Radu Timofte

85

Papers

787

Total Citations

Papers (85)

Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations

NeurIPS 2017arXiv

InstructIR: High-Quality Image Restoration Following Human Instructions

Single-Model and Any-Modality for Video Object Tracking

Deep Equilibrium Diffusion Restoration with Parallel Sampling

Learning Transformer-based World Models with Contrastive Predictive Coding

XTrack: Multimodal Training Boosts RGB-X Video Object Trackers

Rawformer: Unpaired Raw-to-Raw Translation for Learnable Camera ISPs

Bokehlicious: Photorealistic Bokeh Rendering with Controllable Apertures

What You Have is What You Track: Adaptive and Robust Multimodal Tracking

Color Matching Using Hypernetwork-Based Kolmogorov-Arnold Networks

MIORe & VAR-MIORe: Benchmarks to Push the Boundaries of Restoration

Seven Ways to Improve Example-Based Single Image Super Resolution

Some Like It Hot - Visual Guidance for Preference Prediction

Conditional Probability Models for Deep Image Compression

Logo Synthesis and Manipulation With Clustered Generative Adversarial Networks

3D Appearance Super-Resolution With Deep Learning

Practical Full Resolution Learned Lossless Image Compression

Deep Unfolding Network for Image Super-Resolution

Learning for Video Compression With Hierarchical Quality and Recurrent Enhancement

GLU-Net: Global-Local Universal Network for Dense Flow and Correspondences

Group Sparsity: The Hinge Between Filter Pruning and Decomposition for Network Compression

Probabilistic Regression for Visual Tracking

Flow-Based Kernel Prior With Application to Blind Super-Resolution

Unsupervised Real-World Image Super Resolution via Domain-Distance Aware Training

Deep Burst Super-Resolution

Deep Homography for Efficient Stereo Image Compression

Learning Accurate Dense Correspondences and When To Trust Them

The Heterogeneity Hypothesis: Finding Layer-Wise Differentiated Network Architectures

DeFlow: Learning Complex Image Degradations From Unpaired Data With Conditional Flows

Generative Flows With Invertible Attentions

Revisiting Random Channel Pruning for Neural Network Compression

HDNet: High-Resolution Dual-Domain Learning for Spectral Compressive Imaging

Mask-Guided Spectral-Wise Transformer for Efficient Hyperspectral Image Reconstruction

Arbitrary-Scale Image Synthesis

RePaint: Inpainting Using Denoising Diffusion Probabilistic Models

Predict, Prevent, and Evaluate: Disentangled Text-Driven Image Manipulation Empowered by Pre-Trained Vision-Language Model

Graph Transformer GANs for Graph-Constrained House Generation

Single Image Depth Prediction Made Better: A Multivariate Gaussian Take

Efficient and Explicit Modelling of Image Hierarchies for Image Restoration

CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusion

CiaoSR: Continuous Implicit Attention-in-Attention Network for Arbitrary-Scale Image Super-Resolution

Anchored Regression Networks Applied to Age Estimation and Super Resolution

DSLR-Quality Photos on Mobile Devices With Deep Convolutional Networks

Generative Adversarial Networks for Extreme Learned Image Compression

Self-Guided Network for Fast Image Denoising

Fast Image Restoration With Multi-Bin Trainable Linear Units

Learning Filter Basis for Convolutional Neural Network Compression

Learning Discriminative Model Prediction for Tracking

Fourier Space Losses for Efficient Perceptual Image Super-Resolution

Designing a Practical Degradation Model for Deep Blind Image Super-Resolution

Generating Masks From Boxes by Mining Spatio-Temporal Consistencies in Videos

Towards Flexible Blind JPEG Artifacts Removal

Mutual Affine Network for Spatially Variant Kernel Estimation in Blind Image Super-Resolution

Deep Reparametrization of Multi-Frame Super-Resolution and Denoising

RipVIS: Rip Currents Video Instance Segmentation Benchmark for Beach Monitoring and Safety

Towards Efficient Graph Convolutional Networks for Point Cloud Handling

Source-free Depth for Object Pop-out

DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion

Alignment-free HDR Deghosting with Semantics Consistent Transformer

Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement

Spherical Space Feature Decomposition for Guided Depth Map Super-Resolution

SQAD: Automatic Smartphone Camera Quality Assessment and Benchmarking

Learning What to Learn for Video Object Segmentation

SRFlow: Learning the Super-Resolution Space with Normalizing Flow

DHP: Differentiable Meta Pruning via HyperNetworks

SESAME: Semantic Editing of Scenes by Adding, Manipulating or Erasing Objects

Know Your Surroundings: Exploiting Scene Information for Object Tracking

Transform Your Smartphone into a DSLR Camera: Learning the ISP in the Wild

Coarse-to-Fine Sparse Transformer for Hyperspectral Image Reconstruction

Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling

ReCap: Better Gaussian Relighting with Cross-Environment Captures

Complexity Experts are Task-Discriminative Learners for Any Image Restoration

After the Party: Navigating the Mapping From Color to Ambient Lighting

PixTalk: Controlling Photorealistic Image Processing and Editing with Language

NILUT: Conditional Neural Implicit 3D Lookup Tables for Image Enhancement

Equivariant Multi-Modality Image Fusion

Real-World Mobile Image Denoising Dataset with Efficient Baselines

Stereo Risk: A Continuous Modeling Approach to Stereo Matching

See More Details: Efficient Image Super-Resolution by Experts Mining

Metric Imitation by Manifold Transfer for Efficient Vision Applications

GOCor: Bringing Globally Optimized Correspondence Volumes into Your Neural Network

DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation

Recurrent Video Restoration Transformer with Guided Deformable Attention

Degradation-Aware Unfolding Half-Shuffle Transformer for Spectral Compressive Imaging

LART: Neural Correspondence Learning with Latent Regularization Transformer for 3D Motion Transfer