D
Dan Andrei Calian
Researcher at Google
Publications - 17
Citations - 395
Dan Andrei Calian is an academic researcher from Google. The author has contributed to research in topics: Robustness (computer science) & Overfitting. The author has an hindex of 6, co-authored 16 publications receiving 346 citations. Previous affiliations of Dan Andrei Calian include Disney Research & University College London.
Papers
More filters
Journal ArticleDOI
3D-printing of non-assembly, articulated models
Jacques Cali,Dan Andrei Calian,Cristina Amati,Rebecca Kleinberger,Anthony Steed,Jan Kautz,Tim Weyrich +6 more
TL;DR: This paper proposes an intuitive work-flow that takes an appropriately rigged 3D model, automatically fits novel 3D-printable and posable joints, and provides an interface for specifying rotational constraints, and shows a number of results, demonstrating the effectiveness of the method.
Journal ArticleDOI
From Faces to Outdoor Light Probes
Dan Andrei Calian,Dan Andrei Calian,Jean-François Lalonde,Paulo F. U. Gotardo,Tomas Simon,Iain Matthews,Kenny Mitchell,Kenny Mitchell +7 more
TL;DR: This paper presents an approach to directly estimate an HDR light probe from a single LDR photograph, shot outdoors with a consumer camera, without specialized calibration targets or equipment, and shows that relighting objects with HDR light probes estimated by the method yields realistic results in a wide variety of settings.
Proceedings ArticleDOI
The shading probe: fast appearance acquisition for mobile AR
TL;DR: A novel light probe is designed and exploited to permit an efficient reformulation of the rendering equation that is suitable for fast shading on mobile devices, and achieves high-performance shading of virtual objects in an AR context, incorporating plausible local global-illumination effects, on mobile platforms.
Posted Content
Fixing Data Augmentation to Improve Adversarial Robustness
Sylvestre-Alvise Rebuffi,Sven Gowal,Dan Andrei Calian,Florian Stimberg,Olivia Wiles,Timothy A. Mann +5 more
TL;DR: In this paper, both heuristics-driven and data-driven augmentations are used to reduce robust overfitting in adversarial training, which is a phenomenon where the robust test accuracy starts to decrease during training.
Patent
Optical illumination mapping
TL;DR: In this article, a visual scene is captured using one or more camera devices and the first object is identified as a first predetermined object type, based on one or multiple object identifiers associated with the physical object.