Towards High Fidelity Monocular Face Reconstruction with Rich Reflectance using Self-supervised Learning and Ray Tracing

Christian Theobalt, Abdallah Dib, Cédric Thébault, Junghyun Ahn, Philippe-Henri Gosselin, Louis Chevallier, Interdigital R&i

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. If it links a repository, it is listed below.

Abstract

Figure 1. A deep neural network trained in a self-supervised manner with a differentiable ray tracer estimates a complete set of facial attributes -3D head pose, geometry, personalized albedo (diffuse and specular) from unconstrained monocular image. Reconstruction based on these attributes enables a variety of applications, such as relighting.

For agents

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

get_harvested_code_for_paper("2103.15432")
get_code_for_paper("2103.15432")
have("2103.15432")

Connect an agent — have() is free.