Research map / Image generation / GANs
InvNet: Encoding Geometric and Statistical Invariances in Deep Generative Models
Ameya Joshi, Minsu Cho, Viraj Shah, Balaji Pokuri, Soumik Sarkar, Baskar Ganapathysubramanian, Chinmay Hegde
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 invariance loss with three-way alternating optimization instead of AC-GAN-style conditioning | WGAN generator · Two-circle shapes | iterations to acceptable circles: ~23k -> ~3k iterations | Improved |
| use invariance loss instead of cGAN/ACGAN conditioning | WGAN generator · Two-circle shapes | respecting radius and position | Improved |
| replace Stinis et al. style constraint-residual discriminator input with invariance loss | WGAN-GP · Binary microstructures | training convergence | Improved |
| replace numerical PDE simulation with trained InvNet for 100000 microstructures | Cahn-Hilliard microstructure generation · Binary microstructures | total time (s): 184000s -> 58700s | Improved |
Closest papers by meaning
- A Geometric Analysis of Deep Generative Image Models and Its Applications (ICLR 2021 · similarity 0.89)
- Learning Generative Models of Textured 3D Meshes From Real-World Images (ICCV 2021 · similarity 0.87)
- Learning Conditional Generative Models for Phase Retrieval (JMLR 2023 · similarity 0.87)
- Statistically Optimal Generative Modeling with Maximum Deviation from the Empirical Distribution (ICML 2024 · similarity 0.87)
- Compositional GAN: Learning Image-Conditional Binary Composition (IJCV 2020 · similarity 0.87)
- Non-Parametric Priors For Generative Adversarial Networks (ICML 2019 · 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.
