• Corpus ID: 243848018

Neural BRDFs: Representation and Operations

  title={Neural BRDFs: Representation and Operations},
  author={Jiahui Fan and Beibei Wang and Milos Hasan and Jian Yang and Ling-Qi Yan},
JIAHUI FAN, School of Computer Science and Engineering, Nanjing University of Science and Technology, China BEIBEI WANG†, School of Computer Science and Engineering, Nanjing University of Science and Technology, China MILOŠ HAŠAN, Adobe Research, USA JIAN YANG†, School of Computer Science and Engineering, Nanjing University of Science and Technology, China LING-QI YAN, University of California, Santa Barbara, USA 



Neural Complex Luminaires: Representation and Rendering

JUNQIU ZHU, Shandong University, China YAOYI BAI, University of California, Santa Barbara, USA ZILIN XU, Shandong University, China STEVE BAKO, University of California, Santa Barbara, USA EDGAR

Neural Importance Sampling

This work introduces piecewise-polynomial coupling transforms that greatly increase the modeling power of individual coupling layers and derives a gradient-descent-based optimization for the Kullback-Leibler and the χ2 divergence for the specific application of Monte Carlo integration with unnormalized stochastic estimates of the target distribution.

Neural BRDF Representation and Importance Sampling

This work proposes a compact neural network-based representation of BRDF data that combines high-accuracy reconstruction with efficient practical rendering via built-in interpolation of reflectance, and encode BRDFs as lightweight networks, and proposes a training scheme with adaptive angular sampling.

Out-of-core tensor approximation of multi-dimensional matrices of visual data

Experimental results indicate that the techniques in this paper can not only process out-of-core data, but also achieve higher compression ratios and quality than previous methods.

Material Classification Based on Training Data Synthesized Using a BTF Database

This work presents a high-quality BTF database with 22,801 densely measured view-light configurations including surface geometry measurements for each of the 84 measured material samples, and demonstrates that the synthesized data allows classifying materials under complex real-world scenarios.

Neural scene graph rendering

A neural scene graph---a modular and controllable representation of scenes with elements that are learned from data, which demonstrates a precise control over the learned object representations in a number of animated 2D and 3D scenes.

Acquisition , Compression , and Synthesis of Bidirectional Texture Functions

This work uses image based techniques to analyze and represent bidirectional texture functions, or BTFs, with correct geometric and lighting effects as the lighting or viewpoint in a scene changes.

BTF Compression via Sparse Tensor Decomposition

A novel compression technique for Bidirectional Texture Functions based on a sparse tensor decomposition using the K‐SVD algorithm along two different modes of a tensor to decompose it into a small dictionary and two sparse tensors.

Neural BTF Compression and Interpolation

A neural network‐based BTF representation inspired by autoencoders is proposed: the encoder compresses each texel to a small set of latent coefficients, while the decoder additionally takes in a light and view direction and outputs a single RGB vector at a time, eliminating the need for linear interpolation between discrete samples.

Deferred Neural Rendering: Image Synthesis using Neural Textures

This work proposes Neural Textures, which are learned feature maps that are trained as part of the scene capture process that can be utilized to coherently re-render or manipulate existing video content in both static and dynamic environments at real-time rates.