconstruction from Single-View RGB Images
    Niu, Chengjie
    Yu, Yang
    Bian, Zhenwei
    Li, Jun
    Xu, Kai
    COMPUTER GRAPHICS FORUM, 2020, 39 (07) : 447 - 457