Search Results for author:
Found 89 papers, 37 papers with code
Physics-based Feature Dehazing Networks
We propose an effective feature dehazing unit (FDU), which is applied to the deep feature space to explore useful features for image dehazing based on the physics model.
Ranked #22 on
Image Dehazing
on SOTS Indoor
Learning Event-Driven Video Deblurring and Interpolation
Event-based sensors, which have a response if the change of pixel intensity exceeds a triggering threshold, can capture high-speed motion with microsecond accuracy.
MFSR: Multi-fractal Feature for Super-resolution Reconstruction with Fine Details Recovery
MFSR employs convolution as a soft assignment to approximate the fractal features of low-resolution images.
ExpRDiff: Short-exposure Guided Diffusion Model for Realistic Local Motion Deblurring
Furthermore, to restore images realistically and visually-pleasant, we develop a short-exposure guided diffusion model that explores useful features from short-exposure images and blurred regions to better constrain the diffusion process.
FoundIR: Unleashing Million-scale Training Data to Advance Foundation Models for Image Restoration
Despite the significant progress made by all-in-one models in universal image restoration, existing methods suffer from a generalization bottleneck in real-world scenarios, as they are mostly trained on small-scale synthetic datasets with limited degradations.
FaithDiff: Unleashing Diffusion Priors for Faithful Image Super-resolution
Faithful image super-resolution (SR) not only needs to recover images that appear realistic, similar to image generation tasks, but also requires that the restored images maintain fidelity and structural consistency with the input.
Super-resolving Real-world Image Illumination Enhancement: A New Dataset and A Conditional Diffusion Model
To solve this problem, we propose a SRRIIE dataset with an efficient conditional diffusion probabilistic models-based method.
Degradation Oriented and Regularized Network for Blind Depth Super-Resolution
Recent RGB-guided depth super-resolution methods have achieved impressive performance under the assumption of fixed and known degradation (e. g., bicubic downsampling).
Cascaded Temporal Updating Network for Efficient Video Super-Resolution
However, the key components in recurrent-based VSR networks significantly impact model efficiency, e. g., the alignment module occupies a substantial portion of model parameters, while the bidirectional propagation mechanism significantly amplifies the inference time.
Ultra-High-Definition Image Restoration: New Benchmarks and A Dual Interaction Prior-Driven Solution
To better utilize these priors, we introduce single prior feature interaction and dual prior feature interaction, where the former respectively fuses normal and gradient priors with high-resolution features to enhance prior ones, while the latter calculates the similarity between enhanced prior ones and further exploits dual guided filtering to boost the feature interaction of dual priors.
Technique Report of CVPR 2024 PBDL Challenges
The intersection of physics-based vision and deep learning presents an exciting frontier for advancing computer vision technologies.
Correlation Matching Transformation Transformers for UHD Image Restoration
To better improve feature representation in low-resolution space, we propose to build feature transformation from the high-resolution space to the low-resolution one.
PatchScaler: An Efficient Patch-Independent Diffusion Model for Image Super-Resolution
To further optimize the patch-level reconstruction process of PGS, we propose a texture prompt that provides rich texture conditional information to the diffusion model.
Towards Ultra-High-Definition Image Deraining: A Benchmark and An Efficient Method
In this paper, we focus on the task of UHD image deraining, and contribute the first large-scale UHD image deraining dataset, 4K-Rain13k, that contains 13, 000 image pairs at 4K resolution.
Efficient Visual State Space Model for Image Deblurring
Convolutional neural networks (CNNs) and Vision Transformers (ViTs) have achieved excellent performance in image restoration.
Real-Time 4K Super-Resolution of Compressed AVIF Images. AIS 2024 Challenge Survey
This paper introduces a novel benchmark as part of the AIS 2024 Real-Time Image Super-Resolution (RTSR) Challenge, which aims to upscale compressed images from 540p to 4K resolution (4x factor) in real-time on commercial GPUs.
The Ninth NTIRE 2024 Efficient Super-Resolution Challenge Report
In sub-track 1, the practical runtime performance of the submissions was evaluated, and the corresponding score was used to determine the ranking.
Efficient Concertormer for Image Deblurring and Beyond
By retaining partial information in additional dimensions independent from the self-attention calculations, our method effectively captures global contextual representations with complexity linear to the image size.
ColorMNet: A Memory-based Deep Spatial-Temporal Feature Propagation Network for Video Colorization
To explore this property for better spatial and temporal feature utilization, we develop a local attention module to aggregate the features from adjacent frames in a spatial-temporal neighborhood.
Collaborative Feedback Discriminative Propagation for Video Super-Resolution
However, inaccurate alignment usually leads to aligned features with significant artifacts, which will be accumulated during propagation and thus affect video restoration.
Ranked #5 on
Video Super-Resolution
on Vid4 - 4x upscaling
Bidirectional Multi-Scale Implicit Neural Representations for Image Deraining
To better explore the common degradation representations from spatially-varying rain streaks, we incorporate intra-scale implicit neural representations based on pixel coordinates with the degraded inputs in a closed-loop design, enabling the learned features to facilitate rain removal and improve the robustness of the model in complex scenarios.
Spread Your Wings: A Radial Strip Transformer for Image Deblurring
This attention module contains radial strip windows to reweight image features in the polar coordinate, which preserves more useful information in rotation and translation motion together for better recovering the sharp images.
How Powerful Potential of Attention on Image Restoration?
Our designs provide a closer look at the attention mechanism and reveal that some simple operations can significantly affect the model performance.
Scene Prior Filtering for Depth Super-Resolution
Specifically, we design an All-in-one Prior Propagation that computes the similarity between multi-modal scene priors, i. e., RGB, normal, semantic, and depth, to reduce the texture interference.
VJT: A Video Transformer on Joint Tasks of Deblurring, Low-light Enhancement and Denoising
Video restoration task aims to recover high-quality videos from low-quality observations.
Adapt or Perish: Adaptive Sparse Transformer with Attentive Feature Refinement for Image Restoration
Meanwhile FRFN employs an enhance-and-ease scheme to eliminate feature redundancy in channels enhancing the restoration of clear latent images.
Multi-task Image Restoration Guided By Robust DINO Features
To guide the restoration model with the features of DINOv2, we develop a DINO-Restore adaption and fusion module to adjust the channel of fused features from PSF and then integrate them with the features from the restoration model.
Towards Unified Deep Image Deraining: A Survey and A New Benchmark
In this paper, we provide a comprehensive review of existing image deraining method and provide a unify evaluation setting to evaluate the performance of image deraining methods.
Learning A Coarse-to-Fine Diffusion Transformer for Image Restoration
Specifically, our C2F-DFT contains diffusion self-attention (DFSA) and diffusion feed-forward network (DFN) within a new coarse-to-fine training scheme.
Deep Richardson-Lucy Deconvolution for Low-Light Image Deblurring
In this paper, we develop a data-driven approach to model the saturated pixels by a learned latent map.
Learning A Sparse Transformer Network for Effective Image Deraining
To overcome this problem, we propose an effective DeRaining network, Sparse Transformer (DRSformer) that can adaptively keep the most useful self-attention values for feature aggregation so that the aggregated features better facilitate high-quality image reconstruction.
Open-World Pose Transfer via Sequential Test-Time Adaption
In open-world conditions, the pose transfer task raises various independent signals: OOD appearance and skeleton, which need to be extracted and distributed in speciality.
SelfPromer: Self-Prompt Dehazing Transformers with Depth-Consistency
For this purpose, we develop a prompt based on the features of depth differences between the hazy input images and corresponding clear counterparts that can guide dehazing models for better restoration.
Spatially-Adaptive Feature Modulation for Efficient Image Super-Resolution
Although numerous solutions have been proposed for image super-resolution, they are usually incompatible with low-power devices with many computational and memory constraints.
Ranked #53 on
Image Super-Resolution
on Set14 - 4x upscaling
Deep Dynamic Scene Deblurring from Optical Flow
In this paper, we explore optical flow to remove dynamic scene blur by using the multi-scale spatially variant recurrent neural network (RNN).
DLGSANet: Lightweight Dynamic Local and Global Self-Attention Networks for Image Super-Resolution
We develop a hybrid dynamic-Transformer block(HDTB) that integrates the MHDLSA and SparseGSA for both local and global feature exploration.
Deep Discriminative Spatial and Temporal Network for Efficient Video Deblurring
In contrast to existing methods that directly align adjacent frames without discrimination, we develop a deep discriminative spatial and temporal network to facilitate the spatial and temporal feature exploration for better video deblurring.
Multi-Scale Residual Low-Pass Filter Network for Image Deblurring
We present a simple and effective Multi-scale Residual Low-Pass Filter Network (MRLPFNet) that jointly explores the image details and main structures for image deblurring.
BiSTNet: Semantic Image Prior Guided Bidirectional Temporal Feature Fusion for Deep Exemplar-based Video Colorization
To overcome this problem, we further develop a mixed expert block to extract semantic information for modeling the object boundaries of frames so that the semantic image prior can better guide the colorization process for better performance.
FFHQ-UV: Normalized Facial UV-Texture Dataset for 3D Face Reconstruction
Our pipeline utilizes the recent advances in StyleGAN-based facial image editing approaches to generate multi-view normalized face images from single-image inputs.
Ranked #3 on
3D Face Reconstruction
on REALY
Efficient Frequency Domain-based Transformers for High-Quality Image Deblurring
We present an effective and efficient method that explores the properties of Transformers in the frequency domain for high-quality image deblurring.
Ranked #2 on
Image Deblurring
on GoPro
(using extra training data)
SLLEN: Semantic-aware Low-light Image Enhancement Network
How to effectively explore semantic feature is vital for low-light image enhancement (LLE).
Efficient and Accurate Quantized Image Super-Resolution on Mobile NPUs, Mobile AI & AIM 2022 challenge: Report
While numerous solutions have been proposed for this problem in the past, they are usually not compatible with low-power mobile NPUs having many computational and memory constraints.
DnSwin: Toward Real-World Denoising via Continuous Wavelet Sliding-Transformer
Real-world image denoising is a practical image restoration problem that aims to obtain clean images from in-the-wild noisy inputs.
Boosting Video Super Resolution with Patch-Based Temporal Redundancy Optimization
We develop two simple yet effective plug and play methods to improve the performance of existing local and non-local propagation-based VSR algorithms on widely-used public videos.
Structural Prior Guided Generative Adversarial Transformers for Low-Light Image Enhancement
The generator is based on a U-shaped Transformer which is used to explore non-local information for better clear image restoration.
Real-World Image Super-Resolution by Exclusionary Dual-Learning
Real-world image super-resolution is a practical image restoration problem that aims to obtain high-quality images from in-the-wild input, has recently received considerable attention with regard to its tremendous application potentials.
ShuffleMixer: An Efficient ConvNet for Image Super-Resolution
We propose a simple and effective approach, ShuffleMixer, for lightweight image super-resolution that explores large convolution and channel split-shuffle operation.
NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results
The aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics including runtime, parameters, FLOPs, activations, and memory consumption while at least maintaining the PSNR of 29. 00dB on DIV2K validation set.
Online-updated High-order Collaborative Networks for Single Image Deraining
Most of the existing deep-learning-based methods constrain the network to generate derained images but few of them explore features from intermediate layers, different levels, and different modules which are beneficial for rain streaks removal.
Memory-augmented Deep Unfolding Network for Guided Image Super-resolution
Guided image super-resolution (GISR) aims to obtain a high-resolution (HR) target image by enhancing the spatial resolution of a low-resolution (LR) target image under the guidance of a HR image.
Self-Supervised Deep Blind Video Super-Resolution
As directly using LR videos as supervision usually leads to trivial solutions, we develop a simple and effective method to generate auxiliary paired data from original LR videos according to the image formation of video SR, so that the networks can be better constrained by the generated paired data for both blur kernel estimation and latent HR video restoration.
Deep Recurrent Neural Network with Multi-scale Bi-directional Propagation for Video Deblurring
Instead of estimating alignment information, we propose a simple and effective deep Recurrent Neural Network with Multi-scale Bi-directional Propagation (RNN-MBP) to effectively propagate and gather the information from unaligned neighboring frames for better video deblurring.
Ranked #20 on
Deblurring
on GoPro
Learning Discriminative Shrinkage Deep Networks for Image Deconvolution
Most existing methods usually formulate the non-blind deconvolution problem into a maximum-a-posteriori framework and address it by manually designing kinds of regularization terms and data terms of the latent clear images.
Unpaired Deep Image Deraining Using Dual Contrastive Learning
Learning single image deraining (SID) networks from an unpaired set of clean and rainy images is practical and valuable as acquiring paired real-world data is almost infeasible.
Learning a Non-Blind Deblurring Network for Night Blurry Images
Deblurring night blurry images is difficult, because the common-used blur model based on the linear convolution operation does not hold in this situation due to the influence of saturated pixels.
Learning To Restore Hazy Video: A New Real-World Dataset and a New Method
On the other hand, the video dehazing algorithms, which can acquire more satisfying dehazing results by exploiting the temporal redundancy from neighborhood hazy frames, receive less attention due to the absence of the video dehazing datasets.
Image De-Raining via Continual Learning
The proposed model is capable of achieving superior performance on both inhomogeneous and incremental datasets, and is promising for highly compact systems to gradually learn myriad regularities of the different types of rain streaks.
Unpaired Learning for Deep Image Deraining With Rain Direction Regularizer
With the estimated rain maps from the semi-supervised learning part, we first synthesize a new paired set by adding to rain-free images based on the superimposition model.
Multi-Scale Boosted Dehazing Network with Dense Feature Fusion
To address the issue of preserving spatial information in the U-Net architecture, we design a dense feature fusion module using the back-projection feedback scheme.
Ranked #11 on
Image Dehazing
on Haze4k
Cascaded Deep Video Deblurring Using Temporal Sharpness Prior
The proposed algorithm mainly consists of optical flow estimation from intermediate latent frames and latent frame restoration steps.
Ranked #2 on
Deblurring
on Beam-Splitter Deblurring (BSD)
Deep Blind Video Super-resolution
Existing video super-resolution (SR) algorithms usually assume that the blur kernels in the degradation process are known and do not model the blur kernels in the restoration.
Image Formation Model Guided Deep Image Super-Resolution
We present a simple and effective image super-resolution algorithm that imposes an image formation constraint on the deep neural networks via pixel substitution.
Spatially Variant Linear Representation Models for Joint Filtering
Different from existing algorithms that rely on locally linear models or hand-designed objective functions to extract the structural information from the guidance image, we propose a new joint filter based on a spatially variant linear representation model (SVLRM), where the target image is linearly represented by the guidance image.
Spatio-Temporal Filter Adaptive Network for Video Deblurring
To overcome the limitation of separate optical flow estimation, we propose a Spatio-Temporal Filter Adaptive Network (STFAN) for the alignment and deblurring in a unified framework.
Ranked #3 on
Deblurring
on DVD
(using extra training data)
DAVANet: Stereo Deblurring with View Aggregation
Nowadays stereo cameras are more commonly adopted in emerging devices such as dual-lens smartphones and unmanned aerial vehicles.
Deep Non-Blind Deconvolution via Generalized Low-Rank Approximation
In this paper, we present a deep convolutional neural network to capture the inherent properties of image degradation, which can handle different kernels and saturated pixels in a unified framework.
Joint Face Hallucination and Deblurring via Structure Generation and Detail Enhancement
We first propose a facial component guided deep Convolutional Neural Network (CNN) to restore a coarse face image, which is denoted as the base image where the facial component is automatically generated from the input face image.
Learning Data Terms for Non-blind Deblurring
We propose a simple and effective discriminative framework to learn data terms that can adaptively handle blurred images in the presence of severe noise and outliers.
Physics-Based Generative Adversarial Models for Image Restoration and Beyond
We present an algorithm to directly solve numerous image restoration problems (e. g., image deblurring, image dehazing, image deraining, etc.).
Dynamic Scene Deblurring Using Spatially Variant Recurrent Neural Networks
The proposed network is composed of three deep convolutional neural networks (CNNs) and a recurrent neural network (RNN).
Ranked #11 on
Deblurring
on RealBlur-R (trained on GoPro)
(SSIM (sRGB) metric)
Single Image Dehazing via Conditional Generative Adversarial Network
In contrast, we solve this problem based on a conditional generative adversarial network (cGAN), where the clear image is estimated by an end-to-end trainable neural network.
Learning to Deblur Images with Exemplars
However, existing methods are less effective as only few edges can be restored from blurry face images for kernel estimation.
Learning Dual Convolutional Neural Networks for Low-Level Vision
These problems usually involve the estimation of two components of the target signals: structures and details.
Gated Fusion Network for Single Image Dehazing
The proposed algorithm hinges on an end-to-end trainable neural network that consists of an encoder and a decoder.
Ranked #28 on
Image Dehazing
on SOTS Indoor
Learning a Discriminative Prior for Blind Image Deblurring
We present an effective blind image deblurring method based on a data-driven discriminative prior. Our work is motivated by the fact that a good image prior should favor clear images over blurred images. In this work, we formulate the image prior as a binary classifier which can be achieved by a deep convolutional neural network (CNN). The learned prior is able to distinguish whether an input image is clear or not. Embedded into the maximum a posterior (MAP) framework, it helps blind deblurring in various scenarios, including natural, face, text, and low-illumination images. However, it is difficult to optimize the deblurring method with the learned image prior as it involves a non-linear CNN. Therefore, we develop an efficient numerical approach based on the half-quadratic splitting method and gradient decent algorithm to solve the proposed model. Furthermore, the proposed model can be easily extended to non-uniform deblurring. Both qualitative and quantitative experimental results show that our method performs favorably against state-of-the-art algorithms as well as domain-specific image deblurring approaches.
Deep Blind Image Inpainting
However, directly using exist- ing residual learning algorithms in image restoration does not well solve this problem as little information is available in the corrupted regions.
LSTM Pose Machines
Such suboptimal results are mainly attributed to the inability of imposing sequential geometric consistency, handling severe image quality degradation (e. g. motion blur and occlusion) as well as the inability of capturing the temporal correlation among video frames.
Ranked #3 on
Pose Estimation
on J-HMDB
Image Dehazing using Bilinear Composition Loss Function
In this paper, we introduce a bilinear composition loss function to address the problem of image dehazing.
Learning to Super-Resolve Blurry Face and Text Images
We present an algorithm to directly restore a clear high-resolution image from a blurry low-resolution input.
Learning Discriminative Data Fitting Functions for Blind Image Deblurring
Solving blind image deblurring usually requires defining a data fitting function and image priors.
Blind Image Deblurring With Outlier Handling
We analyze the relationship between the proposed algorithm and other blind deblurring methods with outlier handling and show how to estimate intermediate latent images for blur kernel estimation principally.
Video Deblurring via Semantic Segmentation and Pixel-Wise Non-Linear Kernel
We analyze the relationship between motion blur trajectory and optical flow, and present a novel pixel-wise non-linear kernel model to account for motion blur.
Learning Fully Convolutional Networks for Iterative Non-blind Deconvolution
In this paper, we propose a fully convolutional networks for iterative non-blind deconvolution We decompose the non-blind deconvolution problem into image denoising and image deconvolution.
Blind Image Deblurring Using Dark Channel Prior
Therefore, enforcing the sparsity of the dark channel helps blind deblurring on various scenarios, including natural, face, text, and low-illumination images.
Ranked #11 on
Deblurring
on RealBlur-R (trained on GoPro)
Soft-Segmentation Guided Object Motion Deblurring
To address these problems, we propose a novel model for object motion deblurring.
Robust Kernel Estimation With Outliers Handling for Image Deblurring
Estimating blur kernels from real world images is a challenging problem as the linear image formation assumption does not hold when significant outliers, such as saturated pixels and non-Gaussian noise, are present.
Deblurring Text Images via L0-Regularized Intensity and Gradient Prior
We propose a simple yet effective L_0-regularized prior based on intensity and gradient for text image deblurring.
Kernel Estimation from Salient Structure for Robust Motion Deblurring
One effective way to eliminate these details is to apply image denoising model based on the Total Variation (TV).
