# Geometry-Driven Shadow Harmonisation for Composited Faces: A Multiplicative, Albedo-Preserving Relighting Pipeline

arXiv: https://arxiv.org/abs/2609.17740 · HTML: https://mlsanity.com/paper/2609.17740/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 13 references that are in the map.
- First posted on arXiv 15 Sep 2026.

## Builds on (most cited first, 5 of 5)

- [Single Image Portrait Relighting](https://mlsanity.com/paper/1905.00824/) (2019)
- [DoveNet: Deep Image Harmonization via Domain Verification](https://mlsanity.com/paper/1911.13239/) (2019)
- [Deep Image Harmonization](https://mlsanity.com/paper/1703.00069/) (2017)
- [SfSNet: Learning Shape, Reflectance and Illuminance of Faces in the Wild](https://mlsanity.com/paper/1712.01261/) (2017)
- [Real-time Facial Surface Geometry from Monocular Video on Mobile GPUs](https://mlsanity.com/paper/1907.06724/) (2019)

## Built on by (most cited first, 1 of 1)

- [The Skin-Restricted Reinhard Transform:Uniqueness under a Lightness-Preserving Constraint](https://mlsanity.com/paper/2609.28424/) (2026)

## Abstract (arXiv)

Face swapping and face compositing pipelines routinely produce a face that is geometrically well aligned but photometrically implausible: the donor face carries flat, near-frontal studio illumination while the host body and background carry directional scene light. Most existing remedies re-synthesise the face through colour transfer, neural relighting, or inverse rendering, and therefore risk altering identity, skin tone, and texture. We present a conservative alternative: geometry-driven form-shadow injection. The pipeline never repaints the face. It estimates a per-pixel gain field g∈[gmin,1] from a rasterised 3D face proxy and multiplies it channel-uniformly onto linear RGB, so the operator can only darken and cannot shift chromaticity. A dense landmark mesh is rasterised into a depth buffer, from which we derive surface normals, a cavity term, and screen-space cast shadows. Key-light direction is estimated from host-side cues (body, background, hair halo); on-face cues are downweighted because they recover the donor's lighting. Shadow magnitude is not matched to the host: it is set by a three-parameter transfer (τ,σ,gmin). The shading field is divided by its 75th percentile over skin, then gated, scaled, clamped, smoothed, and re-clipped inside a feathered, skin-gated face mask. On an analytic face heightfield, the default (τ,σ,gmin)=(0.90,0.45,0.82) modifies 56.5% of face pixels with mean gain 0.938 (0.890 on modified pixels) and drives 3.4% of pixels to the floor. Hue invariance is a corollary of the operator. We analyse the transfer in closed form, ablate its parameters, and discuss failure modes of a monotone, darkening-only formulation, including double-shadowing of non-flat donors.