Research map / Video / Video segmentation and tracking
SparkVSR: Interactive Video Super-Resolution via Sparse Keyframe Propagation
Jiongze Yu, Xiangbo Gao, Pooja Verlani, Akshay Gadde, Yilin Wang, Balu Adsumilli, Zhengzhong Tu
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 |
|---|---|---|---|
| raise reference-free guidance scale from 0 to 1.5 (Nano-Banana-Pro ref) (ablation) | SparkVSR · UDM10 | PSNR: 26.62 -> 20.89 | Hurt |
| raise reference-free guidance scale from 0.5 to 1.5 (Nano-Banana-Pro ref) (ablation) | SparkVSR · UDM10 | MUSIQ: 58.76 -> 68.36 | Improved |
| raise reference-free guidance scale from 0.5 to 1.5 (PiSA-SR ref) (ablation) | SparkVSR · UDM10 | MUSIQ: 60.17 -> 70.39 | Improved |
| raise reference-free guidance scale from 0.5 to 1.5 (PiSA-SR ref) (ablation) | SparkVSR · UDM10 | PSNR: 25.66 -> 20.94 | Hurt |
| raise reference-free guidance scale from 0.5 to 1.5 (Nano-Banana-Pro ref) (ablation) | SparkVSR · UDM10 | DOVER: 0.571 -> 0.746 | Improved |
| add pixel-space stage 2 after latent stage 1 (ablation) | SparkVSR · UDM10 | perceptual metrics | Improved |
| add pixel-space stage 2 after latent stage 1 (zero reference) (ablation) | SparkVSR · UDM10 | PSNR: 26.73 -> 26.62 | Mixed |
| add a single reference keyframe (ablation) | SparkVSR · MovieLQ | MUSIQ: 56.34 -> 61.73 | Improved |
| add more distributed reference frames (three uniform or four I-frames) (ablation) | SparkVSR · MovieLQ | perceptual quality | Improved |
| use Nano-Banana-Pro reference with the no-reference model | SparkVSR · UDM10 | DOVER: 0.5494 -> 0.6902 | Improved |
| use PiSA-SR reference with the no-reference model | SparkVSR · MovieLQ | MUSIQ: 56.34 -> 68.88 | Improved |
Closest papers by meaning
- FlashVSR: Towards Real-time Diffusion-Based Streaming Video Super Resolution (CVPR 2026 · similarity 0.91)
- BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond (CVPR 2021 · similarity 0.91)
- Investigating Tradeoffs in Real-World Video Super-Resolution (CVPR 2022 · similarity 0.90)
- Motion-Guided Latent Diffusion for Temporally Consistent Real-world Video Super-resolution (ECCV 2024 · similarity 0.90)
- Sequence Matters: Harnessing Video Models in 3D Super-Resolution (AAAI 2025 · similarity 0.89)
- SAVSR: Arbitrary-Scale Video Super-Resolution via a Learned Scale-Adaptive Network (AAAI 2024 · similarity 0.88)
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.
