Presenters
Carnegie Mellon University
Carnegie Mellon University
Description
This short course explores how heat and light work together across Vision, Imaging, and Simulation domains. These phenomena are fundamentally coupled — absorbed light heats materials, while hotter objects radiate more thermal energy as infrared light — yet computer vision and imaging typically ignore heat, while engineering focuses only on thermal effects without considering light.
We show how accounting for both heat and light opens new possibilities. Measuring absorbed light intensity enables solving image analysis problems that were previously impossible. Heat flow patterns reveal object shapes. Multi-spectral thermal cameras can separate what objects reflect versus what they emit. These applications rely on thermal cameras that operate fundamentally differently from visible light cameras — using bolometric rather than photoelectric sensing — creating unique challenges in motion deblurring and noise modeling that we address.
These new vision and imaging capabilities demand equally novel simulation tools. The simulation component introduces Monte Carlo methods for thermal phenomena, showing how walk-on-spheres algorithms enable grid-free heat conduction simulation on complex geometry. These methods work together to handle both light and heat processes, enabling complete thermal simulation with potential applications in hardware design, synthetic dataset generation, and real-world scene analysis.
This course targets computer vision, graphics, and imaging researchers wanting to work beyond visible light. Participants will learn basic theory and practical techniques for heat-light interactions, understanding state-of-the-art developments and opening new research directions at the intersection of thermal vision, imaging, and physics-based simulation.
Agenda
Times are approximate. Slides for each course section are available below.
| Time (PT) | Topic | Presenter |
|---|---|---|
| 4:00 - 4:10 pm | What is Light and Heat? Why study it? | Mani Ramanagopal |
| 4:10 - 4:40 pm | Vision with Heat and Light | Mani Ramanagopal |
| 4:40 - 4:55 pm | Physics of Thermal Imaging | Mani Ramanagopal |
| 4:55- 5:25 pm | Monte Carlo Thermal Simulation | Bailey Miller |
| 5:25 - 5:45 pm | Conclusion and Q & A | Mani Ramanagopal |
Slides
PDF version of the slides used in the course are available here. The archival copy of the course notes are available on the ACM Digital Library.
Quiz
A mini-quiz to test your learning is available here.
References
The following is a list of references to papers we highlight in each section of the course. It is not an exhaustive, or even representative, bibliography for the corresponding research areas. For pointers to additional resources, we recommend perusing the bibliography of these references.
Background
- Infrared Thermal Imaging: Fundamentals, Research and Applications
Michael Vollmer, Klaus-Peter Möllmann
Vision with Heat and Light
- A Theory of Joint Light and Heat Transport for Lambertian Scenes
Mani Ramanagopal, Sriram Narayanan, Aswin C. Sankaranarayanan, Srinivasa G. Narasimhan
CVPR 2024 - Shape from Heat Conduction
Sriram Narayanan, Mani Ramanagopal, Mark Sheinin, Aswin C. Sankaranarayanan, Srinivasa G. Narasimhan
ECCV 2024 - Resolving Shape Ambiguities using Heat Conduction and Shading
Akihiko Oharazawa, Sriram Narayanan, Mani Ramanagopal, Srinivasa G. Narasimhan
ICCP 2025 - Physics-Based Decomposition of Reflectance and Shading using a Single Visible-Thermal Image Pair
Zeqing Leo Yuan, Mani Ramanagopal, Aswin C. Sankaranarayanan, Srinivasa G. Narasimhan - Dual Band Video Thermography Near Ambient Conditions
Sriram Narayanan, Mani Ramanagopal, Srinivasa G. Narasimhan
Physics of Thermal Imaging
- Pixel-Wise Motion Deblurring of Thermal Videos
Mani Ramanagopal, Zixu Zhang, Ram Vasudevan, Matthew Johnson-Roberson
RSS 2020 - TRNeRF: Restoring Blurry, Rolling Shutter, and Noisy Thermal Images with Neural Radiance Fields
Spencer Carmichael, Manohar Bhat, Mani Ramanagopal, Austin Buchan, Ram Vasudevan, Katherine A. Skinner
WACV 2025
Monte Carlo Thermal Simulation
- Monte Carlo Geometry Processing: A Grid-Free Approach to PDE-Based Methods on Volumetric Domains
Rohan Sawhney, Keenan Crane
ACM Transactions on Graphics (SIGGRAPH), 2020 - Grid-free Monte Carlo for PDEs with spatially varying coefficients
Rohan Sawhney, Dario Seyb, Wojciech Jarosz, Keenan Crane
ACM Transactions on Graphics (SIGGRAPH), 2022 - Walk on Stars: A Grid-Free Monte Carlo Method for PDEs with Neumann Boundary Conditions
Rohan Sawhney, Bailey Miller, Ioannis Gkioulekas, Keenan Crane
ACM Transactions on Graphics (SIGGRAPH), 2023 - Walkin' Robin: Walk on Stars with Robin Boundary Conditions
Bailey Miller, Rohan Sawhney, Keenan Crane, Ioannis Gkioulekas
ACM Transactions on Graphics (SIGGRAPH), 2024 - Coupling Conduction, Convection and Radiative Transfer in a Single Path-Space: Application to Infrared Rendering
Mégane Bati, Stéphane Blanco, Christophe Coustet, Vincent Eymet, Vincent Forest, Richard Fournier, Jacques Gautrais, Nicolas Mellado, Mathias Paulin, Benjamin Piaud
ACM Transactions on Graphics (SIGGRAPH), 2023 - A Differential Monte Carlo Solver For the Poisson Equation
Zihan Yu, Lifan Wu, Zhiqian Zhou, Shuang Zhao
ACM Transactions on Graphics (SIGGRAPH), 2024 - Differential walk on spheres
Bailey Miller, Rohan Sawhney, Keenan Crane, Ioannis Gkioulekas
ACM Transactions on Graphics (SIGGRAPH Asia), 2024 - Solving Inverse PDE Problems using Grid-Free Monte Carlo Estimators
Ekrem Fatih Yilmazer, Delio Vicini, Wenzel Jakob
ACM Transactions on Graphics (SIGGRAPH Asia), 2024
Sponsors
The research presented in this course was supported in part by the NSF-NIFA AI Institute of Resilient Agriculture (AIIRA), National Institute of Food and Agriculture (2023-67021-39073), Alfred P. Sloan Foundation (FG202013153), Packard Fellowship, NSF (IIS-2107236, 2504890, 2212290, 1943123, 1900849, 2008123, DGE2140739), Nvidia Graduate Research Fellowship, Tata Consultancy Services Presidential Fellowship, Ford Motor Company via the Ford-UM Alliance (N022884), and gifts from Adobe Systems, nTopology, and Disney Research.