eprintid: 10159070 rev_number: 6 eprint_status: archive userid: 699 dir: disk0/10/15/90/70 datestamp: 2022-11-14 14:53:29 lastmod: 2022-11-14 14:53:29 status_changed: 2022-11-14 14:53:29 type: article metadata_visibility: show sword_depositor: 699 creators_name: Henzler, Philipp creators_name: Deschaintre, Valentin creators_name: Mitra, Niloy J creators_name: Ritschel, Tobias title: Generative Modelling of BRDF Textures from Flash Images ispublished: pub divisions: UCL divisions: B04 divisions: C05 divisions: F48 keywords: Science & Technology, Technology, Computer Science, Software Engineering, Computer Science, material capture, appearance capture, SVBRDF, deep learning, generative model, unsupervised learning, ILLUMINATION, REFLECTANCE note: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. abstract: We learn a latent space for easy capture, consistent interpolation, and efficient reproduction of visual material appearance. When users provide a photo of a stationary natural material captured under flashlight illumination, first it is converted into a latent material code. Then, in the second step, conditioned on the material code, our method produces an infinite and diverse spatial field of BRDF model parameters (diffuse albedo, normals, roughness, specular albedo) that subsequently allows rendering in complex scenes and illuminations, matching the appearance of the input photograph. Technically, we jointly embed all flash images into a latent space using a convolutional encoder, and -conditioned on these latent codes- convert random spatial fields into fields of BRDF parameters using a convolutional neural network (CNN). We condition these BRDF parameters to match the visual characteristics (statistics and spectra of visual features) of the input under matching light. A user study compares our approach favorably to previous work, even those with access to BRDF supervision. Project webpage: https://henzler.github.io/publication/neuralmaterial/. date: 2021-12-01 date_type: published publisher: ASSOC COMPUTING MACHINERY official_url: https://doi.org/10.1145/3478513.3480507 oa_status: green full_text_type: other language: eng primo: open primo_central: open_green verified: verified_manual elements_id: 1914734 doi: 10.1145/3478513.3480507 lyricists_name: Mitra, Niloy lyricists_id: NMITR19 actors_name: Mitra, Niloy actors_id: NMITR19 actors_role: owner funding_acknowledgements: [ERC]; [Google AR/VR Research Award]; EP/N006259/1 [EPSRC] full_text_status: public publication: ACM Transactions on Graphics volume: 40 number: 6 article_number: 284 pages: 13 issn: 0730-0301 citation: Henzler, Philipp; Deschaintre, Valentin; Mitra, Niloy J; Ritschel, Tobias; (2021) Generative Modelling of BRDF Textures from Flash Images. ACM Transactions on Graphics , 40 (6) , Article 284. 10.1145/3478513.3480507 <https://doi.org/10.1145/3478513.3480507>. Green open access document_url: https://discovery.ucl.ac.uk/id/eprint/10159070/1/brdf.pdf