Research map / Image generation / Editing and style transfer
Stylization-Based Architecture for Fast Deep Exemplar Colorization
Zhongyou Xu, Tingting Wang, Faming Fang, Yun Sheng, Guixu Zhang
Check 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 |
|---|---|---|---|
| use the two-sub-net architecture: transfer coarse chrominance, then refine with the colorization sub-net (ablation) | Stylization-based colorization · Exemplar colorization | visual quality | Improved |
| use only the colorization sub-net with an empty ab map (ablation) | Stylization-based colorization · Exemplar colorization | visual quality | Hurt |
| use only the transfer sub-net without colorization refinement (ablation) | Stylization-based colorization · Exemplar colorization | visual quality | Hurt |
| add AdaIN in both encoder and decoder (ablation) | Transfer sub-net · Exemplar colorization | visual quality | Improved |
| remove AdaIN from the encoder (ablation) | Transfer sub-net · Exemplar colorization | visual quality | Hurt |
| remove AdaIN from the decoder (ablation) | Transfer sub-net · Exemplar colorization | visual quality | Hurt |
| replace AdaIN with WCT (ablation) | Transfer sub-net · Image stylization | visual quality | Hurt |
| use the proposed colorization method rather than He et al. [8] | Exemplar colorization · Colorization 256 x 256 | runtime: 7.25+1.14 vs 0.04+0.08x2 | Improved |
| use the proposed colorization method rather than He et al. [8] | Exemplar colorization · Colorization 512 x 512 | runtime: 33.69+1.30 vs 0.14+0.12x2 | Improved |
| use the proposed colorization method rather than He et al. [8] | Exemplar colorization · Colorization 1024 x 1024 | runtime: 49.96+OMM vs 0.59+0.28x2 | Improved |
| use the proposed method rather than Xiao et al. [38] | Exemplar colorization · Colorization 256 x 256 | runtime: 0.48 vs 0.04+0.08x2 | Improved |
Closest papers by meaning
- Semantic-Sparse Colorization Network for Deep Exemplar-Based Colorization (ECCV 2022 · similarity 0.90)
- Deep Exemplar-Based Video Colorization (CVPR 2019 · similarity 0.90)
- BiSTNet: Semantic Image Prior Guided Bidirectional Temporal Feature Fusion for Deep Exemplar-Based Video Colorization (TPAMI 2024 · similarity 0.88)
- Automatic Content-Aware Color and Tone Stylization (CVPR 2016 · similarity 0.87)
- Colorful Image Colorization (ECCV 2016 · similarity 0.87)
- DDColor: Towards Photo-Realistic Image Colorization via Dual Decoders (ICCV 2023 · 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.
