Search Results for author:
Found 18 papers, 1 papers with code
Lossy Image Compression with Foundation Diffusion Models
Incorporating diffusion models in the image compression domain has the potential to produce realistic and detailed reconstructions, especially at extremely low bitrates.
Revitalizing Legacy Video Content: Deinterlacing with Bidirectional Information Propagation
Our proposed method supports bidirectional spatio-temporal information propagation across multiple scales to leverage information in both space and time.
Controllable Inversion of Black-Box Face Recognition Models via Diffusion
Face recognition models embed a face image into a low-dimensional identity vector containing abstract encodings of identity-specific facial features that allow individuals to be distinguished from one another.
A Generative Model for Digital Camera Noise Synthesis
To this end, we propose an effective generative model which utilizes clean features as guidance followed by noise injections into the network.
Kernel Aware Resampler
This renders our model applicable for different types of data not seen during the training such as normals.
Video Compression With Entropy-Constrained Neural Representations
This performance gap can be explained by the fact that current NVR methods: i) use architectures that do not efficiently obtain a compact representation of temporal and spatial information; and ii) minimize rate and distortion disjointly (first overfitting a network on a video and then using heuristic techniques such as post-training quantization or weight pruning to compress the model).
Frame Interpolation Transformer and Uncertainty Guidance
Through this error estimation, our method can produce even higher-quality intermediate frames using only a fraction of the time compared to a full rendering.
Microdosing: Knowledge Distillation for GAN based Compression
Recently, significant progress has been made in learned image and video compression.
Blind Image Restoration with Flow Based Priors
In contrast to this, we propose using normalizing flows to model the distribution of the target content and to use this as a prior in a maximum a posteriori (MAP) formulation.
Lossy Image Compression with Normalizing Flows
However, state-of-the-art solutions for deep image compression typically employ autoencoders which map the input to a lower dimensional latent space and thus irreversibly discard information already before quantization.
Content Adaptive Optimization for Neural Image Compression
The field of neural image compression has witnessed exciting progress as recently proposed architectures already surpass the established transform coding based approaches.
Deep Generative Video Compression
The usage of deep generative models for image compression has led to impressive performance gains over classical codecs while neural video compression is still in its infancy.
Deep Probabilistic Video Compression
We propose a variational inference approach to deep probabilistic video compression.
Deep Video Color Propagation
Traditional approaches for color propagation in videos rely on some form of matching between consecutive video frames.
A Fully Progressive Approach to Single-Image Super-Resolution
Recent deep learning approaches to single image super-resolution have achieved impressive results in terms of traditional error measures and perceptual quality.
Ranked #14 on
Image Super-Resolution
on BSD100 - 4x upscaling
Normalized Cut Loss for Weakly-supervised CNN Segmentation
Our normalized cut loss approach to segmentation brings the quality of weakly-supervised training significantly closer to fully supervised methods.
PhaseNet for Video Frame Interpolation
We show that this is superior to the hand-crafted heuristics previously used in phase-based methods and also compares favorably to recent deep learning based approaches for video frame interpolation on challenging datasets.
On Regularized Losses for Weakly-supervised CNN Segmentation
This approach simplifies weakly-supervised training by avoiding extra MRF/CRF inference steps or layers explicitly generating full masks, while improving both the quality and efficiency of training.
