Search Results for author:
Found 13 papers, 6 papers with code
Tunable Convolutions with Parametric Multi-Loss Optimization
Behavior of neural networks is irremediably determined by the specific loss and data used during training.
Efficient View Synthesis and 3D-based Multi-Frame Denoising with Multiplane Feature Representations
While current multi-frame restoration methods combine information from multiple input images using 2D alignment techniques, recent advances in novel view synthesis are paving the way for a new paradigm relying on volumetric scene representations.
Adaptive Spiral Layers for Efficient 3D Representation Learning on Meshes
The success of deep learning models on structured data has generated significant interest in extending their application to non-Euclidean domains.
FlexHDR: Modelling Alignment and Exposure Uncertainties for Flexible HDR Imaging
We introduce a strategy that learns to jointly align and assess the alignment and exposure reliability using an HDR-aware, uncertainty-driven attention map that robustly merges the frames into a single high quality HDR image.
NTIRE 2021 Challenge on Quality Enhancement of Compressed Video: Methods and Results
This paper reviews the first NTIRE challenge on quality enhancement of compressed video, with a focus on the proposed methods and results.
Diagnosing and Preventing Instabilities in Recurrent Video Processing
Recurrent models are a popular choice for video enhancement tasks such as video denoising or super-resolution.
NTIRE 2020 Challenge on Real Image Denoising: Dataset, Methods and Results
This challenge is based on a newly collected validation and testing image datasets, and hence, named SIDD+.
Multiple-Identity Image Attacks Against Face-based Identity Verification
New quantitative results are presented that support an explanation in terms of the geometry of the representations spaces used by the verification systems.
Batch Normalization is a Cause of Adversarial Vulnerability
Batch normalization (batch norm) is often used in an attempt to stabilize and accelerate training in deep neural networks.
A New Angle on L2 Regularization
Imagine two high-dimensional clusters and a hyperplane separating them.
Built-in Vulnerabilities to Imperceptible Adversarial Perturbations
Designing models that are robust to small adversarial perturbations of their inputs has proven remarkably difficult.
Adversarial Training Versus Weight Decay
Performance-critical machine learning models should be robust to input perturbations not seen during training.
A Boundary Tilting Persepective on the Phenomenon of Adversarial Examples
Deep neural networks have been shown to suffer from a surprising weakness: their classification outputs can be changed by small, non-random perturbations of their inputs.
