6 papers
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…
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…
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…
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…
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…
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…