Zhi-Song Liu

Heikki Haario, Zhi-Song Liu, Martin Simon et al.

Neural networks are a commonly used approach to replace physical models with computationally cheap surrogates. Parametric uncertainty quantification can be included in training, assuming that an accurate prior distribution of the model parameters is available. Here we study the common opposite situation, where direct screening or random sampling of model parameters leads to exhaustive training times and evaluations at unphysical parameter values. Our solution is to decouple uncertainty quantification from network architecture. Instead of sampling network weights, we introduce the model-parameter distribution as an input to network training via Markov chain Monte Carlo (MCMC). In this way, the surrogate achieves the same uncertainty quantification as the underlying physical model, but with substantially reduced computation time. The approach is fully agnostic with respect to the neural network choice. In our examples, we present a quantile emulator for prediction and a novel autoencoder-based ODE network emulator that can flexibly estimate different trajectory paths corresponding to different ODE model parameters. Moreover, we present a mathematical analysis that provides a transparent way to relate potential performance loss to measurable distribution mismatch.

Zhi-Song Liu, Zijia Wang, Zhen Jia

Continuous image super-resolution (SR) recently receives a lot of attention from researchers, for its practical and flexible image scaling for various displays. Local implicit image representation is one of the methods that can map the coordinates and 2D features for latent space interpolation. Inspired by Variational AutoEncoder, we propose a Soft-introVAE for continuous latent space image super-resolution (SVAE-SR). A novel latent space adversarial training is achieved for photo-realistic image restoration. To further improve the quality, a positional encoding scheme is used to extend the original pixel coordinates by aggregating frequency information over the pixel areas. We show the effectiveness of the proposed SVAE-SR through quantitative and qualitative comparisons, and further, illustrate its generalization in denoising and real-image super-resolution.

Zhi-Song Liu, Chenhang He, Roland Maier et al.

Recent advances in generative modeling have demonstrated strong promise for high-quality point cloud upsampling. In this work, we present PUFM++, an enhanced flow-matching framework for reconstructing dense and accurate point clouds from sparse, noisy, and partial observations. PUFM++ improves flow matching along three key axes: (i) geometric fidelity, (ii) robustness to imperfect input, and (iii) consistency with downstream surface-based tasks. We introduce a two-stage flow-matching strategy that first learns a direct, straight-path flow from sparse inputs to dense targets, and then refines it using noise-perturbed samples to approximate the terminal marginal distribution better. To accelerate and stabilize inference, we propose a data-driven adaptive time scheduler that improves sampling efficiency based on interpolation behavior. We further impose on-manifold constraints during sampling to ensure that generated points remain aligned with the underlying surface. Finally, we incorporate a recurrent interface network~(RIN) to strengthen hierarchical feature interactions and boost reconstruction quality. Extensive experiments on synthetic benchmarks and real-world scans show that PUFM++ sets a new state of the art in point cloud upsampling, delivering superior visual fidelity and quantitative accuracy across a wide range of tasks. Code and pretrained models are publicly available at https://github.com/Holmes-Alan/Enhanced_PUFM.

Ammar Kheder, Helmi Toropainen, Wenqing Peng et al.

Vision Transformers have achieved remarkable success in spatio-temporal prediction, but their scalability remains limited for ultra-high-resolution, continent-scale domains required in real-world environmental monitoring. A single European air-quality map at 1 km resolution comprises 29 million pixels, far beyond the limits of naive self-attention. We introduce CRAN-PM, a dual-branch Vision Transformer that leverages cross-resolution attention to efficiently fuse global meteorological data (25 km) with local high-resolution PM2.5 at the current time (1 km). Instead of including physically driven factors like temperature and topography as input, we further introduce elevation-aware self-attention and wind-guided cross-attention to force the network to learn physically consistent feature representations for PM2.5 forecasting. CRAN-PM is fully trainable and memory-efficient, generating the complete 29-million-pixel European map in 1.8 seconds on a single GPU. Evaluated on daily PM2.5 forecasting throughout Europe in 2022 (362 days, 2,971 European Environment Agency (EEA) stations), it reduces RMSE by 4.7% at T+1 and 10.7% at T+3 compared to the best single-scale baseline, while reducing bias in complex terrain by 36%.

Zhi-Song Liu, Markus Büttner, Matthew Scarborough et al.

Learning the fine-scale details of a coastal ocean simulation from a coarse representation is a challenging task. For real-world applications, high-resolution simulations are necessary to advance understanding of many coastal processes, specifically, to predict flooding resulting from tsunamis and storm surges. We propose a Downscaling Neural Network for Coastal Simulation (DNNCS) for spatiotemporal enhancement to learn the high-resolution numerical solution. Given images of coastal simulations produced on low-resolution computational meshes using low polynomial order discontinuous Galerkin discretizations and a coarse temporal resolution, the proposed DNNCS learns to produce high-resolution free surface elevation and velocity visualizations in both time and space. To model the dynamic changes over time and space, we propose grid-aware spatiotemporal attention to project the temporal features to the spatial domain for non-local feature matching. The coordinate information is also utilized via positional encoding. For the final reconstruction, we use the spatiotemporal bilinear operation to interpolate the missing frames and then expand the feature maps to the frequency domain for residual mapping. Besides data-driven losses, the proposed physics-informed loss guarantees gradient consistency and momentum changes, leading to a 24% reduction in root-mean-square error compared to the model trained with only data-driven losses. To train the proposed model, we propose a coastal simulation dataset and use it for model optimization and evaluation. Our method shows superior downscaling quality and fast computation compared to the state-of-the-art methods.

Zhi-Song Liu, Petri Clusius, Michael Boy

Modeling atmospheric chemistry is complex and computationally intense. Given the recent success of Deep neural networks in digital signal processing, we propose a Neural Network Emulator for fast chemical concentration modeling. We consider atmospheric chemistry as a time-dependent Ordinary Differential Equation. To extract the hidden correlations between initial states and future time evolution, we propose ChemNNE, an Attention based Neural Network Emulator (NNE) that can model the atmospheric chemistry as a neural ODE process. To efficiently simulate the chemical changes, we propose the sinusoidal time embedding to estimate the oscillating tendency over time. More importantly, we use the Fourier neural operator to model the ODE process for efficient computation. We also propose three physical-informed losses to supervise the training optimization. To evaluate our model, we propose a large-scale chemical dataset that can be used for neural network training and evaluation. The extensive experiments show that our approach achieves state-of-the-art performance in modeling accuracy and computational speed.

Zhi-Song Liu, Zijia Wang, Zhen Jia

Point clouds acquired from 3D sensors are usually sparse and noisy. Point cloud upsampling is an approach to increase the density of the point cloud so that detailed geometric information can be restored. In this paper, we propose a Dual Back-Projection network for point cloud upsampling (DBPnet). A Dual Back-Projection is formulated in an up-down-up manner for point cloud upsampling. It not only back projects feature residues but also coordinates residues so that the network better captures the point correlations in the feature and space domains, achieving lower reconstruction errors on both uniform and non-uniform sparse point clouds. Our proposed method is also generalizable for arbitrary upsampling tasks (e.g. 4x, 5.5x). Experimental results show that the proposed method achieves the lowest point set matching losses with respect to the benchmark. In addition, the success of our approach demonstrates that generative networks are not necessarily needed for non-uniform point clouds.

Zhi-Song Liu, Wenqing Peng, Helmi Toropainen et al.

We propose the Inverse Neural Operator (INO), a two-stage framework for recovering hidden ODE parameters from sparse, partial observations. In Stage 1, a Conditional Fourier Neural Operator (C-FNO) with cross-attention learns a differentiable surrogate that reconstructs full ODE trajectories from arbitrary sparse inputs, suppressing high-frequency artifacts via spectral regularization. In Stage 2, an Amortized Drifting Model (ADM) learns a kernel-weighted velocity field in parameter space, transporting random parameter initializations toward the ground truth without backpropagating through the surrogate, avoiding the Jacobian instabilities that afflict gradient-based inversion in stiff regimes. Experiments on a real-world stiff atmospheric chemistry benchmark (POLLU, 25 parameters) and a synthetic Gene Regulatory Network (GRN, 40 parameters) show that INO outperforms gradient-based and amortized baselines in parameter recovery accuracy while requiring only 0.23s inference time, a 487x speedup over iterative gradient descent.

Ammar Kheder, Helmi Toropainen, Wenqing Peng et al.

We propose TopoFlow (Topography-aware pollutant Flow learning), a physics-guided neural network for efficient, high-resolution air quality prediction. To explicitly embed physical processes into the learning framework, we identify two critical factors governing pollutant dynamics: topography and wind direction. Complex terrain can channel, block, and trap pollutants, while wind acts as a primary driver of their transport and dispersion. Building on these insights, TopoFlow leverages a vision transformer architecture with two novel mechanisms: topography-aware attention, which explicitly models terrain-induced flow patterns, and wind-guided patch reordering, which aligns spatial representations with prevailing wind directions. Trained on six years of high-resolution reanalysis data assimilating observations from over 1,400 surface monitoring stations across China, TopoFlow achieves a PM2.5 RMSE of 9.71 ug/m3, representing a 71-80% improvement over operational forecasting systems and a 13% improvement over state-of-the-art AI baselines. Forecast errors remain well below China's 24-hour air quality threshold of 75 ug/m3 (GB 3095-2012), enabling reliable discrimination between clean and polluted conditions. These performance gains are consistent across all four major pollutants and forecast lead times from 12 to 96 hours, demonstrating that principled integration of physical knowledge into neural networks can fundamentally advance air quality prediction.

Zhi-Song Liu, Robin Courant, Vicky Kalogeiton

Automatically understanding funny moments (i.e., the moments that make people laugh) when watching comedy is challenging, as they relate to various features, such as body language, dialogues and culture. In this paper, we propose FunnyNet-W, a model that relies on cross- and self-attention for visual, audio and text data to predict funny moments in videos. Unlike most methods that rely on ground truth data in the form of subtitles, in this work we exploit modalities that come naturally with videos: (a) video frames as they contain visual information indispensable for scene understanding, (b) audio as it contains higher-level cues associated with funny moments, such as intonation, pitch and pauses and (c) text automatically extracted with a speech-to-text model as it can provide rich information when processed by a Large Language Model. To acquire labels for training, we propose an unsupervised approach that spots and labels funny audio moments. We provide experiments on five datasets: the sitcoms TBBT, MHD, MUStARD, Friends, and the TED talk UR-Funny. Extensive experiments and analysis show that FunnyNet-W successfully exploits visual, auditory and textual cues to identify funny moments, while our findings reveal FunnyNet-W's ability to predict funny moments in the wild. FunnyNet-W sets the new state of the art for funny moment detection with multimodal cues on all datasets with and without using ground truth information.

Zijia Wang, Zhi-Song Liu

We present StyleMamba, an efficient image style transfer framework that translates text prompts into corresponding visual styles while preserving the content integrity of the original images. Existing text-guided stylization requires hundreds of training iterations and takes a lot of computing resources. To speed up the process, we propose a conditional State Space Model for Efficient Text-driven Image Style Transfer, dubbed StyleMamba, that sequentially aligns the image features to the target text prompts. To enhance the local and global style consistency between text and image, we propose masked and second-order directional losses to optimize the stylization direction to significantly reduce the training iterations by 5 times and the inference time by 3 times. Extensive experiments and qualitative evaluation confirm the robust and superior stylization performance of our methods compared to the existing baselines.

Zhi-Song Liu, Marie-Paule Cani, Wan-Chi Siu

We present See360, which is a versatile and efficient framework for 360 panoramic view interpolation using latent space viewpoint estimation. Most of the existing view rendering approaches only focus on indoor or synthetic 3D environments and render new views of small objects. In contrast, we suggest to tackle camera-centered view synthesis as a 2D affine transformation without using point clouds or depth maps, which enables an effective 360? panoramic scene exploration. Given a pair of reference images, the See360 model learns to render novel views by a proposed novel Multi-Scale Affine Transformer (MSAT), enabling the coarse-to-fine feature rendering. We also propose a Conditional Latent space AutoEncoder (C-LAE) to achieve view interpolation at any arbitrary angle. To show the versatility of our method, we introduce four training datasets, namely UrbanCity360, Archinterior360, HungHom360 and Lab360, which are collected from indoor and outdoor environments for both real and synthetic rendering. Experimental results show that the proposed method is generic enough to achieve real-time rendering of arbitrary views for all four datasets. In addition, our See360 model can be applied to view synthesis in the wild: with only a short extra training time (approximately 10 mins), and is able to render unknown real-world scenes. The superior performance of See360 opens up a promising direction for camera-centered view rendering and 360 panoramic view interpolation.

Zhi-Song Liu, Chenhang He, Lei Li

Diffusion models are a powerful framework for tackling ill-posed problems, with recent advancements extending their use to point cloud upsampling. Despite their potential, existing diffusion models struggle with inefficiencies as they map Gaussian noise to real point clouds, overlooking the geometric information inherent in sparse point clouds. To address these inefficiencies, we propose PUFM, a flow matching approach to directly map sparse point clouds to their high-fidelity dense counterparts. Our method first employs midpoint interpolation to sparse point clouds, resolving the density mismatch between sparse and dense point clouds. Since point clouds are unordered representations, we introduce a pre-alignment method based on Earth Mover's Distance (EMD) optimization to ensure coherent interpolation between sparse and dense point clouds, which enables a more stable learning path in flow matching. Experiments on synthetic datasets demonstrate that our method delivers superior upsampling quality but with fewer sampling steps. Further experiments on ScanNet and KITTI also show that our approach generalizes well on RGB-D point clouds and LiDAR point clouds, making it more practical for real-world applications.

Ammar Kheder, Benjamin Foreback, Lili Wang et al.

Air quality prediction is key to mitigating health impacts and guiding decisions, yet existing models tend to focus on temporal trends while overlooking spatial generalization. We propose AQ-Net, a spatiotemporal reanalysis model for both observed and unobserved stations in the near future. AQ-Net utilizes the LSTM and multi-head attention for the temporal regression. We also propose a cyclic encoding technique to ensure continuous time representation. To learn fine-grained spatial air quality estimation, we incorporate AQ-Net with the neural kNN to explore feature-based interpolation, such that we can fill the spatial gaps given coarse observation stations. To demonstrate the efficiency of our model for spatiotemporal reanalysis, we use data from 2013-2017 collected in northern China for PM2.5 analysis. Extensive experiments show that AQ-Net excels in air quality reanalysis, highlighting the potential of hybrid spatio-temporal models to better capture environmental dynamics, especially in urban areas where both spatial and temporal variability are critical.

Wenqing Peng, Zhi-Song Liu, Michael Boy

Estimating rate coefficients from complex chemical reactions is essential for advancing detailed chemistry. However, the stiffness inherent in real-world atmospheric chemistry systems poses severe challenges, leading to training instability and poor convergence, which hinder effective rate coefficient estimation using learning-based approaches. To address this, we propose a Stiff Physics-Informed Neural ODE framework (SPIN-ODE) for chemical reaction modelling. Our method introduces a three-stage optimisation process: first, a black-box neural ODE is trained to fit concentration trajectories; second, a Chemical Reaction Neural Network (CRNN) is pre-trained to learn the mapping between concentrations and their time derivatives; and third, the rate coefficients are fine-tuned by integrating with the pre-trained CRNN. Extensive experiments on both synthetic and newly proposed real-world datasets validate the effectiveness and robustness of our approach. As the first work addressing stiff neural ODE for chemical rate coefficient discovery, our study opens promising directions for integrating neural networks with detailed chemistry.

Ilmari Vahteristo, Zhi-Song Liu, Andreas Rupp

Reconstructing an image from its Radon transform is a fundamental computed tomography (CT) task arising in applications such as X-ray scans. In many practical scenarios, a full 180-degree scan is not feasible, or there is a desire to reduce radiation exposure. In these limited-angle settings, the problem becomes ill-posed, and methods designed for full-view data often leave significant artifacts. We propose a very low-data approach to reconstruct the original image from its Radon transform under severe angle limitations. Because the inverse problem is ill-posed, we combine multiple regularization methods, including Total Variation, a sinogram filter, Deep Image Prior, and a patch-level autoencoder. We use a differentiable implementation of the Radon transform, which allows us to use gradient-based techniques to solve the inverse problem. Our method is evaluated on a dataset from the Helsinki Tomography Challenge 2022, where the goal is to reconstruct a binary disk from its limited-angle sinogram. We only use a total of 12 data points--eight for learning a prior and four for hyperparameter selection--and achieve results comparable to the best synthetic data-driven approaches.

Zhi-Song Liu, Roland Maier, Andreas Rupp

Finite element methods typically require a high resolution to satisfactorily approximate micro and even macro patterns of an underlying physical model. This issue can be circumvented by appropriate numerical homogenization or multiscale strategies that are able to obtain reasonable approximations on under-resolved scales. In this paper, we study the implicit neural representation and propose a continuous super-resolution network as a numerical homogenization strategy. It can take coarse finite element data to learn both in-distribution and out-of-distribution high-resolution finite element predictions. Our highlight is the design of a local implicit transformer, which is able to learn multiscale features. We also propose Gabor wavelet-based coordinate encodings which can overcome the bias of neural networks learning low-frequency features. Finally, perception is often preferred over distortion so scientists can recognize the visual pattern for further investigation. However, implicit neural representation is known for its lack of local pattern supervision. We propose to use stochastic cosine similarities to compare the local feature differences between prediction and ground truth. It shows better performance on structural alignments. Our experiments show that our proposed strategy achieves superior performance as an in-distribution and out-of-distribution super-resolution strategy.

Zhi-Song Liu, Li-Wen Wang, Jun Xiao et al.

Image style transfer has attracted widespread attention in the past few years. Despite its remarkable results, it requires additional style images available as references, making it less flexible and inconvenient. Using text is the most natural way to describe the style. More importantly, text can describe implicit abstract styles, like styles of specific artists or art movements. In this paper, we propose a Contrastive Learning for Artistic Style Transfer (CLAST) that leverages advanced image-text encoders to control arbitrary style transfer. We introduce a supervised contrastive training strategy to effectively extract style descriptions from the image-text model (i.e., CLIP), which aligns stylization with the text description. To this end, we also propose a novel and efficient adaLN based state space models that explore style-content fusion. Finally, we achieve a text-driven image style transfer. Extensive experiments demonstrate that our approach outperforms the state-of-the-art methods in artistic style transfer. More importantly, it does not require online fine-tuning and can render a 512x512 image in 0.03s.

Zhi-Song Liu, Li-Wen Wang, Wan-Chi Siu et al.

Image style transfer has attracted widespread attention in the past few years. Despite its remarkable results, it requires additional style images available as references, making it less flexible and inconvenient. Using text is the most natural way to describe the style. More importantly, text can describe implicit abstract styles, like styles of specific artists or art movements. In this paper, we propose a text-driven image style transfer (TxST) that leverages advanced image-text encoders to control arbitrary style transfer. We introduce a contrastive training strategy to effectively extract style descriptions from the image-text model (i.e., CLIP), which aligns stylization with the text description. To this end, we also propose a novel and efficient attention module that explores cross-attentions to fuse style and content features. Finally, we achieve an arbitrary artist-aware image style transfer to learn and transfer specific artistic characters such as Picasso, oil painting, or a rough sketch. Extensive experiments demonstrate that our approach outperforms the state-of-the-art methods on both image and textual styles. Moreover, it can mimic the styles of one or many artists to achieve attractive results, thus highlighting a promising direction in image style transfer.

Zhi-Song Liu, Vicky Kalogeiton, Marie-Paule Cani

Modern works on style transfer focus on transferring style from a single image. Recently, some approaches study multiple style transfer; these, however, are either too slow or fail to mix multiple styles. We propose ST-VAE, a Variational AutoEncoder for latent space-based style transfer. It performs multiple style transfer by projecting nonlinear styles to a linear latent space, enabling to merge styles via linear interpolation before transferring the new style to the content image. To evaluate ST-VAE, we experiment on COCO for single and multiple style transfer. We also present a case study revealing that ST-VAE outperforms other methods while being faster, flexible, and setting a new path for multiple style transfer.

Zhi-Song Liu, Wan-Chi Siu, Li-Wen Wang

In this paper, we propose a novel reference based image super-resolution approach via Variational AutoEncoder (RefVAE). Existing state-of-the-art methods mainly focus on single image super-resolution which cannot perform well on large upsampling factors, e.g., 8$\times$. We propose a reference based image super-resolution, for which any arbitrary image can act as a reference for super-resolution. Even using random map or low-resolution image itself, the proposed RefVAE can transfer the knowledge from the reference to the super-resolved images. Depending upon different references, the proposed method can generate different versions of super-resolved images from a hidden super-resolution space. Besides using different datasets for some standard evaluations with PSNR and SSIM, we also took part in the NTIRE2021 SR Space challenge and have provided results of the randomness evaluation of our approach. Compared to other state-of-the-art methods, our approach achieves higher diverse scores.

Majed El Helou, Ruofan Zhou, Sabine Süsstrunk et al.

We review the AIM 2020 challenge on virtual image relighting and illumination estimation. This paper presents the novel VIDIT dataset used in the challenge and the different proposed solutions and final evaluation results over the 3 challenge tracks. 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). The goal of the second track was to estimate illumination settings, namely the color temperature and orientation, from a given image. Lastly, the third track dealt with any-to-any relighting, thus a generalization of the first track. The target color temperature and orientation, rather than being pre-determined, are instead given by a guide image. Participants were allowed to make use of their track 1 and 2 solutions for track 3. The tracks had 94, 52, and 56 registered participants, respectively, leading to 20 confirmed submissions in the final competition stage.

Pengxu Wei, Hannan Lu, Radu Timofte et al.

This paper introduces the real image Super-Resolution (SR) challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2020. This challenge involves three tracks to super-resolve an input image for $\times$2, $\times$3 and $\times$4 scaling factors, respectively. The goal is to attract more attention to realistic image degradation for the SR task, which is much more complicated and challenging, and contributes to real-world image super-resolution applications. 452 participants were registered for three tracks in total, and 24 teams submitted their results. They gauge the state-of-the-art approaches for real image SR in terms of PSNR and SSIM.

Li-Wen Wang, Wan-Chi Siu, Zhi-Song Liu et al.

Manipulating the light source of given images is an interesting task and useful in various applications, including photography and cinematography. Existing methods usually require additional information like the geometric structure of the scene, which may not be available for most images. In this paper, we formulate the single image relighting task and propose a novel Deep Relighting Network (DRN) with three parts: 1) scene reconversion, which aims to reveal the primary scene structure through a deep auto-encoder network, 2) shadow prior estimation, to predict light effect from the new light direction through adversarial learning, and 3) re-renderer, to combine the primary structure with the reconstructed shadow view to form the required estimation under the target light source. Experimental results show that the proposed method outperforms other possible methods, both qualitatively and quantitatively. Specifically, the proposed DRN has achieved the best PSNR in the "AIM2020 - Any to one relighting challenge" of the 2020 ECCV conference.

Chu-Tak Li, Wan-Chi Siu, Zhi-Song Liu et al.

The degree of difficulty in image inpainting depends on the types and sizes of the missing parts. Existing image inpainting approaches usually encounter difficulties in completing the missing parts in the wild with pleasing visual and contextual results as they are trained for either dealing with one specific type of missing patterns (mask) or unilaterally assuming the shapes and/or sizes of the masked areas. We propose a deep generative inpainting network, named DeepGIN, to handle various types of masked images. We design a Spatial Pyramid Dilation (SPD) ResNet block to enable the use of distant features for reconstruction. We also employ Multi-Scale Self-Attention (MSSA) mechanism and Back Projection (BP) technique to enhance our inpainting results. Our DeepGIN outperforms the state-of-the-art approaches generally, including two publicly available datasets (FFHQ and Oxford Buildings), both quantitatively and qualitatively. We also demonstrate that our model is capable of completing masked images in the wild.

Andreas Lugmayr, Martin Danelljan, Radu Timofte et al.

This paper reviews the NTIRE 2020 challenge on real world super-resolution. It focuses on the participating methods and final results. The challenge addresses the real world setting, where paired true high and low-resolution images are unavailable. For training, only one set of source input images is therefore provided along with a set of unpaired high-quality target images. In Track 1: Image Processing artifacts, the aim is to super-resolve images with synthetically generated image processing artifacts. This allows for quantitative benchmarking of the approaches \wrt a ground-truth image. In Track 2: Smartphone Images, real low-quality smart phone images have to be super-resolved. In both tracks, the ultimate goal is to achieve the best perceptual quality, evaluated using a human study. This is the second challenge on the subject, following AIM 2019, targeting to advance the state-of-the-art in super-resolution. To measure the performance we use the benchmark protocol from AIM 2019. In total 22 teams competed in the final testing phase, demonstrating new and innovative solutions to the problem.

Zhi-Song Liu, Wan-Chi Siu, Li-Wen Wang et al.

Benefited from the deep learning, image Super-Resolution has been one of the most developing research fields in computer vision. Depending upon whether using a discriminator or not, a deep convolutional neural network can provide an image with high fidelity or better perceptual quality. Due to the lack of ground truth images in real life, people prefer a photo-realistic image with low fidelity to a blurry image with high fidelity. In this paper, we revisit the classic example based image super-resolution approaches and come up with a novel generative model for perceptual image super-resolution. Given that real images contain various noise and artifacts, we propose a joint image denoising and super-resolution model via Variational AutoEncoder. We come up with a conditional variational autoencoder to encode the reference for dense feature vector which can then be transferred to the decoder for target image denoising. With the aid of the discriminator, an additional overhead of super-resolution subnetwork is attached to super-resolve the denoised image with photo-realistic visual quality. We participated the NTIRE2020 Real Image Super-Resolution Challenge. Experimental results show that by using the proposed approach, we can obtain enlarged images with clean and pleasant features compared to other supervised methods. We also compared our approach with state-of-the-art methods on various datasets to demonstrate the efficiency of our proposed unsupervised super-resolution model.

Zhi-Song Liu, Li-Wen Wang, Chu-Tak Li et al.

Deep learning based image Super-Resolution (SR) has shown rapid development due to its ability of big data digestion. Generally, deeper and wider networks can extract richer feature maps and generate SR images with remarkable quality. However, the more complex network we have, the more time consumption is required for practical applications. It is important to have a simplified network for efficient image SR. In this paper, we propose an Attention based Back Projection Network (ABPN) for image super-resolution. Similar to some recent works, we believe that the back projection mechanism can be further developed for SR. Enhanced back projection blocks are suggested to iteratively update low- and high-resolution feature residues. Inspired by recent studies on attention models, we propose a Spatial Attention Block (SAB) to learn the cross-correlation across features at different layers. Based on the assumption that a good SR image should be close to the original LR image after down-sampling. We propose a Refined Back Projection Block (RBPB) for final reconstruction. Extensive experiments on some public and AIM2019 Image Super-Resolution Challenge datasets show that the proposed ABPN can provide state-of-the-art or even better performance in both quantitative and qualitative measurements.

Zhi-Song Liu, Li-Wen Wang, Chu-Tak Li et al.

Deep learning based single image super-resolution methods use a large number of training datasets and have recently achieved great quality progress both quantitatively and qualitatively. Most deep networks focus on nonlinear mapping from low-resolution inputs to high-resolution outputs via residual learning without exploring the feature abstraction and analysis. We propose a Hierarchical Back Projection Network (HBPN), that cascades multiple HourGlass (HG) modules to bottom-up and top-down process features across all scales to capture various spatial correlations and then consolidates the best representation for reconstruction. We adopt the back projection blocks in our proposed network to provide the error correlated up and down-sampling process to replace simple deconvolution and pooling process for better estimation. A new Softmax based Weighted Reconstruction (WR) process is used to combine the outputs of HG modules to further improve super-resolution. Experimental results on various datasets (including the validation dataset, NTIRE2019, of the Real Image Super-resolution Challenge) show that our proposed approach can achieve and improve the performance of the state-of-the-art methods for different scaling factors.