# Relighting Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/relighting
> Markdown URL: https://aitinkerers.org/technologies/relighting.md
> Technology record last updated: 2026-03-05T10:04:22Z
> Generated: 2026-09-21T15:53:00Z

Relighting is the post-capture process of digitally manipulating a photograph's illumination (direction, color, intensity) with the precision of a 3D computer graphics pipeline.

This technology fundamentally decouples light from the image content, enabling full illumination control after the shot. The cutting-edge approach, as demonstrated by the Simon Fraser University team at SIGGRAPH 2025, combines mid-level computer vision, physically-based rendering, and a neural renderer to achieve photorealistic results. The pipeline first infers a colored mesh representation of the scene, allowing users to define new lighting configurations (e.g., spotlights, environment maps) in 3D. This brings the explicit, physical control of a tool like Blender directly into 2D photo editing, a capability that traditional software like Photoshop lacked.

- Official technology site: https://yaksoy.github.io/PhysicalRelighting/
- Public AI Tinkerers demos and talks: 2
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Your Webcam Knows the Geometry - Real-Time Relighting & Single-Shot Novel Views](https://lausanne.aitinkerers.org/talks/rsvp_cMMuinG2WV4)

Two single-view inverse-rendering systems that reconstruct scene geometry from one camera and re-render it under conditions never captured — one changes the light, the other changes the viewpoint, both fast enough to ship. The Relighting part decomposes a live webcam frame into geometry + material (normals/albedo/shading) and re-renders it under any lighting in real time (~24 FPS), showcasing a variety of lighting conditions (multiple colored lights, orbiting and rainbow-rotating lights) The Novel View Synthesis builds a 3D representation of the scene using Gaussian Splatting and renders it from a different angle. It currently runs at 5 FPS but we are hoping to get closer to real time soon.

- Event context: AI Tinkerers Lausanne June 2026 Meetup — 2026-06-25 — Lausanne
- Public talk page: https://lausanne.aitinkerers.org/talks/rsvp_cMMuinG2WV4

### [AI Video Relighting](https://denver-boulder.aitinkerers.org/talks/rsvp_uUhYbhfSe_I)

We use AI to relight the subject of a video to match an Unreal Engine virtual environment.

- Event context: AI Tinkerers Denver - January Meetup — 2024-01-18 — Denver
- Public talk page: https://denver-boulder.aitinkerers.org/talks/rsvp_uUhYbhfSe_I

## Related Technologies

- [PyTorch](https://aitinkerers.org/technologies/pytorch) ([Markdown](https://aitinkerers.org/technologies/pytorch.md)) — 273 public demos
- [BERT](https://aitinkerers.org/technologies/bert) ([Markdown](https://aitinkerers.org/technologies/bert.md)) — 179 public demos
- [Data](https://aitinkerers.org/technologies/data) ([Markdown](https://aitinkerers.org/technologies/data.md)) — 8 public demos
- [Diffusion](https://aitinkerers.org/technologies/diffusion) ([Markdown](https://aitinkerers.org/technologies/diffusion.md)) — 2 public demos
- [DINOv3](https://aitinkerers.org/technologies/dinov3) ([Markdown](https://aitinkerers.org/technologies/dinov3.md)) — 1 public demo
- [DINOv3-ConvNext](https://aitinkerers.org/technologies/dinov3-convnext) ([Markdown](https://aitinkerers.org/technologies/dinov3-convnext.md)) — 1 public demo
- [Gaussian Splatting](https://aitinkerers.org/technologies/gaussian-splatting) ([Markdown](https://aitinkerers.org/technologies/gaussian-splatting.md)) — 5 public demos
- [GPT-3](https://aitinkerers.org/technologies/gpt-3) ([Markdown](https://aitinkerers.org/technologies/gpt-3.md)) — 191 public demos
- [GPT-4](https://aitinkerers.org/technologies/gpt-4) ([Markdown](https://aitinkerers.org/technologies/gpt-4.md)) — 529 public demos
- [Inference](https://aitinkerers.org/technologies/inference) ([Markdown](https://aitinkerers.org/technologies/inference.md)) — 9 public demos
- [Keras](https://aitinkerers.org/technologies/keras) ([Markdown](https://aitinkerers.org/technologies/keras.md)) — 74 public demos
- [ONNX](https://aitinkerers.org/technologies/onnx) ([Markdown](https://aitinkerers.org/technologies/onnx.md)) — 83 public demos
- [OpenCV](https://aitinkerers.org/technologies/opencv) ([Markdown](https://aitinkerers.org/technologies/opencv.md)) — 26 public demos
- [OpenGL](https://aitinkerers.org/technologies/opengl) ([Markdown](https://aitinkerers.org/technologies/opengl.md)) — 2 public demos
- [scikit-learn](https://aitinkerers.org/technologies/scikit-learn) ([Markdown](https://aitinkerers.org/technologies/scikit-learn.md)) — 84 public demos
- [Sharp](https://aitinkerers.org/technologies/sharp) ([Markdown](https://aitinkerers.org/technologies/sharp.md)) — 2 public demos
- [Skyglass](https://aitinkerers.org/technologies/skyglass) ([Markdown](https://aitinkerers.org/technologies/skyglass.md)) — 2 public demos
- [TensorFlow](https://aitinkerers.org/technologies/tensorflow) ([Markdown](https://aitinkerers.org/technologies/tensorflow.md)) — 90 public demos