Calipso: physics-based image and video editing through CAD model proxies

被引:0
|
作者
Nazim Haouchine
Frederick Roy
Hadrien Courtecuisse
Matthias Nießner
Stephane Cotin
机构
[1] Inria,AVR/ICube
[2] University of Strasbourg,undefined
[3] CNRS,undefined
[4] Stanford University,undefined
[5] Technical University of Munich,undefined
来源
The Visual Computer | 2020年 / 36卷
关键词
Video and image manipulations; Interactive editing; Physics-based modeling; Scene dynamics;
D O I
暂无
中图分类号
学科分类号
摘要
We present Calipso, an interactive method for editing images and videos in a physically coherent manner. Our main idea is to realize physics-based manipulations by running a full-physics simulation on proxy geometries given by non-rigidly aligned CAD models. Running these simulations allows us to apply new, unseen forces to move or deform selected objects, change physical parameters such as mass or elasticity, or even add entire new objects that interact with the rest of the underlying scene. In our method, the user makes edits directly in 3D; these edits are processed by the simulation and then transferred to the target 2D content using shape-to-image correspondences in a photo-realistic rendering process. To align the CAD models, we introduce an efficient CAD-to-image alignment procedure that jointly minimizes for rigid and non-rigid alignment while preserving the high-level structure of the input shape. Moreover, the user can choose to exploit image flow to estimate scene motion, producing coherent physical behavior with ambient dynamics. We demonstrate physics-based editing on a wide range of examples producing myriad physical behavior while preserving geometric and visual consistency.
引用
收藏
页码:211 / 226
页数:15
相关论文
共 50 条
  • [21] A physics-based power diode model optimized through experiment based parameter extraction
    Chibante, Rui
    Araujo, Armando
    Carvalho, Adriano
    2007 EUROPEAN CONFERENCE ON POWER ELECTRONICS AND APPLICATIONS, VOLS 1-10, 2007, : 2737 - +
  • [22] Physics-based shape deformations for medical image analysis
    Hamarneh, G
    McInerney, T
    IMAGE PROCESSING: ALGORITHMS AND SYSTEMS II, 2003, 5014 : 354 - 362
  • [23] Physics-based shading reconstruction for intrinsic image decomposition
    Baslamisli, Anil S.
    Liu, Yang
    Karaoglu, Sezer
    Gevers, Theo
    COMPUTER VISION AND IMAGE UNDERSTANDING, 2021, 205
  • [24] Physics-Based Shadow Image Decomposition for Shadow Removal
    Le, Hieu
    Samaras, Dimitris
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2022, 44 (12) : 9088 - 9101
  • [25] Physics-based shape matching for intraoperative image guidance
    Suwelack, Stefan
    Roehl, Sebastian
    Bodenstedt, Sebastian
    Reichard, Daniel
    Dillmann, Ruediger
    dos Santos, Thiago
    Maier-Hein, Lena
    Wagner, Martin
    Wuenscher, Josephine
    Kenngott, Hannes
    Mueller, Beat P.
    Speidel, Stefanie
    MEDICAL PHYSICS, 2014, 41 (11)
  • [26] Physics-based deformable organisms for medical image analysis
    Hamarneh, G
    McIntosh, C
    MEDICAL IMAGING 2005: IMAGE PROCESSING, PT 1-3, 2005, 5747 : 326 - 335
  • [27] Physics-based reward driven image analysis in microscopy
    Barakati, K.
    Yuan, Hui
    Goyal, Amit
    Kalinin, S. V.
    DIGITAL DISCOVERY, 2024, 3 (10): : 2061 - 2069
  • [28] Physics-based Fast Single Image Fog Removal
    Yu, Jing
    Xiao, Chuangbai
    Li, Dapeng
    2010 IEEE 10TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING PROCEEDINGS (ICSP2010), VOLS I-III, 2010, : 1048 - +
  • [29] Physics-based models of color and IR video for sensor fusion
    Nadimi, S
    Bhanu, B
    PROCEEDINGS OF THE IEEE INTERNATIONAL CONFERENCE ON MULTISENSOR FUSION AND INTEGRATION FOR INTELLIGENT SYSTEMS, 2003, : 161 - 166
  • [30] A minimal physics-based model for musical perception
    Mozaffari, Kosar
    Ahmadpoor, Fatemeh
    Deng, Qian
    Sharma, Pradeep
    PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2023, 120 (05)