All‐frequency Full‐body Human Image Relighting

• DOI: 10.1111/cgf.70007
• Publication Date: 2025-04-08T05:52:11Z
• Authors: D. Tajima; Y. Kanamori; Y. Endo
• Keywords: Human body

Abstract Relighting of human images enables post‐photography editing lighting effects in portraits. The current mainstream approach uses neural networks to approximate without explicitly accounting for the principle physical shading. As a result, it often has difficulty representing high‐frequency shadows and In this paper, we propose two‐stage relighting method that can reproduce physically‐based shading from low high frequencies. key idea is an environment light source with set fixed number area sources. first stage employs supervised inverse rendering single image using calculates second then shadow each sums up render final image. We make soft mapping differentiable area‐light approximation lighting. demonstrate our plausibly all‐frequency caused by illumination, which have been difficult existing methods.