Collision sequences are commonly used in games and entertainment to add drama and excitement. Authoring even two body collisions in real world can be difficult as one has to get timing and the object trajectories to be correctly synchronized. After trial-anderror iterations, when objects can actually be made to collide, then they are difficult to acquire in 3D. In contrast, synthetically generating plausible collisions is difficult as it requires adjusting different collision parameters (e.g., object mass ratio, coefficient of restitution, etc.) and appropriate initial parameters. We present SMASH to directly ‘read off’ appropriate collision parameters simply based on input video recordings. Specifically, we describe how to use laws of rigid body collision to regularize the problem of lifting 2D annotated poses to 3D reconstruction of collision sequences. The reconstructed sequences can then be modified and combined to easily author novel and plausible collision sequences. We demonstrate the system on various complex collision sequences.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    SMASH: Data-driven Reconstruction of Physically Valid Collisions.


    Beteiligte:
    Monszpart, A (Autor:in) / Thuerey, N (Autor:in) / Mitra, NJ (Autor:in)

    Erscheinungsdatum :

    11.11.2016


    Anmerkungen:

    CM Transactions on Graphics (TOG) , 35 (6) , Article 199. (2016)


    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    629



    Physically-Valid View Synthesis by Image Interpolation

    Seitz, S. / Dyer, C. / IEEE et al. | British Library Conference Proceedings | 1995


    Physically-valid view synthesis by image interpolation

    Seitz, S.M. / Dyer, C.R. | IEEE | 1995


    Smash & Grab

    Online Contents | 1998


    Italian tilt train smash

    British Library Online Contents | 1997


    Consistent Valid Physically-Realizable Adversarial Attack Against Crowd-Flow Prediction Models

    Ali, Hassan / Butt, Muhammad Atif / Filali, Fethi et al. | IEEE | 2024

    Freier Zugriff