Research map / Label-efficient and robust learning / Domain adaptation and generalization
OT-ALD: Aligning Latent Distributions with Optimal Transport for Accelerated Image-to-Image Translation
Zhanpeng Wang, Shuting Cao, Yuhang Lu, , YuhanLi, Na Lei, Zhongxuan Luo
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 |
|---|---|---|---|
| add OT latent alignment (OT-ALD vs DDIB) | DDIB · Cat->Dog | FID: 59.62 -> 44.31 | Improved |
| add OT latent alignment (OT-ALD vs DDIB) | DDIB · Wild->Dog | FID: 55.34 -> 47.65 | Improved |
| add OT latent alignment (OT-ALD vs DDIB) | DDIB · Male->Female | FID: 38.25 -> 25.21 | Improved |
| add OT latent alignment (OT-ALD vs DDIB) | DDIB · Summer->Winter | FID: 90.8 -> 52.87 | Improved |
| add OT latent alignment and smaller T (OT-ALD vs DDIB) | DDIB · Cat->Dog | translation time (s/image): 92.30 -> 45.15 | Improved |
| add OT latent alignment and smaller T (OT-ALD vs DDIB) | DDIB · Summer->Winter | translation time (s/image): 20.64 -> 10.21 | Improved |
| add OT latent alignment (OT-ALD vs DDIB) | DDIB · Cat->Dog | L2: 60.23 -> 42.35 | Improved |
| add OT latent alignment (OT-ALD vs DDIB) | DDIB · Male->Female | PSNR: 21.37 -> 23.05 | Improved |
| increase noise scale eta with fixed T (ablation) | DDIB · OT-ALD | output quality and diversity | Improved |
| increase diffusion time T with positive eta (ablation) | DDIB · OT-ALD | generation quality and diversity | Improved |
| increase diffusion time T (ablation) | DDIB · OT-ALD | translation time | Hurt |
| use OT-ALD instead of CUT | OT-ALD · Cat->Dog | SSIM: 0.601 -> 0.470 | Hurt |
Closest papers by meaning
- Deterministic Image-to-Image Translation via Denoising Brownian Bridge Models with Dual Approximators (CVPR 2025 · similarity 0.88)
- Diffusion Bridge Implicit Models (ICLR 2025 · similarity 0.88)
- Exploring the Design Space of Diffusion Bridge Models (NeurIPS 2025 · similarity 0.88)
- OSCAR: One-Step Diffusion Codec Across Multiple Bit-rates (NeurIPS 2025 · similarity 0.87)
- Simpler Diffusion: 1.5 FID on ImageNet512 with Pixel-space Diffusion (CVPR 2025 · similarity 0.87)
- Denoising Diffusion Bridge Models (ICLR 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.
