eprintid: 10071737 rev_number: 28 eprint_status: archive userid: 608 dir: disk0/10/07/17/37 datestamp: 2019-04-05 15:54:07 lastmod: 2021-10-13 23:30:43 status_changed: 2019-10-22 15:47:29 type: article metadata_visibility: show creators_name: Rainer, G creators_name: Jakob, W creators_name: Ghosh, A creators_name: Weyrich, T title: Neural BTF Compression and Interpolation ispublished: pub divisions: UCL divisions: B04 divisions: C05 divisions: F48 note: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. abstract: The Bidirectional Texture Function (BTF) is a data‐driven solution to render materials with complex appearance. A typical capture contains tens of thousands of images of a material sample under varying viewing and lighting conditions. While capable of faithfully recording complex light interactions in the material, the main drawback is the massive memory requirement, both for storing and rendering, making effective compression of BTF data a critical component in practical applications. Common compression schemes used in practice are based on matrix factorization techniques, which preserve the discrete format of the original dataset. While this approach generalizes well to different materials, rendering with the compressed dataset still relies on interpolating between the closest samples. Depending on the material and the angular resolution of the BTF, this can lead to blurring and ghosting artefacts. An alternative approach uses analytic model fitting to approximate the BTF data, using continuous functions that naturally interpolate well, but whose expressive range is often not wide enough to faithfully recreate materials with complex non‐local lighting effects (subsurface scattering, inter‐reflections, shadowing and masking…). In light of these observations, we propose a neural network‐based BTF representation inspired by autoencoders: our encoder compresses each texel to a small set of latent coefficients, while our decoder additionally takes in a light and view direction and outputs a single RGB vector at a time. This allows us to continuously query reflectance values in the light and view hemispheres, eliminating the need for linear interpolation between discrete samples. We train our architecture on fabric BTFs with a challenging appearance and compare to standard PCA as a baseline. We achieve competitive compression ratios and high‐quality interpolation/extrapolation without blurring or ghosting artifacts. date: 2019-05 date_type: published publisher: Eurographics Association official_url: https://doi.org/10.1111/cgf.13633 oa_status: green full_text_type: other language: eng primo: open primo_central: open_green verified: verified_manual elements_id: 1644793 doi: 10.1111/cgf.13633 lyricists_name: Rainer, Gilles lyricists_name: Weyrich, Tim lyricists_id: GCRAI40 lyricists_id: TAWEY36 actors_name: Weyrich, Tim actors_id: TAWEY36 actors_role: owner full_text_status: public publication: Computer Graphics Forum (Proc. Eurographics) volume: 38 number: 2 pagerange: 235-244 citation: Rainer, G; Jakob, W; Ghosh, A; Weyrich, T; (2019) Neural BTF Compression and Interpolation. Computer Graphics Forum (Proc. Eurographics) , 38 (2) pp. 235-244. 10.1111/cgf.13633 <https://doi.org/10.1111/cgf.13633>. Green open access document_url: https://discovery.ucl.ac.uk/id/eprint/10071737/1/rainer19neural.pdf