Mani Ramanagopal
Postdoc · Carnegie Mellon University
Heat as a carrier of visual information: thermal computational imaging and physics-based vision.
- CVPR 2026 Oral · Award Candidate
- ECCV 2024 Oral
- IEEE RA-L Best Paper
ORCID DBLP Semantic Scholar OpenReview
Also published as Manikandasriram Srinivasan Ramanagopal
I'm a postdoc at Carnegie Mellon University, working with Prof. Srinivasa Narasimhan and Prof. Aswin Sankaranarayanan. My research explores heat as a carrier of visual information. I develop novel vision and imaging systems that leverage the ubiquitous interplay of light and heat all around us.
Previously, I obtained my Ph.D. and M.S. in Robotics from the University of Michigan, where I was advised by Prof. Matthew Johnson-Roberson and Prof. Ram Vasudevan. My doctoral research explored the physics of image formation in thermal cameras and the use of novel sensors for autonomous vehicles.
Prior to my Ph.D., I earned my B.Tech and M.Tech in Electrical Engineering from the Indian Institute of Technology, Madras. During my undergraduate studies, I spent a summer at Polytechnique Montréal, Canada, working with Prof. Jerome Le Ny on motion planning algorithms for autonomous mapping of ground structures, through the Mitacs Globalink Research Internship.
Publications
2026
Temporal derivative
Revealing Subtle Heat Flows all around us using Microbolometric Videos
Conditionally Accepted
Dual Band Thermal Videography: Separating Time-Varying Reflection and Emission Near Ambient Conditions
Oral and Award Candidate (74 out of 4072 accepted)
VT-Intrinsic: Physics-Based Decomposition of Reflectance and Shading using a Single Visible-Thermal Image Pair
2025
Resolving Shape Ambiguities using Heat Conduction and Shading
RT-X Net: RGB-Thermal cross attention network for Low-Light Image Enhancement
Dataset and benchmark: Novel sensors for autonomous vehicle perception
TRNeRF: Restoring Blurry, Rolling Shutter, and Noisy Thermal Images with Neural Radiance Fields
2024
Shape from heat conduction
Oral (200 out of 2387 accepted)
A theory of joint light and heat transport for lambertian scenes
2023
LONER: LiDAR Only Neural Representations for Real-Time SLAM
IEEE RAL Best Paper Award
Waternerf: Neural radiance fields for underwater scenes
CLONeR: Camera-Lidar Fusion for Occupancy Grid-Aided Neural Representations
2020
Pixel-wise motion deblurring of thermal videos
Listereo: Generate dense depth maps from lidar and stereo imagery
2019
Pedx: Benchmark dataset for metric 3-d pose estimation of pedestrians in complex urban intersections
2018
Failing to learn: Autonomously identifying perception failures for self-driving cars
Toward real-time autonomous target area protection: Theory and implementation
2017
