SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.11686 · CVPR · 2023

Learning a 3D Morphable Face Reflectance Model from Low-cost Data

Yuxuan Han, Feng Xu, Zhibo Wang

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Linear Combination Weights for Different Specular Exponents Figure 1. We propose the first 3D morphable face reflectance model with spatially varying BRDF and a technique to train the model with low-cost publicly-available data. We represent face reflectance as a Lambertian BRDF combined with the linear combination of Blinn-Phong BRDFs with different predefined specular exponents. The reflectance parameters for each face vertex are the diffuse albedo and a set of weights. We show the first 3 principal components of diffuse albedo and spatially varying weights here in nonlinear sRGB space.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2303.11686")
get_code_for_paper("2303.11686")
have("2303.11686")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2303.11686.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2303.11686.svg)](https://syntology.ai/paper/2303.11686)

Connect an agent — have() is free.