Geometry-Aware Scattering Compensation for 3D Printing

被引:38
|
作者
Sumin, Denis [1 ]
Rittig, Tobias [2 ]
Babaei, Vahid [1 ]
Nindel, Thomas [2 ]
Wilkie, Alexander [2 ]
Didyk, Piotr [3 ]
Bickel, Bernd [4 ]
Krivanek, Jaroslav [2 ]
Myszkowski, Karol [1 ]
Weyrich, Tim [5 ]
机构
[1] Max Planck Inst Informat, Saarbrucken, Germany
[2] Charles Univ Prague, Prague, Czech Republic
[3] Univ Svizzera Italiana, Lugano, Switzerland
[4] IST Austria, Vienna, Austria
[5] UCL, London, England
来源
ACM TRANSACTIONS ON GRAPHICS | 2019年 / 38卷 / 04期
基金
欧盟地平线“2020”;
关键词
computational fabrication; appearance reproduction; appearance enhancement; sub-surface light transport; volumetric optimization; gradient rendering;
D O I
10.1145/3306346.3322992
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
Commercially available full-color 3D printing allows for detailed control of material deposition in a volume, but an exact reproduction of a target surface appearance is hampered by the strong subsurface scattering that causes nontrivial volumetric cross-talk at the print surface. Previous work showed how an iterative optimization scheme based on accumulating absorptive materials at the surface can be used to find a volumetric distribution of print materials that closely approximates a given target appearance. In this work, we first revisit the assumption that pushing the absorptive materials to the surface results in minimal volumetric cross-talk. We design a full-fledged optimization on a small domain for this task and confirm this previously reported heuristic. Then, we extend the above approach that is critically limited to color reproduction on planar surfaces, to arbitrary 3D shapes. Our method enables high-fidelity color texture reproduction on 3D prints by effectively compensating for internal light scattering within arbitrarily shaped objects. In addition, we propose a content-aware gamut mapping that significantly improves color reproduction for the pathological case of thin geometric features. Using a wide range of sample objects with complex textures and geometries, we demonstrate color reproduction whose fidelity is superior to state-of-the-art drivers for color 3D printers.
引用
收藏
页数:14
相关论文
共 50 条
  • [21] GNet: 3D Object Detection from Point Cloud with Geometry-Aware Network
    Ruan, Hao
    Xu, Bingrong
    Gao, Junbin
    Liu, Lianguang
    Lv, Junting
    Sheng, Yin
    Zeng, Zhigang
    2022 IEEE INTERNATIONAL CONFERENCE ON CYBORG AND BIONIC SYSTEMS, CBS, 2022, : 190 - 195
  • [22] Human Motion Prediction: Assessing Direct and Geometry-Aware Approaches in 3D Space
    Idrees, Sarmad
    Kim, Jiwoo
    Choi, Jongeun
    Sohn, Seokman
    IEEE ACCESS, 2024, 12 : 104643 - 104662
  • [23] Improving 3D-aware Image Synthesis with A Geometry-aware Discriminator
    Shi, Zifan
    Xu, Yinghao
    Shen, Yujun
    Zhao, Deli
    Chen, Qifeng
    Yeung, Dit-Yan
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35 (NEURIPS 2022), 2022,
  • [24] Weakly-Supervised Discovery of Geometry-Aware Representation for 3D Human Pose Estimation
    Chen, Xipeng
    Lin, Kwan-Yee
    Liu, Wentao
    Qian, Chen
    Lin, Liang
    2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, : 10887 - 10896
  • [25] Neural Acceleration of Scattering-Aware Color 3D Printing
    Rittig, Tobias
    Sumin, Denis
    Babaei, Vahid
    Didyk, Piotr
    Voloboy, Alexey
    Wilkie, Alexander
    Bickel, Bernd
    Myszkowski, Karol
    Weyrich, Tim
    Krivanek, Jaroslav
    COMPUTER GRAPHICS FORUM, 2021, 40 (02) : 205 - 219
  • [26] Self-Supervised Geometry-Aware Encoder for Style-Based 3D GAN Inversion
    Lan, Yushi
    Meng, Xuyi
    Yang, Shuai
    Loy, Chen Change
    Dai, Bo
    2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2023, : 20940 - 20949
  • [27] Exploring Geometry-aware Contrast and Clustering Harmonization for Self-supervised 3D Object Detection
    Liang, Hanxue
    Jiang, Chenhan
    Feng, Dapeng
    Chen, Xin
    Xu, Hang
    Liang, Xiaodan
    Zhang, Wei
    Li, Zhenguo
    Van Gool, Luc
    2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 3273 - 3282
  • [28] Learning 6-DOF Grasping Interaction via Deep Geometry-aware 3D Representations
    Yan, Xinchen
    Hsu, Jasmine
    Khansari, Mohammad
    Bai, Yunfei
    Pathak, Arkanath
    Gupta, Abhinav
    Davidson, James
    Lee, Honglak
    2018 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2018, : 3766 - 3773
  • [29] Consistent-1-to-3: Consistent Image to 3D View Synthesis via Geometry-aware Diffusion Models
    Ye, Jianglong
    Wang, Peng
    Li, Kejie
    Shi, Yichun
    Wang, Heng
    2024 INTERNATIONAL CONFERENCE IN 3D VISION, 3DV 2024, 2024, : 664 - 674
  • [30] Geometry-Aware Neural Rendering
    Tobin, Josh
    Abbeel, Pieter
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), 2019, 32