135 citations · 275 across the 19 of their papers we have counts for
19 papers
GRVS: a Generalizable and Recurrent Approach to Monocular Dynamic View Synthesis
Thomas Tanay, Mohammed Brahimi, Michal Nazarczuk +5
Synthesizing novel views from monocular videos of dynamic scenes remains a challenging problem. Scene-specific methods that optimize 4D representations with explicit motion priors…
Charge: A Comprehensive Novel View Synthesis Benchmark and Dataset to Bind Them All
Michal Nazarczuk, Thomas Tanay, Arthur Moreau +2
This paper presents a new dataset for Novel View Synthesis, generated from a high-quality, animated film with stunning realism and intricate detail. Our dataset captures a variety…
Off The Grid: Detection of Primitives for Feed-Forward 3D Gaussian Splatting
Arthur Moreau, Richard Shaw, Michal Nazarczuk +5
Feed-forward 3D Gaussian Splatting (3DGS) models enable real-time scene generation but are hindered by suboptimal pixel-aligned primitive placement, which relies on a dense, rigid…
ViDAR: Video Diffusion-Aware 4D Reconstruction From Monocular Inputs
Michal Nazarczuk, Sibi Catley-Chandar, Thomas Tanay +3
Dynamic Novel View Synthesis aims to generate photorealistic views of moving subjects from arbitrary viewpoints. This task is particularly challenging when relying on monocular vid…
AIM 2024 Sparse Neural Rendering Challenge: Methods and Results
Michal Nazarczuk, Sibi Catley-Chandar, Thomas Tanay +27
This paper reviews the challenge on Sparse Neural Rendering that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2024. This manuscript…
AIM 2024 Sparse Neural Rendering Challenge: Dataset and Benchmark
Michal Nazarczuk, Thomas Tanay, Sibi Catley-Chandar +3
Recent developments in differentiable and neural rendering have made impressive breakthroughs in a variety of 2D and 3D tasks, e.g. novel view synthesis, 3D reconstruction. Typical…
Global Latent Neural Rendering
Thomas Tanay, Matteo Maggioni
A recent trend among generalizable novel view synthesis methods is to learn a rendering operator acting over single camera rays. This approach is promising because it removes the n…
Efficient View Synthesis and 3D-based Multi-Frame Denoising with Multiplane Feature Representations
Thomas Tanay, Aleš Leonardis, Matteo Maggioni
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 w…
Tunable Convolutions with Parametric Multi-Loss Optimization
Matteo Maggioni, Thomas Tanay, Francesca Babiloni +2
Behavior of neural networks is irremediably determined by the specific loss and data used during training. However it is often desirable to tune the model at inference time based o…
FlexHDR: Modelling Alignment and Exposure Uncertainties for Flexible HDR Imaging
Sibi Catley-Chandar, Thomas Tanay, Lucas Vandroux +3
High dynamic range (HDR) imaging is of fundamental importance in modern digital photography pipelines and used to produce a high-quality photograph with well exposed regions despit…
NTIRE 2021 Challenge on Quality Enhancement of Compressed Video: Methods and Results
Ren Yang, Radu Timofte, Jing Liu +69
This paper reviews the first NTIRE challenge on quality enhancement of compressed video, with a focus on the proposed methods and results. In this challenge, the new Large-scale Di…
Diagnosing and Preventing Instabilities in Recurrent Video Processing
Thomas Tanay, Aivar Sootla, Matteo Maggioni +4
Recurrent models are a popular choice for video enhancement tasks such as video denoising or super-resolution. In this work, we focus on their stability as dynamical systems and sh…
NTIRE 2020 Challenge on Real Image Denoising: Dataset, Methods and Results
Abdelrahman Abdelhamed, Mahmoud Afifi, Radu Timofte +87
This paper reviews the NTIRE 2020 challenge on real image denoising with focus on the newly introduced dataset, the proposed methods and their results. The challenge is a new versi…
Multiple-Identity Image Attacks Against Face-based Identity Verification
Jerone T. A. Andrews, Thomas Tanay, Lewis D. Griffin
Facial verification systems are vulnerable to poisoning attacks that make use of multiple-identity images (MIIs)---face images stored in a database that resemble multiple persons,…
Batch Normalization is a Cause of Adversarial Vulnerability
Angus Galloway, Anna Golubeva, Thomas Tanay +2
Batch normalization (batch norm) is often used in an attempt to stabilize and accelerate training in deep neural networks. In many cases it indeed decreases the number of parameter…
A New Angle on L2 Regularization
Thomas Tanay, Lewis D Griffin
Imagine two high-dimensional clusters and a hyperplane separating them. Consider in particular the angle between: the direction joining the two clusters' centroids and the normal t…
Built-in Vulnerabilities to Imperceptible Adversarial Perturbations
Thomas Tanay, Jerone T. A. Andrews, Lewis D. Griffin
Designing models that are robust to small adversarial perturbations of their inputs has proven remarkably difficult. In this work we show that the reverse problem---making models m…
Adversarial Training Versus Weight Decay
Angus Galloway, Thomas Tanay, Graham W. Taylor
Performance-critical machine learning models should be robust to input perturbations not seen during training. Adversarial training is a method for improving a model's robustness t…
A Boundary Tilting Persepective on the Phenomenon of Adversarial Examples
Thomas Tanay, Lewis Griffin
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. This adve…