A multimodal diffusion model generates controllable alternative streetscapes from street-view imagery using visual metrics and text, shown on Chicago and Orlando data with gains in semantic consistency.
Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizer
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
Autoencoders provide a powerful framework for learning compressed representations by encoding all of the information needed to reconstruct a data point in a latent code. In some cases, autoencoders can "interpolate": By decoding the convex combination of the latent codes for two datapoints, the autoencoder can produce an output which semantically mixes characteristics from the datapoints. In this paper, we propose a regularization procedure which encourages interpolated outputs to appear more realistic by fooling a critic network which has been trained to recover the mixing coefficient from interpolated data. We then develop a simple benchmark task where we can quantitatively measure the extent to which various autoencoders can interpolate and show that our regularizer dramatically improves interpolation in this setting. We also demonstrate empirically that our regularizer produces latent codes which are more effective on downstream tasks, suggesting a possible link between interpolation abilities and learning useful representations.
years
2026 2representative citing papers
A single-network implicit neural optimal transport method that solves the c-transform via proximal fixed-point iteration for stable, non-adversarial training.
citing papers explorer
-
Designing streetscapes from street-view imagery using diffusion models
A multimodal diffusion model generates controllable alternative streetscapes from street-view imagery using visual metrics and text, shown on Chicago and Orlando data with gains in semantic consistency.
-
Implicit Neural Optimal Transport via Fixed-Point Optimization
A single-network implicit neural optimal transport method that solves the c-transform via proximal fixed-point iteration for stable, non-adversarial training.