Research map / Image generation / Autoregressive and latent generation
Autoencoder Image Interpolation by Shaping the Latent Space
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 adversarial, cycle-consistency, and smoothness regularization with latent linear interpolation | Autoencoder interpolation · COIL-100 | interpolated-image MSE | Helped |
| Use adversarial, cycle-consistency, and smoothness regularization with latent linear interpolation | Autoencoder interpolation · Synthetic pole dataset | interpolation smoothness | Helped |
| Add the discriminator (ablation) | AEAI · COIL-100 | interpolated-image MSE | Helped |
| Add cycle-consistency loss (ablation) | AEAI · COIL-100 | interpolated-image MSE | Helped |
| Add smoothness loss (ablation) | AEAI · COIL-100 | interpolated-image MSE | Helped |
| Add cycle-consistency loss (ablation) | AEAI · COIL-100 | interpolation smoothness | Helped |
| Add discriminator (ablation) | AEAI · COIL-100 | interpolation faithfulness | Helped |
| Add smoothness loss (ablation) | AEAI · COIL-100 | interpolation smoothness | Helped |
Closest papers by meaning
- Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizer (ICLR 2019 · similarity 0.91)
- Graph Geometry-Preserving Autoencoders (ICML 2024 · similarity 0.88)
- Regularized Autoencoders for Isometric Representation Learning (ICLR 2022 · similarity 0.88)
- Geometrically regularized autoencoders for non-Euclidean data (ICLR 2023 · similarity 0.88)
- Sparse Autoencoders, Again? (ICML 2025 · similarity 0.87)
- Bringing NeRFs to the Latent Space: Inverse Graphics Autoencoder (ICLR 2025 · 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.
