Research map / Video / Video segmentation and tracking
Diffusion-Based Extreme High-speed Scenes Reconstruction with the Complementary Vision Sensor
Yapeng Meng, Yihan Lin, Taoyi Wang, Yuguo Chen, Lijian Wang, Rong Zhao
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 temporal difference (TD) input on top of RGB and SD (ablation) | CBRDM single-stage baseline · SportsSlomo | PSNR: 21.98 -> 23.92 | Improved |
| add spatial difference (SD) input on top of RGB and TD (ablation) | CBRDM single-stage baseline · SportsSlomo | PSNR: 23.65 -> 23.92 | Improved |
| add both TD and SD inputs to RGB-only conditioning (ablation) | CBRDM single-stage baseline · SportsSlomo | LPIPS: 0.2190 -> 0.0994 | Improved |
| add bi-directional recurrent block (BRB) for temporal awareness (ablation) | CBRDM · SportsSlomo | PSNR: 23.92 -> 24.36 | Improved |
| replace BRB with temporal conv-attention block (TCAB) (ablation) | CBRDM · SportsSlomo | LPIPS: 0.0806 -> 0.0897 | Hurt |
| use BRB instead of TCAB (parameters) (ablation) | CBRDM · SportsSlomo | parameters: 249.88M -> 166.18M | Improved |
| use CBRDM instead of RGB-only interpolation methods | CBRDM vs AMT · GoPro | PSNR: 21.74 -> 27.65 | Improved |
| use clean-RGB only-interpolation mode for the baselines | AMT · GoPro | PSNR: 21.74 -> 21.17 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- LDMVFI — LDMVFI: Video Frame Interpolation with Latent Diffusion Models (AAAI 2024) · better on 3 of 3 shared results
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
- High Speed and High Dynamic Range Video with an Event Camera (TPAMI 2019 · similarity 0.89)
- Learning To Reconstruct High Speed and High Dynamic Range Videos From Events (CVPR 2021 · similarity 0.89)
- Spatio-Temporal Difference Guided Motion Deblurring with the Complementary Vision Sensor (CVPR 2026 · similarity 0.89)
- Color-Encoded Illumination for High-Speed Volumetric Scene Reconstruction (CVPR 2026 · similarity 0.88)
- Event based Multi-Velocity-Scale Imaging (NeurIPS 2026 · similarity 0.88)
- High-Resolution Frame Interpolation with Patch-based Cascaded Diffusion (AAAI 2025 · similarity 0.86)
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.
