Research map / Image generation / Super-resolution
SYENet: A Simple Yet Effective Network for Multiple Low-Level Vision Tasks with Real-Time Performance on Mobile Device
Weiran Gou, Ziyao Yi, Yan Xiang, Shaoqing Li, Zibin Liu, Dehui Kong, Ke Xu
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 |
|---|---|---|---|
| replace L1 loss with Outlier-Aware Loss (ablation) | SYENet · ISP | PSNR (dB): 24.7200 -> 24.8732 | Improved |
| replace L1 loss with Outlier-Aware Loss (ablation) | SYENet(LLE) · LoL | PSNR (dB): 20.9717 -> 22.5900 | Improved |
| replace L1 loss with Outlier-Aware Loss (ablation) | EDSR x4 · SR | PSNR (dB): 28.9164 -> 28.9530 | Improved |
| use revised ConvRep with 1x1 convolution instead of RepVGGBlock (ablation) | SYENet · ISP | PSNR (dB): 22.6797 -> 24.8732 | Improved |
| add channel attention (ablation) | SYENet · ISP | PSNR (dB): 24.0936 -> 24.8732 | Improved |
| use QCU (multiplication plus learnable bias) instead of addition (ablation) | SYENet · ISP | PSNR (dB): 24.5252 -> 24.8732 | Improved |
| use QCU instead of pure multiplication (ablation) | SYENet · ISP | PSNR (dB): 24.7971 -> 24.8732 | Improved |
| use two asymmetric branches instead of single branch (ablation) | SYENet · ISP | PSNR (dB): 24.5510 -> 24.8732 | Improved |
| add re-parameterized convolution (ConvRep) vs plain convolution (ablation) | SYENet · ISP | PSNR (dB): 24.6778 -> 24.8732 | Improved |
| use SYENet instead of the best large SOTA model for low-light enhancement | LoL · LoL | PSNR (dB): 25.19 (LLFlow) vs 22.59 | Hurt |
Closest papers by meaning
- Real-time Core-Periphery Guided ViT with Smart Data Layout Selection on Mobile Devices (NeurIPS 2024 · similarity 0.85)
- RepViT: Revisiting Mobile CNN From ViT Perspective (CVPR 2024 · similarity 0.84)
- GradQ-ViT: Robust and Efficient Gradient Quantization for Vision Transformers (AAAI 2025 · similarity 0.84)
- SHViT: Single-Head Vision Transformer with Memory Efficient Macro Design (CVPR 2024 · similarity 0.83)
- FreeNet: Liberating Depth-Wise Separable Operations for Building Faster Mobile Vision Architectures (AAAI 2025 · similarity 0.83)
- IFORMER: INTEGRATING CONVNET AND TRANSFORMER FOR MOBILE APPLICATION (ICLR 2025 · similarity 0.83)
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.
