Research map / Image generation / Super-resolution
Achieving On-Mobile Real-Time Super-Resolution With Neural Architecture and Pruning Search
Zheng Zhan, Yifan Gong, Pu Zhao, Geng Yuan, Wei Niu, Yushu Wu, Tianyun Zhang, Malith Jayaweera, David Kaeli, Bin Ren, Xue Lin, Yanzhi 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 pruning search to architecture search (ablation) | searched x2 SR model · Set5 x2 (Samsung S20) | FPS: 1.82 FPS for architecture search only; pruning search lifts speed to real-time (over 20 FPS at t = 50ms) | Improved |
| add pruning search to architecture search (ablation) | searched x2 SR model · Set5 x2 | PSNR (dB): 37.84 -> 37.81 | Hurt |
| add architecture search before pruning search (ablation) | WDSR blocks with pruning (t = 150ms) · Set5 x2 | PSNR (dB): 37.40 -> 37.52 | Improved |
| lower target latency from 450ms to 50ms (ablation) | searched x2 SR model · Urban100 x2 | PSNR (dB): 31.58 -> 30.35 | Hurt |
| lower target latency from 170ms to 40ms (ablation) | searched x4 SR model · Set5 x4 | PSNR (dB): 31.93 -> 30.74 | Hurt |
| use compiler-optimized sparse execution instead of MNN and PyTorch Mobile | searched SR model on mobile · Samsung Galaxy S20 CPU/GPU | FPS: Ours highest FPS, above 20 FPS for x2 and x3 and above 25 for x4 | Improved |
Closest papers by meaning
- Compiler-Aware Neural Architecture Search for On-Mobile Real-Time Super-Resolution (ECCV 2022 · similarity 0.95)
- Iterative Soft Shrinkage Learning for Efficient Image Super-Resolution (ICCV 2023 · similarity 0.88)
- Accelerating the Super-Resolution Convolutional Neural Network (ECCV 2016 · similarity 0.87)
- Edge-SD-SR: Low Latency and Parameter Efficient On-device Super-Resolution with Stable Diffusion via Bidirectional Conditioning (CVPR 2025 · similarity 0.87)
- PocketSR: The Super-Resolution Expert in Your Pocket Mobiles (NeurIPS 2025 · similarity 0.87)
- Lightweight Image Super-Resolution via Flexible Meta Pruning (ICML 2024 · 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.
