Towards Racially Unbiased Skin Tone Estimation via Scene Disambiguation

Feng, Haiwen; Bolkart, Timo; Tesch, Joachim; Black, Michael J.; Abrevaya, Victoria Fernández

doi:10.1007/978-3-031-19778-9_5

Cited by 13 publications

(1 citation statement)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is also difficult to address with a learning framework due to the extreme scarcity of realistic labeled data and infinite possible lighting conditions for a scene. In the context of portrait relighting, it means recovering the true skin tone of a portrait subject is very challenging [12,49]. Instead of trying to collect a balanced large-scale light-stage [8] dataset to capture the continuous and subtle variations in different skin tones, we propose an alternative solution dubbed SkinFill.…”

Section: Introductionmentioning

confidence: 99%

LightPainter: Interactive Portrait Relighting with Freehand Scribble

Mei¹,

Zhang²,

Xuaner³

et al. 2023

Preprint

View full text Add to dashboard Cite

Recent portrait relighting methods have achieved realistic results of portrait lighting effects given a desired lighting representation such as an environment map. However, these methods are not intuitive for user interaction and lack precise lighting control. We introduce LightPainter, a scribble-based relighting system that allows users to interactively manipulate portrait lighting effect with ease. This is achieved by two conditional neural networks, a delighting module that recovers geometry and albedo optionally conditioned on skin tone, and a scribble-based module for relighting. To train the relighting module, we propose a novel scribble simulation procedure to mimic real user scribbles, which allows our pipeline to be trained without any human annotations. We demonstrate high-quality and flexible portrait lighting editing capability with both quantitative and qualitative experiments. User study comparisons with commercial lighting editing tools also demonstrate consistent user preference for our method.

show abstract

Section: Introductionmentioning

confidence: 99%