Search Results for author:
Found 31 papers, 12 papers with code
What makes an image realistic?
The last decade has seen tremendous progress in our ability to generate realistic-looking data, be it images, text, audio, or video.
C3: High-performance and low-complexity neural compression from a single image or video
On the UVG video benchmark, we match the RD performance of the Video Compression Transformer (Mentzer et al.), a well-established neural video codec, with less than 5k MACs/pixel for decoding.
The Unreasonable Effectiveness of Linear Prediction as a Perceptual Metric
We show how perceptual embeddings of the visual system can be constructed at inference-time with no training data or deep neural network features.
Wasserstein Distortion: Unifying Fidelity and Realism
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 other.
High-Fidelity Image Compression with Score-based Generative Models
Despite the tremendous success of diffusion generative models in text-to-image generation, replicating this success in the domain of image compression has proven difficult.
Lossy Compression with Gaussian Diffusion
Unlike modern compression schemes which rely on transform coding and quantization to restrict the transmitted information, DiffC relies on the efficient communication of pixels corrupted by Gaussian noise.
An Introduction to Neural Data Compression
Neural compression is the application of neural networks and other machine learning methods to data compression.
Optimal Compression of Locally Differentially Private Mechanisms
Compressing the output of \epsilon-locally differentially private (LDP) randomizers naively leads to suboptimal utility.
Algorithms for the Communication of Samples
The efficient communication of noisy data has applications in several areas of machine learning, such as neural compression or differential privacy, and is also known as reverse channel coding or the channel simulation problem.
A coding theorem for the rate-distortion-perception function
The rate-distortion-perception function (RDPF; Blau and Michaeli, 2019) has emerged as a useful tool for thinking about realism and distortion of reconstructions in lossy compression.
Importance weighted compression
The connection between variational autoencoders (VAEs) and compression is well established and they have been used for both lossless and lossy compression.
On the advantages of stochastic encoders
Stochastic encoders have been used in rate-distortion theory and neural compression because they can be easier to handle.
Universally Quantized Neural Compression
A popular approach to learning encoders for lossy compression is to use additive uniform noise during training as a differentiable approximation to test-time quantization.
Discriminative Topic Modeling with Logistic LDA
We propose logistic LDA, a novel discriminative variant of latent Dirichlet allocation which is easy to apply to arbitrary inputs.
Addressing Delayed Feedback for Continuous Training with Neural Networks in CTR prediction
The focus of this paper is to identify the best combination of loss functions and models that enable large-scale learning from a continuous stream of data in the presence of delayed labels.
HoloGAN: Unsupervised learning of 3D representations from natural images
This shows that HoloGAN is the first generative model that learns 3D representations from natural images in an entirely unsupervised manner.
Faster gaze prediction with dense networks and Fisher pruning
Predicting human fixations from images has recently seen large improvements by leveraging deep representations which were pretrained for object recognition.
Checkerboard artifact free sub-pixel convolution: A note on sub-pixel convolution, resize convolution and convolution resize
Compared to sub-pixel convolution initialized with schemes designed for standard convolution kernels, it is free from checkerboard artifacts immediately after initialization.
Lossy Image Compression with Compressive Autoencoders
We propose a new approach to the problem of optimizing autoencoders for lossy image compression.
Fast Face-swap Using Convolutional Neural Networks
We consider the problem of face swapping in images, where an input identity is transformed into a target identity while preserving pose, facial expression, and lighting.
Amortised MAP Inference for Image Super-resolution
We show that, using this architecture, the amortised MAP inference problem reduces to minimising the cross-entropy between two distributions, similar to training generative models.
Is the deconvolution layer the same as a convolutional layer?
In this note, we want to focus on aspects related to two questions most people asked us at CVPR about the network we presented.
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
The adversarial loss pushes our solution to the natural image manifold using a discriminator network that is trained to differentiate between the super-resolved images and original photo-realistic images.
Ranked #3 on
Image Super-Resolution
on VggFace2 - 8x upscaling
A note on the evaluation of generative models
In particular, we show that three of the currently most commonly used criteria---average log-likelihood, Parzen window estimates, and visual fidelity of samples---are largely independent of each other when the data is high-dimensional.
Generative Image Modeling Using Spatial LSTMs
Modeling the distribution of natural images is challenging, partly because of strong statistical dependencies which can extend over hundreds of pixels.
Ranked #63 on
Image Generation
on CIFAR-10
(bits/dimension metric)
A trust-region method for stochastic variational inference with applications to streaming data
However, the algorithm is prone to local optima which can make the quality of the posterior approximation sensitive to the choice of hyperparameters and initialization.
A Generative Model of Natural Texture Surrogates
In order to model this variability, we first applied the parametric texture algorithm of Portilla and Simoncelli to image patches of 64X64 pixels in a large database of natural images such that each image patch is then described by 655 texture parameters which specify certain statistics, such as variances and covariances of wavelet coefficients or coefficient magnitudes within that patch.
Supervised learning sets benchmark for robust spike detection from calcium imaging signals
A fundamental challenge in calcium imaging has been to infer the timing of action potentials from the measured noisy calcium fluorescence traces.
Deep Gaze I: Boosting Saliency Prediction with Feature Maps Trained on ImageNet
Recent results suggest that state-of-the-art saliency models perform far from optimal in predicting fixations.
Inference and Mixture Modeling with the Elliptical Gamma Distribution
We study modeling and inference with the Elliptical Gamma Distribution (EGD).
Training sparse natural image models with a fast Gibbs sampler of an extended state space
We present a new learning strategy based on an efficient blocked Gibbs sampler for sparse overcomplete linear models.
