Research map / Image generation / Editing and style transfer
Vector Quantized Image-to-Image Translation
Yu-Jie Chen, Shin-I Cheng, Wei-Chen Chiu, Hung-Yu Tseng, Hsin-Ying Lee
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 sequential StyleGAN2 + U-GAT-IT + Boundless pipeline with unified VQ-I2I | VQ-I2I · Generate-translate-extend (Yosemite summer) | FID: 128.73 -> 107.62 | Improved |
| VQ-I2I vs StyleGAN2 for unconditional generation | VQ-I2I · Unconditional generation (Yosemite) | FID: 106.35 -> 127.31 | Hurt |
| VQ-I2I vs VQGAN for unconditional generation | VQ-I2I · Unconditional generation (Yosemite) | FID: 127.84 -> 127.31 | No clear effect |
| VQ-I2I vs InfinityGAN for image extension | VQ-I2I · Image extension (Yosemite) | FID: 143.97 -> 109.86 | Improved |
| VQ-I2I vs Boundless for image extension | VQ-I2I · Image extension (Yosemite) | FID: 101.68 -> 109.86 | Hurt |
| disentangle content and style latents (VQ-I2I vs uni-VQ-I2I) (ablation) | VQ-I2I · AFHQ / Yosemite translation (qualitative) | content consistency | Improved |
| increase number of splits in transitional stylization (ablation) | Transitional stylization · Yosemite (qualitative) | smoothness | 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.
- InfinityGAN — InfinityGAN: Towards Infinite-Pixel Image Synthesis (ICLR 2022) · better on 1 of 1 shared result
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
- RelGAN: Multi-Domain Image-to-Image Translation via Relative Attributes (ICCV 2019 · similarity 0.86)
- Channel-wise Vector Quantization (NeurIPS 2026 · similarity 0.83)
- Rethinking the Objectives of Vector-Quantized Tokenizers for Image Synthesis (CVPR 2024 · similarity 0.83)
- Finite Scalar Quantization: VQ-VAE Made Simple (ICLR 2024 · similarity 0.82)
- Optimize & Reduce: A Top-Down Approach for Image Vectorization (AAAI 2024 · similarity 0.82)
- Zero-Shot Quantization via Weight-Space Arithmetic (NeurIPS 2026 · similarity 0.82)
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.
