Research map / Image generation / GANs
Optimizing the Latent Space of Generative Networks
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 GLO instead of DCGAN for reconstruction | GLO and DCGAN · SVHN 32 test, Lap1 codes | pSNR: 26.0 -> 28.0 | Helped |
| Use GLO instead of VAE for reconstruction | GLO and VAE · CelebA 64 test, Lap1 codes | pSNR: 22.8 -> 25.6 | Helped |
| Use GLO instead of VAE for reconstruction | GLO and VAE · CelebA 128 test, Lap1 codes | pSNR: 23.2 -> 24.8 | Helped |
| Use GLO instead of VAE for reconstruction | GLO and VAE · LSUN 64 test, Lap1 codes | pSNR: 22.1 -> 23.4 | Helped |
| Use GLO instead of VAE for reconstruction | GLO and VAE · LSUN 128 test, Lap1 codes | pSNR: 20.6 -> 21.4 | Helped |
| Use GLO instead of DCGAN for reconstruction | GLO and DCGAN · MNIST 32 test, MSE codes | pSNR: 27.2 -> 27.2 | No clear effect |
| Use GLO instead of DCGAN for reconstruction | GLO and DCGAN · MNIST 32 test, Lap1 codes | pSNR: 26.2 -> 26.2 | No clear effect |
| Find latent codes using MSE rather than Lap1 (ablation) | GLO and DCGAN generators · Image reconstruction | pSNR: +1-2 points | Helped |
| Use reconstruction-trained GLO rather than DCGAN | GLO and DCGAN · LSUN bedrooms | generation visual quality | Hurt |
Closest papers by meaning
- Generalized Adversarially Learned Inference (AAAI 2021 · similarity 0.90)
- Improving Generative Adversarial Networks via Adversarial Learning in Latent Space (NeurIPS 2022 · similarity 0.90)
- Complexity Matters: Rethinking the Latent Space for Generative Modeling (NeurIPS 2023 · similarity 0.90)
- GLeaD: Improving GANs With a Generator-Leading Task (CVPR 2023 · similarity 0.90)
- A Variational Inequality Perspective on Generative Adversarial Networks (ICLR 2019 · similarity 0.90)
- MCGAN: Enhancing GAN Training with Regression-Based Generator Loss (AAAI 2025 · similarity 0.89)
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.