4 Hits in 3.7 sec

LASR: Learning Articulated Shape Reconstruction from a Monocular Video [article]

Gengshan Yang, Deqing Sun, Varun Jampani, Daniel Vlasic, Forrester Cole, Huiwen Chang, Deva Ramanan, William T. Freeman, Ce Liu
2021 arXiv   pre-print
In this work, we introduce a template-free approach to learn 3D shapes from a single video.  ...  Remarkable progress has been made in 3D reconstruction of rigid structures from a video or a collection of images.  ...  Conclusion We present LASR, a template-free approach for articulated shape reconstruction from a monocular video.  ... 
arXiv:2105.02976v1 fatcat:oostakof65ah7epconiy63y24y

DOVE: Learning Deformable 3D Objects by Watching Videos [article]

Shangzhe Wu, Tomas Jakab, Christian Rupprecht, Andrea Vedaldi
2021 arXiv   pre-print
Specifically, we present DOVE, which learns to predict 3D canonical shape, deformation, viewpoint and texture from a single 2D image of a bird, given a bird video collection as well as automatically obtained  ...  Our method reconstructs temporally consistent 3D shape and deformation, which allows us to animate and re-render the bird from arbitrary viewpoints from a single image.  ...  In summary, we present a method that learns to reconstruct deformable 3D object categories from "in-the-wild" monocular videos.  ... 
arXiv:2107.10844v1 fatcat:iegcege7djcd7m4wshirelmdsm

BANMo: Building Animatable 3D Neural Models from Many Casual Videos [article]

Gengshan Yang, Minh Vo, Natalia Neverova, Deva Ramanan, Andrea Vedaldi, Hanbyul Joo
2021 arXiv   pre-print
BANMo builds high-fidelity, articulated 3D models (including shape and animatable skinning weights) from many monocular casual videos in a differentiable rendering framework.  ...  We present BANMo, a method that requires neither a specialized sensor nor a pre-defined template shape.  ...  LASR: Learning articulated shape rigid structure from motion with latent space constraints. In reconstruction from a monocular video.  ... 
arXiv:2112.12761v2 fatcat:creiz2vswzdozoghhury7g5aza

Self-supervised Neural Articulated Shape and Appearance Models [article]

Fangyin Wei, Rohan Chabra, Lingni Ma, Christoph Lassner, Michael Zollhöfer, Szymon Rusinkiewicz, Chris Sweeney, Richard Newcombe, Mira Slavcheva
2022 arXiv   pre-print
In a self-supervised manner, our novel representation learns shape, appearance, and articulation codes that enable independent control of these semantic dimensions.  ...  We propose a novel approach for learning a representation of the geometry, appearance, and motion of a class of articulated objects given only a set of color images as input.  ...  However, the reconstruction only provides geometry. Recently, LASR [70] proposes a template-free approach to reconstructing articulated shapes from monocular video.  ... 
arXiv:2205.08525v1 fatcat:fjmtfkjn7jbkzafuncxzsu5lje