C
Cristian Sminchisescu
Researcher at Google
Publications - 189
Citations - 14699
Cristian Sminchisescu is an academic researcher from Google. The author has contributed to research in topics: Computer science & Image segmentation. The author has an hindex of 53, co-authored 173 publications receiving 12268 citations. Previous affiliations of Cristian Sminchisescu include University of Toronto & Romanian Academy.
Papers
More filters
Proceedings ArticleDOI
Chebyshev approximations to the histogram χ 2 kernel
TL;DR: An asymptotically convergent analytic series of the χ2 measure, based on analogies with Chebyshev polynomials, is proposed to reduce the dimensionality of the approximation and achieve better performance at the expense of only an additional constant factor to the time complexity.
Proceedings ArticleDOI
Photorealistic Monocular 3D Reconstruction of Humans Wearing Clothing
TL;DR: PHORHUM, a novel, end-to-end trainable, deep neural network methodology for photorealistic 3D human reconstruction given just a monocular RGB image, introduces patch-based rendering losses that enable reliable color reconstruction on visible parts of the human, and detailed and plausible color estimation for the non-visible parts.
Proceedings Article
imGHUM: Implicit Generative Models of 3D Human Shape and Articulated Pose
TL;DR: In this article, the authors present imGHUM, the first holistic generative model of 3D human shape and articulated pose, represented as a signed distance function, which can be queried at arbitrary resolutions and spatial locations.
Proceedings Article
Spatiotemporal closure
TL;DR: The concept of spatiotemporal closure is introduced, and it is shown how it can be globally minimized using the parametric maxflow framework in an efficient manner.
Posted Content
Neural Descent for Visual 3D Human Pose and Shape.
Andrei Zanfir,Eduard Gabriel Bazavan,Mihai Zanfir,William T. Freeman,Rahul Sukthankar,Cristian Sminchisescu +5 more
TL;DR: HUND’s symmetry between training and testing makes it the first 3d human sensing architecture to natively support different operating regimes including self-supervised ones, as well as good quality 3d reconstructions for complex imagery collected in-the-wild.