Research map / 3D vision / Depth and stereo
Dual Band Thermal Videography: Separating Time-Varying Reflection and Emission Near Ambient Conditions
Sriram Narayanan, Mani Ramanagopal, Srinivasa Narasimhan
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add reconstruction loss via k2 (ablation) | uncalibrated dual-band optimization · Simulation, SNR sweep | temperature error reduction: 90.10% error reduction | Improved |
| add second-order smoothing loss (ablation) | uncalibrated dual-band optimization · Simulation, SNR sweep | temperature error reduction: 56.73% error reduction | Improved |
| add normalized Huber loss (ablation) | uncalibrated dual-band optimization · Simulation, SNR sweep | temperature error reduction: 11.31% error reduction | Improved |
| add explicit noise modeling terms (ablation) | uncalibrated dual-band optimization · Simulation, SNR sweep | temperature error reduction: 11.64% error reduction | Improved |
| use uncalibrated method instead of naive least squares | wineglass video · Wineglass video temperature | estimation error (%): 31.68% -> 1.72% | Improved |
| use uncalibrated method instead of BCP | coffee pot video · Coffee pot video temperature | estimation error (%): 6.62% -> 5.34% | Improved |
| use calibrated emissivity instead of uncalibrated estimation | dual-band separation · Wineglass versus coffee pot | estimation error (%): wineglass 1.72% -> 5.04%; coffee pot 5.34% -> 0.36% | Mixed |
| use spectral-library calibration instead of reflector method for low-emissivity materials | emissivity calibration · Chrome ball emissivity | emissivity (reference 0.1): 0.43 -> 0.12 | Improved |
| use calibration method instead of reflector method for high-emissivity materials | emissivity calibration · Blue paint, glass jar, wineglass | emissivity: blue paint 0.88 vs 0.88 | No clear effect |
| limit to scenes where background is uncorrelated with object signal | dual-band method · uniformly warming room | validity | Hurt |
Closest papers by meaning
- Time-Resolved Light Transport Decomposition for Thermal Photometric Stereo (CVPR 2018 · similarity 0.87)
- Time-Resolved Far Infrared Light Transport Decomposition for Thermal Photometric Stereo (TPAMI 2019 · similarity 0.87)
- PhysIR-Splat: Physically Consistent Thermal Infrared Radiative Transfer in 3D Gaussian Splatting (CVPR 2026 · similarity 0.86)
- A Theory of Joint Light and Heat Transport for Lambertian Scenes (CVPR 2024 · similarity 0.85)
- ThermalGaussian: Thermal 3D Gaussian Splatting (ICLR 2025 · similarity 0.85)
- NTR-Gaussian: Nighttime Dynamic Thermal Reconstruction with 4D Gaussian Splatting Based on Thermodynamics (CVPR 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
