# Light Stage Super-Resolution: Continuous High-Frequency Relighting

arXiv: https://arxiv.org/abs/2010.08888 · HTML: https://mlsanity.com/paper/2010.08888/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Oct 2020.

## Built on by (most cited first, 20 of 20)

- [Point-Based Neural Rendering with Per-View Optimization](https://mlsanity.com/paper/2109.02369/) (2021)
- [Im4D: High-Fidelity and Real-Time Novel View Synthesis for Dynamic Scenes](https://mlsanity.com/paper/2310.08585/) (2023)
- [ReLight My NeRF: A Dataset for Novel View Synthesis and Relighting of Real World Objects](https://mlsanity.com/paper/2304.10448/) (2023)
- [Relighting Neural Radiance Fields with Shadow and Highlight Hints](https://mlsanity.com/paper/2308.13404/) (2023)
- [Neural Radiance Transfer Fields for Relightable Novel-view Synthesis with Global Illumination](https://mlsanity.com/paper/2207.13607/) (2022)
- [NeLF: Neural Light-transport Field for Portrait View Synthesis and Relighting](https://mlsanity.com/paper/2107.12351/) (2021)
- [Towards Practical Capture of High-Fidelity Relightable Avatars](https://mlsanity.com/paper/2309.04247/) (2023)
- [Curriculum Learning for ab initio Deep Learned Refractive Optics](https://mlsanity.com/paper/2302.01089/) (2023)
- [SunStage: Portrait Reconstruction and Relighting using the Sun as a Light Stage](https://mlsanity.com/paper/2204.03648/) (2022)
- [OutCast: Outdoor Single-image Relighting with Cast Shadows](https://mlsanity.com/paper/2204.09341/) (2022)
- [SynthLight: Portrait Relighting with Diffusion Model by Learning to Re-render Synthetic Faces](https://mlsanity.com/paper/2501.09756/) (2025)
- [A Light Stage on Every Desk](https://mlsanity.com/paper/2105.08051/) (2021)
- [RelightableHands: Efficient Neural Relighting of Articulated Hand Models](https://mlsanity.com/paper/2302.04866/) (2023)
- [Relightable Neural Human Assets from Multi-view Gradient Illuminations](https://mlsanity.com/paper/2212.07648/) (2022)
- [BareSkinNet: De-makeup and De-lighting via 3D Face Reconstruction](https://mlsanity.com/paper/2209.09029/) (2022)
- [3DPR: Single Image 3D Portrait Relight using Generative Priors](https://mlsanity.com/paper/2510.15846/) (2025)
- [Single-sample image-fusion upsampling of fluorescence lifetime images](https://mlsanity.com/paper/2404.13102/) (2024)
- [Fovea Stacking: Imaging with Dynamic Localized Aberration Correction](https://mlsanity.com/paper/2506.00716/) (2025)
- [Learning a Delighting Prior for Facial Appearance Capture in the Wild](https://mlsanity.com/paper/2605.05636/) (2026)
- [Pixel Cube: Diffusion-based Portrait Video Relighting Through Realistic Lighting Reproduction](https://mlsanity.com/paper/2606.02919/) (2026)

## Abstract (arXiv)

The light stage has been widely used in computer graphics for the past two decades, primarily to enable the relighting of human faces. By capturing the appearance of the human subject under different light sources, one obtains the light transport matrix of that subject, which enables image-based relighting in novel environments. However, due to the finite number of lights in the stage, the light transport matrix only represents a sparse sampling on the entire sphere. As a consequence, relighting the subject with a point light or a directional source that does not coincide exactly with one of the lights in the stage requires interpolation and resampling the images corresponding to nearby lights, and this leads to ghosting shadows, aliased specularities, and other artifacts. To ameliorate these artifacts and produce better results under arbitrary high-frequency lighting, this paper proposes a learning-based solution for the "super-resolution" of scans of human faces taken from a light stage. Given an arbitrary "query" light direction, our method aggregates the captured images corresponding to neighboring lights in the stage, and uses a neural network to synthesize a rendering of the face that appears to be illuminated by a "virtual" light source at the query location. This neural network must circumvent the inherent aliasing and regularity of the light stage data that was used for training, which we accomplish through the use of regularized traditional interpolation methods within our network. Our learned model is able to produce renderings for arbitrary light directions that exhibit realistic shadows and specular highlights, and is able to generalize across a wide variety of subjects.