Search Results for author:
Found 13 papers, 8 papers with code
On the Convergence of PatchMatch and Its Variants
We also derive more specific bounds for two of these particular cases: the original PatchMatch and Coherency Sensitive Hashing.
Model-blind Video Denoising Via Frame-to-frame Training
Modeling the processing chain that has produced a video is a difficult reverse engineering task, even when the camera is available.
Non-Local Video Denoising by CNN
To the best of our knowledge, this is the first successful application of a CNN to video denoising.
Joint Demosaicking and Denoising by Fine-Tuning of Bursts of Raw Images
Due to the unavailability of ground truth data these networks cannot be currently trained using real RAW images.
Implementation of the VBM3D Video Denoising Method and Some Variants
VBM3D is an extension to video of the well known image denoising algorithm BM3D, which takes advantage of the sparse representation of stacks of similar patches in a transform domain.
Self-Supervised training for blind multi-frame video denoising
We propose a self-supervised approach for training multi-frame video denoising networks.
Proba-V-ref: Repurposing the Proba-V challenge for reference-aware super resolution
We argue that in doing so, the challenge ranks the proposed methods not only by their MISR performance, but mainly by the heuristics used to guess which image in the series is the most similar to the high-resolution target.
Investigating Neural Architectures by Synthetic Dataset Design
It is therefore impossible to know what cues a given neural structure is taking advantage of in such data.
Self-supervision versus synthetic datasets: which is the lesser evil in the context of video denoising?
In this paper, we propose a study aiming to determine which is the best approach to train denoising networks for real raw videos: supervision on synthetic realistic data or self-supervision on real data.
Self-Supervised Super-Resolution for Multi-Exposure Push-Frame Satellites
Modern Earth observation satellites capture multi-exposure bursts of push-frame images that can be super-resolved via computational means.
Can neural networks extrapolate? Discussion of a theorem by Pedro Domingos
In particular, what are the interpolation capabilities of trained neural networks?
L1BSR: Exploiting Detector Overlap for Self-Supervised Single-Image Super-Resolution of Sentinel-2 L1B Imagery
Unfortunately the lack of reliable high-resolution (HR) ground truth limits the application of deep learning methods to this task.
SING: A Plug-and-Play DNN Learning Technique
We propose SING (StabIlized and Normalized Gradient), a plug-and-play technique that improves the stability and generalization of the Adam(W) optimizer.
