Research map / Image generation / Editing and style transfer
EBDM: Exemplar-guided Image Translation with Brownian-bridge Diffusion Models
Eungbean Lee, Somi Jeong, Kwanghoon Sohn
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 |
|---|---|---|---|
| use Brownian bridge with structure control as fixed start instead of matching-based or noise-to-image conditional diffusion | EBDM · CelebA-HQ mask-to-photo | FID: 20.44 -> 12.21 | Improved |
| EBDM versus matching-based methods on edge-to-photo FID | EBDM · CelebA-HQ edge-to-photo | FID: 11.84 vs RABIT 11.67 | No clear effect |
| EBDM on pose-to-photo diversity (LPIPS) and semantic consistency | EBDM · DeepFashion pose-to-photo | LPIPS: 0.255 vs MCL-Net 0.286 | Hurt |
| use DINOv2 global encoder instead of CLIP | EBDM · CelebA-HQ edge-to-photo | detail fidelity (qualitative) | Improved |
| add Exemplar Network on top of Global Encoder | EBDM · CelebA-HQ edge-to-photo | image sharpness (qualitative) | Improved |
| replace ControlNet + IP-Adapter conditioning with single-condition bridge diffusion | EBDM · inference cost (50 steps) | FLOPs: 86.08 T -> 61.72 T | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 3 on most shared results.
- MIDMs — MIDMs: Matching Interleaved Diffusion Models for Exemplar-Based Image Translation (AAAI 2023) · better on 3 of 4 shared results
- DynaST — DynaST: Dynamic Sparse Transformer for Exemplar-Guided Image Generation (ECCV 2022) · better on 0 of 2 shared results
- CoCosNetv2 — CoCosNet v2: Full-Resolution Correspondence Learning for Image Translation (CVPR 2021) · 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
- FAM Diffusion: Frequency and Attention Modulation for High-Resolution Image Generation with Stable Diffusion (CVPR 2025 · similarity 0.89)
- Exploring the Design Space of Diffusion Bridge Models (NeurIPS 2025 · similarity 0.87)
- Simpler Diffusion: 1.5 FID on ImageNet512 with Pixel-space Diffusion (CVPR 2025 · similarity 0.87)
- Plug-and-Play Diffusion Distillation (CVPR 2024 · similarity 0.87)
- PIXELS: Progressive Image Xemplar-based Editing with Latent Surgery (AAAI 2025 · similarity 0.87)
- Faster Diffusion: Rethinking the Role of the Encoder for Diffusion Model Inference (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.
