Highlight-aware two-stream network for single-image SVBRDF acquisition

J Guo, S Lai, C Tao, Y Cai, L Wang, Y Guo… - ACM Transactions on …, 2021 - dl.acm.org
This paper addresses the task of estimating spatially-varying reflectance (ie, SVBRDF) from
a single, casually captured image. Central to our method is a highlight-aware (HA) …

Ultra-high resolution svbrdf recovery from a single image

J Guo, S Lai, Q Tu, C Tao, C Zou, Y Guo - ACM Transactions on Graphics, 2023 - dl.acm.org
Existing convolutional neural networks have achieved great success in recovering Spatially
Varying Bidirectional Surface Reflectance Distribution Function (SVBRDF) maps from a …

Deep Reflectance Scanning: Recovering Spatially‐varying Material Appearance from a Flash‐lit Video Sequence

W Ye, Y Dong, P Peers, B Guo - Computer Graphics Forum, 2021 - Wiley Online Library
In this paper we present a novel method for recovering high‐resolution spatially‐varying
isotropic surface reflectance of a planar exemplar from a flash‐lit close‐up video sequence …

NeuBTF: Neural fields for BTF encoding and transfer

C Rodriguez-Pardo, K Kazatzis, J Lopez-Moreno… - Computers & …, 2023 - Elsevier
Neural material representations are becoming a popular way to represent materials for
rendering. They are more expressive than analytic models and occupy less memory than …

Neural photometry-guided visual attribute transfer

C Rodriguez-Pardo, E Garces - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
We present a deep learning-based method for propagating spatially-varying visual material
attributes (eg, texture maps or image stylizations) to larger samples of the same or similar …

Shape from tracing: Towards reconstructing 3d object geometry and svbrdf material from images via differentiable path tracing

P Goel, L Cohen, J Guesman… - … Conference on 3D …, 2020 - ieeexplore.ieee.org
Reconstructing object geometry and material from multiple views typically requires
optimization. Differentiable path tracing is an appealing framework as it can reproduce …

Progressive acquisition of svbrdf and shape in motion

H Ha, SH Baek, G Nam, MH Kim - Computer Graphics Forum, 2020 - Wiley Online Library
To estimate appearance parameters, traditional SVBRDF acquisition methods require
multiple input images to be captured with various angles of light and camera, followed by a …

New approach of 3D for monumental heritage

C Cou - 2023 - hal.science
The subject of the thesis consists in develo** a new vision of 3D for monumental heritage.
It is both to respond to questions in the art history by incorporating enriched visual …

Estimating homogeneous data-driven BRDF parameters from a reflectance map under known natural lighting

VL Cooper, JC Bieron, P Peers - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
In this article we demonstrate robust estimation of the model parameters of a fully-linear data-
driven BRDF model from a reflectance map under known natural lighting. To regularize the …

On-Site Single Image Svbrdf Reconstruction with Active Planar Lighting

L Zhang, R Sun, L Wang, F Gao, Z Wang… - Available at SSRN … - papers.ssrn.com
Recovering the spatially-varying bidirectional reflectance distribution function (SVBRDF)
from a single image in uncontrolled environments is challenging while essential for various …