Research map / Architectures and efficiency / RNNs and normalization
EVC: Towards Real-Time Neural Image Compression with Mask Decay
Wang Guo-Hua, Jiahao Li, Bin Li, Yan Lu
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 |
|---|---|---|---|
| Apply mask decay to the Medium-Medium model (ablation) | EVC Medium-Medium · Kodak | BD-Rate (%) vs VTM: 2&9 -> 0&9 | Improved |
| Apply mask decay to the Small-Small model (ablation) | EVC Small-Small · Kodak | BD-Rate (%) vs VTM: 10&0 -> 6&9 | Improved |
| Use residual representation learning instead of training separate encoders (ablation) | Scalable-EVC with Large decoder · Kodak, S0,1,2,3 | BD-Rate (%) vs VTM: 1.5 -> 0.6 | Improved |
| Add mask decay to residual representation learning (ablation) | Scalable-EVC with Large decoder · Kodak, S0,1,2,3 | BD-Rate (%) vs VTM: 0.6 -> -0.2 | Improved |
| Add mask decay to residual representation learning (ablation) | Scalable-EVC with Small decoder · Kodak, S0,1,2,3 | BD-Rate (%) vs VTM: 5.5 -> 4.8 | Improved |
| Use the proposed sparsity loss rather than L1 or L2 regularization (ablation) | EVC mask decay · Kodak | BD-Rate (%) vs VTM | Improved |
| Set mask decay rate to 8e-5 rather than the suitable 4e-5 (ablation) | EVC mask decay · Kodak | BD-Rate (%) vs VTM | Hurt |
| Use L2 sparsity loss for mask decay (ablation) | EVC mask decay · Kodak | BD-Rate (%) vs VTM | Hurt |
| Avoid channels selected by the raw mask-decay procedure (ablation) | Avoidable Mask Decay · Kodak | BD-Rate (%) vs VTM | No clear effect |
| Compress the encoder rather than the decoder (ablation) | EVC with a Large counterpart module · Kodak | BD-Rate (%) loss: 2.7% vs 5.1% | Improved |
| Use EVC Small rather than STF CNN | Image compression at 768×512 on A100 · 768×512 | encoding latency (ms): 96.4 -> 17.7 | Improved |
Closest papers by meaning
- Towards Practical Real-Time Neural Video Compression (CVPR 2025 · similarity 0.90)
- NVRC: Neural Video Representation Compression (NeurIPS 2024 · similarity 0.87)
- C3: High-Performance and Low-Complexity Neural Compression from a Single Image or Video (CVPR 2024 · similarity 0.87)
- Neural Video Compression with Feature Modulation (CVPR 2024 · similarity 0.87)
- Controllable Distortion-Perception Tradeoff Through Latent Diffusion for Neural Image Compression (AAAI 2025 · similarity 0.87)
- Robustly overfitting latents for flexible neural image compression (NeurIPS 2024 · similarity 0.87)
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.
