Research map / Video / Video segmentation and tracking
Thermal Diffusion Matters: Infrared Spatial-Temporal Video Super-Resolution through Heat Conduction Priors
Mingxuan Zhou, Shuang Li, Yutang Zhang, Jing Geng, Yirui Shen, Jingxuan Kang, Fuzhen Zhuang, Shuigen Wang
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 learnable spectral mask in TSSM (ablation) | THERIS · IRVAL | PSNR: 19.86 -> 21.37 | Improved |
| add thermal prompt (TDIM time embeddings) to TSSM (ablation) | THERIS · IRVAL | PSNR: 20.54 -> 21.37 | Improved |
| add Temperature Field Modeling loss (ablation) | THERIS · IRVAL | PSNR: 20.81 -> 21.37 | Improved |
| add Temperature Field Modeling loss (ablation) | THERIS · IRVAL | MUSIQ: 53.99 -> 55.59 | Improved |
| use THERIS instead of the best STVSR baseline | BF-STVSR · IRVAL | PSNR: 20.18 -> 21.37 | Improved |
| use THERIS instead of best baseline | TMNet · SGMP | PSNR: 37.54 -> 37.83 | Improved |
| use THERIS super-resolved frames for pedestrian detection | YOLO on LLVIP · LLVIP | mAP@0.5:0.95: 47.4 (BF-STVSR) -> 50.7 | Improved |
| use TDIM alone for interpolation (without TSSM) (ablation) | THERIS · IRVAL | qualitative | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- BF-STVSR — BF-STVSR: B-Splines and Fourier---Best Friends for High Fidelity Spatial-Temporal Video Super-Resolution (CVPR 2025) · better on 9 of 9 shared results
- MoTIF — MoTIF: Learning Motion Trajectories with Local Implicit Neural Functions for Continuous Space-Time Video Super-Resolution (ICCV 2023) · better on 1 of 1 shared result
- VideoINR — VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolution (CVPR 2022) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- HATIR: Heat-Aware Diffusion for Turbulent Infrared Video Super-Resolution (AAAI 2026 · similarity 0.89)
- Thermal-Physics Guided Infrared Image Super-Resolution with Dynamic High-Frequency Amplification (AAAI 2026 · similarity 0.88)
- Toward Real-world Infrared Image Super-Resolution: A Unified Autoregressive Framework and Benchmark Dataset (CVPR 2026 · similarity 0.88)
- DifIISR: A Diffusion Model with Gradient Guidance for Infrared Image Super-Resolution (CVPR 2025 · similarity 0.87)
- ThermalGaussian: Thermal 3D Gaussian Splatting (ICLR 2025 · similarity 0.84)
- Enhancing Infrared Vision: Progressive Prompt Fusion Network and Benchmark (NeurIPS 2025 · similarity 0.84)
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.
