Flexible SVBRDF Capture with a Multi‐Image Deep Network (Englisch)

In: Computer Graphics Forum   ;  38 ,  4  ;  1-13  ;  2019

Wie erhalte ich diesen Titel?

Download
Kommerziell Vergütung an den Verlag: 35,20 € Grundgebühr: 4,00 € Gesamtpreis: 39,20 €
Akademisch Vergütung an den Verlag: 35,20 € Grundgebühr: 2,00 € Gesamtpreis: 37,20 €

Empowered by deep learning, recent methods for material capture can estimate a spatially‐varying reflectance from a single photograph. Such lightweight capture is in stark contrast with the tens or hundreds of pictures required by traditional optimization‐based approaches. However, a single image is often simply not enough to observe the rich appearance of real‐world materials. We present a deep‐learning method capable of estimating material appearance from a variable number of uncalibrated and unordered pictures captured with a handheld camera and flash. Thanks to an order‐independent fusing layer, this architecture extracts the most useful information from each picture, while benefiting from strong priors learned from data. The method can handle both view and light direction variation without calibration. We show how our method improves its prediction with the number of input pictures, and reaches high quality reconstructions with as little as 1 to 10 images ‐ a sweet spot between existing single‐image and complex multi‐image approaches.

Inhaltsverzeichnis – Band 38, Ausgabe 4

Zeige alle Jahrgänge und Ausgaben

Die Inhaltsverzeichnisse werden automatisch erzeugt und basieren auf den im Index des TIB-Portals verfügbaren Einzelnachweisen der enthaltenen Beiträge. Die Anzeige der Inhaltsverzeichnisse kann daher unvollständig oder lückenhaft sein.

1
Flexible SVBRDF Capture with a Multi‐Image Deep Network
Deschaintre, Valentin / Aittala, Miika / Durand, Fredo / Drettakis, George / Bousseau, Adrien | 2019
15
On‐Site Example‐Based Material Appearance Acquisition
Lin, Y. / Peers, P. / Ghosh, A. | 2019
27
Glint Rendering based on a Multiple‐Scattering Patch BRDF
Chermain, Xavier / Claux, Frédéric / Mérillou, Stéphane | 2019
39
Microfacet Model Regularization for Robust Light Transport
Jendersie, Johannes / Grosch, Thorsten | 2019
49
Ray Classification for Accelerated BVH Traversal
Hendrich, J. / Pospíšil, A. / Meister, D. / Bittner, J. | 2019
57
Scalable Virtual Ray Lights Rendering for Participating Media
Vibert, N. / Gruson, A. / Stokholm, H. / Mortensen, T / Jarosz, W. / Hachisuka, T. / Nowrouzezahrai, D. | 2019
67
Adaptive Temporal Sampling for Volumetric Path Tracing of Medical Data
Martschinke, J. / Hartnagel, S. / Keinert, B. / Engel, K. / Stamminger, M. | 2019
77
Real‐time Image‐based Lighting of Microfacet BRDFs with Varying Iridescence
Kneiphof, Tom / Golla, Tim / Klein, Reinhard | 2019
87
Wide Gamut Spectral Upsampling with Fluorescence
Jung, A. / Wilkie, A. / Hanika, J. / Jakob, W. / Dachsbacher, C. | 2019
97
Analytic Spectral Integration of Birefringence‐Induced Iridescence
Steinberg, S. | 2019
111
Quantifying the Error of Light Transport Algorithms
Celarek, A. / Jakob, W. / Wimmer, M. / Lehtinen, J. | 2019
123
Adaptive BRDF‐Oriented Multiple Importance Sampling of Many Lights
Liu, Yifan / Xu, Kun / Yan, Ling‐Qi | 2019
135
Orthogonal Array Sampling for Monte Carlo Rendering
Jarosz, Wojciech / Enayet, Afnan / Kensler, Andrew / Kilpatrick, Charlie / Christensen, Per | 2019
149
Distributing Monte Carlo Errors as a Blue Noise in Screen Space by Permuting Pixel Seeds Between Frames
Heitz, E. / Belcour, L. | 2019
159
Combining Point and Line Samples for Direct Illumination
Salesin, Katherine / Jarosz, Wojciech | 2019
171
Tessellated Shading Streaming
Hladky, J. / Seidel, H. P. / Steinberger, M. | 2019
183
Global Illumination Shadow Layers
Desrichard, François / Vanderhaeghe, David / Paulin, Mathias | 2019
193
Learned Fitting of Spatially Varying BRDFs
Merzbach, S. / Hermann, M. / Rump, M. / Klein, R. | 2019
207
Deep‐learning the Latent Space of Light Transport
Hermosilla, P. / Maisch, S. / Ritschel, T. / Ropinski, T. | 2019
i
Front Matter
| 2019