Research map / Image generation / Editing and style transfer
ELEGANT: Exchanging Latent Encodings with GAN for Transferring Multiple Face Attributes
Taihong Xiao, Jiapeng Hong, Jinwen Ma
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 ELEGANT (latent exchange, residual learning, multi-scale discriminators) instead of DNA-GAN | ELEGANT · CelebA bangs (+) | FID: 79.27 -> 30.71 | Improved |
| use ELEGANT instead of DNA-GAN | ELEGANT · CelebA smiling (+) | FID: 77.04 -> 25.71 | Improved |
| use ELEGANT instead of DNA-GAN | ELEGANT · CelebA mustache (+) | FID: 126.33 -> 37.51 | Improved |
| use ELEGANT instead of DNA-GAN | ELEGANT · CelebA eyeglasses (+) | FID: 75.02 -> 47.35 | Improved |
| use ELEGANT instead of DNA-GAN | ELEGANT · CelebA male (+) | FID: 121.04 -> 59.37 | Improved |
| use ELEGANT instead of StarGAN | ELEGANT · CelebA mustache (-) | FID: 176.18 -> 49.13 | Improved |
| use ELEGANT instead of StarGAN | ELEGANT · CelebA male (-) | FID: 206.21 -> 56.80 | Improved |
| use ELEGANT instead of CycleGAN | ELEGANT · CelebA bangs (+) | FID: 27.81 -> 30.71 | Hurt |
| use ELEGANT instead of CycleGAN | ELEGANT · CelebA mustache (+) | FID: 43.58 -> 37.51 | Improved |
| use ELEGANT instead of CycleGAN | ELEGANT · CelebA eyeglasses (+) | FID: 36.87 -> 47.35 | Hurt |
| replace batch normalization with l2-normalization (ablation) | ELEGANT · training stability | convergence | Improved |
Later papers that compared with this method
11 later accepted papers report EleGANt as a baseline in their results tables; 11 of them report a better number on most of the results they share with it.
- Anchoring on Reality: Breaking the Pseudo-Target Ceiling in Makeup Transfer (ECCV 2026 · better on 1 of 1 shared result)
- Content-Style Decoupling for Unsupervised Makeup Transfer without Generating Pseudo Ground Truth (CVPR 2024 · better on 10 of 10 shared results)
- Toward Tiny and High-quality Facial Makeup with Data Amplify Learning (ECCV 2024 · better on 6 of 6 shared results)
- SDGAN: Disentangling Semantic Manipulation for Facial Attribute Editing (AAAI 2024 · better on 2 of 2 shared results)
- Image-to-Image Translation With Disentangled Latent Vectors for Face Editing (TPAMI 2023 · better on 1 of 1 shared result)
- Image-to-Image Translation via Hierarchical Style Disentanglement (CVPR 2021 · better on 3 of 3 shared results)
- L2M-GAN: Learning To Manipulate Latent Space Semantics for Facial Attribute Editing (CVPR 2021 · better on 2 of 2 shared results)
- Bridging the Gap Between Label- and Reference-Based Synthesis in Multi-Attribute Image-to-Image Translation (ICCV 2021 · better on 2 of 2 shared results)
3 more not listed.
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.
- StarGAN — StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation (CVPR 2018) · better on 10 of 10 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
- Multi-Attribute Transfer via Disentangled Representation (AAAI 2019 · similarity 0.92)
- Image-to-Image Translation With Disentangled Latent Vectors for Face Editing (TPAMI 2023 · similarity 0.89)
- Interpreting the Latent Space of GANs for Semantic Face Editing (CVPR 2020 · similarity 0.89)
- Controllable Image Synthesis With Attribute-Decomposed GAN (TPAMI 2022 · similarity 0.88)
- Learning Residual Images for Face Attribute Manipulation (CVPR 2017 · similarity 0.88)
- Diffusion-driven GAN Inversion for Multi-Modal Face Image Generation (CVPR 2024 · 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.
