activity
20232025
collaborators

6 papers

cs.LG2025

Efficient Bayesian Inference from Noisy Pairwise Comparisons

Till Aczel, Lucas Theis, Roger Wattenhofer

Evaluating generative models is challenging because standard metrics often fail to reflect human preferences. Human evaluations are more reliable but costly and noisy, as participa…

cs.IT2024

Gaussian Channel Simulation with Rotated Dithered Quantization

Szymon Kobus, Lucas Theis, Deniz Gündüz

Channel simulation involves generating a sample from the conditional distribution , where is a remote realization sampled from . This paper introduces a novel…

cs.LG2024

What makes an image realistic?

Lucas Theis

The last decade has seen tremendous progress in our ability to generate realistic-looking data, be it images, text, audio, or video. Here, we discuss the closely related problem of…

eess.IV2023

C3: High-performance and low-complexity neural compression from a single image or video

Hyunjik Kim, Matthias Bauer, Lucas Theis +2

Most neural compression models are trained on large datasets of images or videos in order to generalize to unseen data. Such generalization typically requires large and expressive…

cs.CV2023

The Unreasonable Effectiveness of Linear Prediction as a Perceptual Metric

Daniel Severo, Lucas Theis, Johannes Ballé

We show how perceptual embeddings of the visual system can be constructed at inference-time with no training data or deep neural network features. Our perceptual embeddings are sol…

cs.IT2023

Wasserstein Distortion: Unifying Fidelity and Realism

Yang Qiu, Aaron B. Wagner, Johannes Ballé +1

We introduce a distortion measure for images, Wasserstein distortion, that simultaneously generalizes pixel-level fidelity on the one hand and realism or perceptual quality on the…