Search Results for author:
Found 55 papers, 29 papers with code
Efficient Temporally-Aware DeepFake Detection using H.264 Motion Vectors
Video DeepFakes are fake media created with Deep Learning (DL) that manipulate a person's expression or identity.
Mesh Neural Cellular Automata
We propose Mesh Neural Cellular Automata (MeshNCA), a method for directly synthesizing dynamic textures on 3D meshes without requiring any UV maps.
Exploiting the Signal-Leak Bias in Diffusion Models
This enables us to generate images with more varied brightness, and images that better match a desired style or color.
Vision Transformer Adapters for Generalizable Multitask Learning
We introduce the first multitasking vision transformer adapters that learn generalizable task affinities which can be applied to novel tasks and domains.
Dense Multitask Learning to Reconfigure Comics
In this paper, we develop a MultiTask Learning (MTL) model to achieve dense predictions for comics panels to, in turn, facilitate the transfer of comics from one publication channel to another by assisting authors in the task of reconfiguring their narratives.
InpaintNeRF360: Text-Guided 3D Inpainting on Unbounded Neural Radiance Fields
Neural Radiance Fields (NeRF) can generate highly realistic novel views.
De-coupling and De-positioning Dense Self-supervised Learning
Dense Self-Supervised Learning (SSL) methods address the limitations of using image-level feature representations when handling images with multiple objects.
Spatiotemporal Self-supervised Learning for Point Clouds in the Wild
In this paper, we introduce an SSL strategy that leverages positive pairs in both the spatial and temporal domain.
NEMTO: Neural Environment Matting for Novel View and Relighting Synthesis of Transparent Objects
We propose NEMTO, the first end-to-end neural rendering pipeline to model 3D transparent objects with complex geometry and unknown indices of refraction.
TempSAL -- Uncovering Temporal Information for Deep Saliency Prediction
Deep saliency prediction algorithms complement the object recognition features, they typically rely on additional information, such as scene context, semantic relationships, gaze direction, and object dissimilarity.
Diffusion in Style
Not adapting this initial latent tensor to the style makes fine-tuning slow, expensive, and impractical, especially when only a few target style images are available.
TempSAL - Uncovering Temporal Information for Deep Saliency Prediction
Deep saliency prediction algorithms complement the object recognition features, they typically rely on additional information such as scene context, semantic relationships, gaze direction, and object dissimilarity.
DSI2I: Dense Style for Unpaired Image-to-Image Translation
Unpaired exemplar-based image-to-image (UEI2I) translation aims to translate a source image to a target image domain with the style of a target image exemplar, without ground-truth input-translation pairs.
VolRecon: Volume Rendering of Signed Ray Distance Functions for Generalizable Multi-View Reconstruction
The success of the Neural Radiance Fields (NeRF) in novel view synthesis has inspired researchers to propose neural implicit scene reconstruction.
DyNCA: Real-time Dynamic Texture Synthesis Using Neural Cellular Automata
Current Dynamic Texture Synthesis (DyTS) models can synthesize realistic videos.
PoGaIN: Poisson-Gaussian Image Noise Modeling from Paired Samples
To fill this gap, we derive a novel, cumulant-based, approach for Poisson-Gaussian noise modeling from paired image samples.
DSR: Towards Drone Image Super-Resolution
It would enable drones to fly higher covering larger fields of view, while maintaining a high image quality.
Fast Adversarial Training with Adaptive Step Size
While adversarial training and its variants have shown to be the most effective algorithms to defend against adversarial attacks, their extremely slow training process makes it hard to scale to large datasets like ImageNet.
MulT: An End-to-End Multitask Learning Transformer
At the heart of our approach is a shared attention mechanism modeling the dependencies across the tasks.
Leverage Your Local and Global Representations: A New Self-Supervised Learning Strategy
In essence, this strategy ignores the fact that two crops may truly contain different image information, e. g., background and small objects, and thus tends to restrain the diversity of the learned representations.
RC-MVSNet: Unsupervised Multi-View Stereo with Neural Rendering
Finding accurate correspondences among different views is the Achilles' heel of unsupervised Multi-View Stereo (MVS).
Robust Binary Models by Pruning Randomly-initialized Networks
In this paper, we introduce an approach to obtain robust yet compact models by pruning randomly-initialized binary networks.
Image Denoising with Control over Deep Network Hallucination
In this framework, we exploit the outputs of a deep denoising network alongside an image convolved with a reliable filter.
On the Impact of Hard Adversarial Instances on Overfitting in Adversarial Training
This lets us show that the decay in generalization performance of adversarial training is a result of the model's attempt to fit hard adversarial instances.
Optimizing Latent Space Directions For GAN-based Local Image Editing
Generative Adversarial Network (GAN) based localized image editing can suffer from ambiguity between semantic attributes.
Estimating Image Depth in the Comics Domain
Estimating the depth of comics images is challenging as such images a) are monocular; b) lack ground-truth depth annotations; c) differ across different artistic styles; d) are sparse and noisy.
Ranked #1 on
Depth Estimation
on eBDtheque
Improving Adversarial Defense with Self-supervised Test-time Fine-tuning
Although adversarial training and its variants currently constitute the most effective way to achieve robustness against adversarial attacks, their poor generalization limits their performance on the test samples.
Fidelity Estimation Improves Noisy-Image Classification With Pretrained Networks
Furthermore, as proof of concept, we show that when using our oracle fidelity map we even outperform the fully retrained methods, whether trained on noisy or restored images.
Modeling Object Dissimilarity for Deep Saliency Prediction
Saliency prediction has made great strides over the past two decades, with current techniques modeling low-level information, such as color, intensity and size contrasts, and high-level ones, such as attention and gaze direction for entire objects.
Deep Gaussian Denoiser Epistemic Uncertainty and Decoupled Dual-Attention Fusion
While novel denoising networks were designed for real images coming from different distributions, or for specific applications, comparatively small improvement was achieved on Gaussian denoising.
BIGPrior: Towards Decoupling Learned Prior Hallucination and Data Fidelity in Image Restoration
Our method, though partly reliant on the quality of the generative network inversion, is competitive with state-of-the-art supervised and task-specific restoration methods.
AIM 2020: Scene Relighting and Illumination Estimation Challenge
The first track considered one-to-one relighting; the objective was to relight an input photo of a scene with a different color temperature and illuminant orientation (i. e., light source position).
Volumetric Transformer Networks
We design our VTN as an encoder-decoder network, with modules dedicated to letting the information flow across the feature channels, to account for the dependencies between the semantic parts.
On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them
We analyze the influence of adversarial training on the loss landscape of machine learning models.
VIDIT: Virtual Image Dataset for Illumination Transfer
Deep image relighting is gaining more interest lately, as it allows photo enhancement through illumination-specific retouching without human effort.
Editing in Style: Uncovering the Local Semantics of GANs
Focusing on StyleGAN, we introduce a simple and effective method for making local, semantically-aware edits to a target output image.
Divergence-Based Adaptive Extreme Video Completion
Extreme image or video completion, where, for instance, we only retain 1% of pixels in random locations, allows for very cheap sampling in terms of the required pre-processing.
Evaluating Salient Object Detection in Natural Images with Multiple Objects having Multi-level Saliency
In this paper, we corroborate based on three subjective experiments on a novel image dataset that objects in natural images are inherently perceived to have varying levels of importance.
Stochastic Frequency Masking to Improve Super-Resolution and Denoising Networks
Super-resolution and denoising are ill-posed yet fundamental image restoration tasks.
W2S: Microscopy Data with Joint Denoising and Super-Resolution for Widefield to SIM Mapping
To study JDSR on microscopy data, we propose such a novel JDSR dataset, Widefield2SIM (W2S), acquired using a conventional fluorescence widefield and SIM imaging.
AL2: Progressive Activation Loss for Learning General Representations in Classification Neural Networks
We propose to regularize this representation in the last feature layer before classification layers.
Image Restoration using Plug-and-Play CNN MAP Denoisers
Plug-and-play denoisers can be used to perform generic image restoration tasks independent of the degradation type.
Training Provably Robust Models by Polyhedral Envelope Regularization
Training certifiable neural networks enables one to obtain models with robustness guarantees against adversarial attacks.
Blind Universal Bayesian Image Denoising with Gaussian Noise Level Learning
Blind and universal image denoising consists of using a unique model that denoises images with any level of noise.
Ranked #1 on
Grayscale Image Denoising
on BSD68 sigma40
Drone Shadow Tracking
In this paper, we incorporate knowledge of the shadow's physical properties, in the form of shadow detection masks, into a correlation-based tracking algorithm.
Fast and Efficient Zero-Learning Image Fusion
Our method generates a single image containing features from multiple sources.
Self-Binarizing Networks
To obtain similar binary networks, existing methods rely on the sign activation function.
Detecting Memorization in ReLU Networks
We propose a new notion of `non-linearity' of a network layer with respect to an input batch that is based on its proximity to a linear system, which is reflected in the non-negative rank of the activation matrix.
Fourier-Domain Optimization for Image Processing
Image optimization problems encompass many applications such as spectral fusion, deblurring, deconvolution, dehazing, matting, reflection removal and image interpolation, among others.
Deep Feature Factorization For Concept Discovery
We propose Deep Feature Factorization (DFF), a method capable of localizing similar semantic concepts within an image or a set of images.
Ranked #5 on
Unsupervised Human Pose Estimation
on Tai-Chi-HD
Unsupervised Facial Landmark Detection
Unsupervised Human Pose Estimation
+1
Mirror, Mirror, on the Wall, Who's Got the Clearest Image of Them All? - A Tailored Approach to Single Image Reflection Removal
Removing reflection artefacts from a single image is a problem of both theoretical and practical interest, which still presents challenges because of the massively ill-posed nature of the problem.
Deep Residual Network for Joint Demosaicing and Super-Resolution
By training on high-quality samples, our deep residual demosaicing and super-resolution network is able to recover high-quality super-resolved images from low-resolution Bayer mosaics in a single step without producing the artifacts common to such processing when the two operations are done separately.
Uniform Information Segmentation
Since information is a natural way of measuring image complexity, our proposed algorithm leads to image segments that are smaller and denser in areas of high complexity and larger in homogeneous regions, thus simplifying the image while preserving its details.
God(s) Know(s): Developmental and Cross-Cultural Patterns in Children Drawings
This paper introduces a novel approach to data analysis designed for the needs of specialists in psychology of religion.
Incorporating Near-Infrared Information into Semantic Image Segmentation
Based on a state-of-the-art segmentation framework and a novel manually segmented image database (both indoor and outdoor scenes) that contain 4-channel images (RGB+NIR), we study how to best incorporate the specific characteristics of the NIR response.
