Research map / Video / Video segmentation and tracking
Spatio-Temporal Deformable Convolution for Compressed Video Quality Enhancement
Jianing Deng, Li Wang, Shiliang Pu, Cheng Zhuo
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 |
|---|---|---|---|
| STDF (spatio-temporal deformable fusion) instead of optical-flow fusion | video quality enhancement CNN · HEVC test QP 37 | dPSNR: 0.56 -> 0.75 | Improved |
| use STDC instead of motion-compensated early fusion (ablation) | STDF R=3 · HEVC Class B-E, QP 37 | dPSNR: 0.66 -> 0.74 | Improved |
| joint offset prediction instead of pairwise (ablation) | STDF R=3 · HEVC Class B-E, QP 37 | dPSNR: 0.65 -> 0.74 | Improved |
| joint offset prediction instead of pairwise (ablation) | STDF R=3 · HEVC Class B-E, QP 37 | FLOPs: 409.49 -> 204.08 | Improved |
| increase temporal radius R from 1 to 3 (ablation) | STDF · HEVC test QP 37 | dPSNR: 0.65 -> 0.75 | Improved |
| increase temporal radius R (ablation) | EF_STMC optical-flow fusion · HEVC Class B-E, QP 37 | dPSNR | Hurt |
| enlarge model (C1=64, C2=64, L=16) (ablation) | STDF-R3 · HEVC test QP 37 | dPSNR: 0.75 -> 0.83 | Improved |
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.
- MFQE 2.0 — MFQE 2.0: A New Approach for Multi-Frame Quality Enhancement on Compressed Video (TPAMI 2019) · better on 5 of 5 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
- RivuletMLP: An MLP-based Architecture for Efficient Compressed Video Quality Enhancement (CVPR 2025 · similarity 0.87)
- Video Frame Interpolation via Deformable Separable Convolution (AAAI 2020 · similarity 0.86)
- Multi-Frame Deformable Look-Up Table for Compressed Video Quality Enhancement (AAAI 2025 · similarity 0.85)
- Blur-aware Spatio-temporal Sparse Transformer for Video Deblurring (CVPR 2024 · similarity 0.85)
- Offline and Online Optical Flow Enhancement for Deep Video Compression (AAAI 2024 · similarity 0.85)
- A Unified Solution to Video Fusion: From Multi-Frame Learning to Benchmarking (NeurIPS 2025 · similarity 0.84)
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.
