W
William A. P. Smith
Researcher at University of York
Publications - 202
Citations - 5631
William A. P. Smith is an academic researcher from University of York. The author has contributed to research in topics: Statistical model & Facial recognition system. The author has an hindex of 35, co-authored 198 publications receiving 4489 citations. Previous affiliations of William A. P. Smith include Imperial College London & Daresbury Laboratory.
Papers
More filters
Book ChapterDOI
Facial shadow removal
TL;DR: This paper demonstrates how to recover surface shape from single images of faces using shape-from-shading when shadows are present and shows how ideas from robust statistics can be used to fit the model to facial images in which there is significant self-shadowing.
A virtual research organization enabled by eMinerals minigrid: An integrated study of the transport and immobilisation of arsenic species in the environment
Z Du,V. N. Alexander,Maria Alfredsson,Emilio Artacho,Kat Austen,N. D. Bennett,Marc Blanchard,John P. Brodholt,R. P. Bruin,C. R. A. Catlow,C Chapman,David J. Cooke,Timothy G. Cooper,Martin T. Dove,Wolfgang Emmerich,SM Hasan,Sebastien Kerisit,N. H. de Leeuw,G. J. Lewis,A. Marmier,Stephen C. Parker,Geoffrey D. Price,William A. P. Smith,I. T. Todorov,RP Tyer,Kerstin Kleese van Dam,Andrew Walker,T. O. H. White,Kate Wright +28 more
TL;DR: It is shown here that the new approach for scientific research is only feasible with the use of the eMinerals minigrid, and allows us to achieve the authors' goals in a much quicker, more comprehensive and detailed way.
Book ChapterDOI
A model-based method for face shape recovery
TL;DR: This paper describes a model-based method for recovering the 3D shape of faces using shape-from-shading andfits the model to intensity data using constraints on the surface normal direction provided by Lambert's law.
Book ChapterDOI
Reconstructing Creative Lego Models
TL;DR: A novel, fully automatic pipeline to reconstruct Lego models in 3D from 2D images, an angular variant of DBSCAN, useful for grouping both parallel and anti-parallel vectors; and a method for reducing the problem of non-Manhattan reconstruction to that of Manhattan reconstruction are presented.
Posted Content
Self-supervised Outdoor Scene Relighting
Ye Yu,Abhimitra Meka,Mohamed Elgharib,Hans-Peter Seidel,Christian Theobalt,William A. P. Smith +5 more
TL;DR: In this article, a self-supervised approach for outdoor scene relighting is proposed, which is trained only on corpora of images collected from the internet without any user-supervision.