Shaodi You

Ziteng Cui, Guo-Jun Qi, Lin Gu et al.

Dark environment becomes a challenge for computer vision algorithms owing to insufficient photons and undesirable noise. To enhance object detection in a dark environment, we propose a novel multitask auto encoding transformation (MAET) model which is able to explore the intrinsic pattern behind illumination translation. In a self-supervision manner, the MAET learns the intrinsic visual structure by encoding and decoding the realistic illumination-degrading transformation considering the physical noise model and image signal processing (ISP). Based on this representation, we achieve the object detection task by decoding the bounding box coordinates and classes. To avoid the over-entanglement of two tasks, our MAET disentangles the object and degrading features by imposing an orthogonal tangent regularity. This forms a parametric manifold along which multitask predictions can be geometrically formulated by maximizing the orthogonality between the tangents along the outputs of respective tasks. Our framework can be implemented based on the mainstream object detection architecture and directly trained end-to-end using normal target detection datasets, such as VOC and COCO. We have achieved the state-of-the-art performance using synthetic and real-world datasets. Code is available at https://github.com/cuiziteng/MAET.

Qi Bi, Shaodi You, Theo Gevers

Domain-generalized urban-scene semantic segmentation (USSS) aims to learn generalized semantic predictions across diverse urban-scene styles. Unlike domain gap challenges, USSS is unique in that the semantic categories are often similar in different urban scenes, while the styles can vary significantly due to changes in urban landscapes, weather conditions, lighting, and other factors. Existing approaches typically rely on convolutional neural networks (CNNs) to learn the content of urban scenes. In this paper, we propose a Content-enhanced Mask TransFormer (CMFormer) for domain-generalized USSS. The main idea is to enhance the focus of the fundamental component, the mask attention mechanism, in Transformer segmentation models on content information. To achieve this, we introduce a novel content-enhanced mask attention mechanism. It learns mask queries from both the image feature and its down-sampled counterpart, as lower-resolution image features usually contain more robust content information and are less sensitive to style variations. These features are fused into a Transformer decoder and integrated into a multi-resolution content-enhanced mask attention learning scheme. Extensive experiments conducted on various domain-generalized urban-scene segmentation datasets demonstrate that the proposed CMFormer significantly outperforms existing CNN-based methods for domain-generalized semantic segmentation, achieving improvements of up to 14.00\% in terms of mIoU (mean intersection over union). The source code is publicly available at \url{https://github.com/BiQiWHU/CMFormer}.

Fan Zhang, Shaodi You, Yu Li et al.

Rain is transparent, which reflects and refracts light in the scene to the camera. In outdoor vision, rain, especially rain streaks degrade visibility and therefore need to be removed. In existing rain streak removal datasets, although density, scale, direction and intensity have been considered, transparency is not fully taken into account. This problem is particularly serious in night scenes, where the appearance of rain largely depends on the interaction with scene illuminations and changes drastically on different positions within the image. This is problematic, because unrealistic dataset causes serious domain bias. In this paper, we propose GTAV-NightRain dataset, which is a large-scale synthetic night-time rain streak removal dataset. Unlike existing datasets, by using 3D computer graphic platform (namely GTA V), we are allowed to infer the three dimensional interaction between rain and illuminations, which insures the photometric realness. Current release of the dataset contains 12,860 HD rainy images and 1,286 corresponding HD ground truth images in diversified night scenes. A systematic benchmark and analysis are provided along with the dataset to inspire further research.

Fan Zhang, Shaodi You, Yu Li et al.

Monocular depth estimation has experienced significant progress on terrestrial images in recent years, largely due to deep learning advancements. However, it remains inadequate for underwater scenes, primarily because of data scarcity. Given the inherent challenges of light attenuation and backscattering in water, acquiring clear underwater images or precise depth information is notably difficult and costly. Consequently, learning-based approaches often rely on synthetic data or turn to unsupervised or self-supervised methods to mitigate this lack of data. Nonetheless, the performance of these methods is often constrained by the domain gap and looser constraints. In this paper, we propose a novel pipeline for generating photorealistic underwater images using accurate terrestrial depth data. This approach facilitates the training of supervised models for underwater depth estimation, effectively reducing the performance disparity between terrestrial and underwater environments. Contrary to prior synthetic datasets that merely apply style transfer to terrestrial images without altering the scene content, our approach uniquely creates vibrant, non-existent underwater scenes by leveraging terrestrial depth data through the innovative Stable Diffusion model. Specifically, we introduce a unique Depth2Underwater ControlNet, trained on specially prepared \{Underwater, Depth, Text\} data triplets, for this generation task. Our newly developed dataset enables terrestrial depth estimation models to achieve considerable improvements, both quantitatively and qualitatively, on unseen underwater images, surpassing their terrestrial pre-trained counterparts. Moreover, the enhanced depth accuracy for underwater scenes also aids underwater image restoration techniques that rely on depth maps, further demonstrating our dataset's utility. The dataset will be available at https://github.com/zkawfanx/Atlantis.

Maarten Burger, Rob Wijnhoven, Shaodi You

This study investigates object presence detection and localization in remote sensing imagery, focusing on solar panel recognition. We explore different levels of supervision, evaluating three models: a fully supervised object detector, a weakly supervised image classifier with CAM-based localization, and a minimally supervised anomaly detector. The classifier excels in binary presence detection (0.79 F1-score), while the object detector (0.72) offers precise localization. The anomaly detector requires more data for viable performance. Fusion of model results shows potential accuracy gains. CAM impacts localization modestly, with GradCAM, GradCAM++, and HiResCAM yielding superior results. Notably, the classifier remains robust with less data, in contrast to the object detector.

Zhuoran Du, Shaodi You, Cheng Cheng et al.

Hyperspectral image (HSI) densely samples the world in both the space and frequency domain and therefore is more distinctive than RGB images. Usually, HSI needs to be calibrated to minimize the impact of various illumination conditions. The traditional way to calibrate HSI utilizes a physical reference, which involves manual operations, occlusions, and/or limits camera mobility. These limitations inspire this paper to automatically calibrate HSIs using a learning-based method. Towards this goal, a large-scale HSI calibration dataset is created, which has 765 high-quality HSI pairs covering diversified natural scenes and illuminations. The dataset is further expanded to 7650 pairs by combining with 10 different physically measured illuminations. A spectral illumination transformer (SIT) together with an illumination attention module is proposed. Extensive benchmarks demonstrate the SoTA performance of the proposed SIT. The benchmarks also indicate that low-light conditions are more challenging than normal conditions. The dataset and codes are available online:https://github.com/duranze/Automatic-spectral-calibration-of-HSI

Ryota Yoshihashi, Wen Shao, Rei Kawakami et al.

Open-set classification is a problem of handling `unknown' classes that are not contained in the training dataset, whereas traditional classifiers assume that only known classes appear in the test environment. Existing open-set classifiers rely on deep networks trained in a supervised manner on known classes in the training set; this causes specialization of learned representations to known classes and makes it hard to distinguish unknowns from knowns. In contrast, we train networks for joint classification and reconstruction of input data. This enhances the learned representation so as to preserve information useful for separating unknowns from knowns, as well as to discriminate classes of knowns. Our novel Classification-Reconstruction learning for Open-Set Recognition (CROSR) utilizes latent representations for reconstruction and enables robust unknown detection without harming the known-class classification accuracy. Extensive experiments reveal that the proposed method outperforms existing deep open-set classifiers in multiple standard datasets and is robust to diverse outliers. The code is available in https://nae-lab.org/~rei/research/crosr/.

Qi Bi, Shaodi You, Theo Gevers

Images from outdoor scenes may be taken under various weather conditions. It is well studied that weather impacts the performance of computer vision algorithms and needs to be handled properly. However, existing algorithms model weather condition as a discrete status and estimate it using multi-label classification. The fact is that, physically, specifically in meteorology, weather are modeled as a continuous and transitional status. Instead of directly implementing hard classification as existing multi-weather classification methods do, we consider the physical formulation of multi-weather conditions and model the impact of physical-related parameter on learning from the image appearance. In this paper, we start with solid revisit of the physics definition of weather and how it can be described as a continuous machine learning and computer vision task. Namely, we propose to model the weather uncertainty, where the level of probability and co-existence of multiple weather conditions are both considered. A Gaussian mixture model is used to encapsulate the weather uncertainty and a uncertainty-aware multi-weather learning scheme is proposed based on prior-posterior learning. A novel multi-weather co-presence estimation transformer (MeFormer) is proposed. In addition, a new multi-weather co-presence estimation (MePe) dataset, along with 14 fine-grained weather categories and 16,078 samples, is proposed to benchmark both conventional multi-label weather classification task and multi-weather co-presence estimation task. Large scale experiments show that the proposed method achieves state-of-the-art performance and substantial generalization capabilities on both the conventional multi-label weather classification task and the proposed multi-weather co-presence estimation task. Besides, modeling weather uncertainty also benefits adverse-weather semantic segmentation.

Cas Steigstra, Sergey Milyaev, Shaodi You

The reliability of secure graphic verification, a key anti-counterfeiting tool, is undermined by poor image acquisition on smartphones. Uncontrolled user captures of these high-entropy patterns cause high false rejection rates, creating a significant 'reliability gap'. To bridge this gap, we depart from traditional perceptual IQA and introduce a framework that predictively estimates a frame's utility for the downstream verification task. We propose a lightweight model to predict a quality score for a video frame, determining its suitability for a resource-intensive oracle model. Our framework is validated using re-contextualized FNMR and ISRR metrics on a large-scale dataset of 32,000+ images from 105 smartphones. Furthermore, a novel cross-domain analysis on graphics from different industrial printing presses reveals a key finding: a lightweight probe on a frozen, ImageNet-pretrained network generalizes better to an unseen printing technology than a fully fine-tuned model. This provides a key insight for real-world generalization: for domain shifts from physical manufacturing, a frozen general-purpose backbone can be more robust than full fine-tuning, which can overfit to source-domain artifacts.

Ying Fu, Yu Li, Shaodi You et al.

The intersection of physics-based vision and deep learning presents an exciting frontier for advancing computer vision technologies. By leveraging the principles of physics to inform and enhance deep learning models, we can develop more robust and accurate vision systems. Physics-based vision aims to invert the processes to recover scene properties such as shape, reflectance, light distribution, and medium properties from images. In recent years, deep learning has shown promising improvements for various vision tasks, and when combined with physics-based vision, these approaches can enhance the robustness and accuracy of vision systems. This technical report summarizes the outcomes of the Physics-Based Vision Meets Deep Learning (PBDL) 2024 challenge, held in CVPR 2024 workshop. The challenge consisted of eight tracks, focusing on Low-Light Enhancement and Detection as well as High Dynamic Range (HDR) Imaging. This report details the objectives, methodologies, and results of each track, highlighting the top-performing solutions and their innovative approaches.

Ryota Yoshihashi, Rei Kawakami, Shaodi You et al.

Detecting tiny objects in a high-resolution video is challenging because the visual information is little and unreliable. Specifically, the challenge includes very low resolution of the objects, MPEG artifacts due to compression and a large searching area with many hard negatives. Tracking is equally difficult because of the unreliable appearance, and the unreliable motion estimation. Luckily, we found that by combining this two challenging tasks together, there will be mutual benefits. Following the idea, in this paper, we present a neural network model called the Recurrent Correlational Network, where detection and tracking are jointly performed over a multi-frame representation learned through a single, trainable, and end-to-end network. The framework exploits a convolutional long short-term memory network for learning informative appearance changes for detection, while the learned representation is shared in tracking for enhancing its performance. In experiments with datasets containing images of scenes with small flying objects, such as birds and unmanned aerial vehicles, the proposed method yielded consistent improvements in detection performance over deep single-frame detectors and existing motion-based detectors. Furthermore, our network performs as well as state-of-the-art generic object trackers when it was evaluated as a tracker on a bird image dataset.

Yuxing Huang, Shaodi You, Ying Fu et al.

High-resolution hyperspectral images (HSIs) contain the response of each pixel in different spectral bands, which can be used to effectively distinguish various objects in complex scenes. While HSI cameras have become low cost, algorithms based on it have not been well exploited. In this paper, we focus on a novel topic, weakly-supervised semantic segmentation in cityscape via HSIs. It is based on the idea that high-resolution HSIs in city scenes contain rich spectral information, which can be easily associated to semantics without manual labeling. Therefore, it enables low cost, highly reliable semantic segmentation in complex scenes. Specifically, in this paper, we theoretically analyze the HSIs and introduce a weakly-supervised HSI semantic segmentation framework, which utilizes spectral information to improve the coarse labels to a finer degree. The experimental results show that our method can obtain highly competitive labels and even have higher edge fineness than artificial fine labels in some classes. At the same time, the results also show that the refined labels can effectively improve the effect of semantic segmentation. The combination of HSIs and semantic segmentation proves that HSIs have great potential in high-level visual tasks.

Ruoteng Li, Xiaoyi Zhang, Shaodi You et al.

Image dehazing is one of the important and popular topics in computer vision and machine learning. A reliable real-time dehazing method with reliable performance is highly desired for many applications such as autonomous driving, security surveillance, etc. While recent learning-based methods require datasets containing pairs of hazy images and clean ground truth, it is impossible to capture them in real scenes. Many existing works compromise this difficulty to generate hazy images by rendering the haze from depth on common RGBD datasets using the haze imaging model. However, there is still a gap between the synthetic datasets and real hazy images as large datasets with high-quality depth are mostly indoor and depth maps for outdoor are imprecise. In this paper, we complement the existing datasets with a new, large, and diverse dehazing dataset containing real outdoor scenes from High-Definition (HD) 3D movies. We select a large number of high-quality frames of real outdoor scenes and render haze on them using depth from stereo. Our dataset is clearly more realistic and more diversified with better visual quality than existing ones. More importantly, we demonstrate that using this dataset greatly improves the dehazing performance on real scenes. In addition to the dataset, we also evaluate a series state of the art methods on the proposed benchmarking datasets.

Wei Wang, Shaodi You, Sezer Karaoglu et al.

Kinship verification is a well-explored task: identifying whether or not two persons are kin. In contrast, kinship identification has been largely ignored so far. Kinship identification aims to further identify the particular type of kinship. An extension to kinship verification run short to properly obtain identification, because existing verification networks are individually trained on specific kinships and do not consider the context between different kinship types. Also, existing kinship verification datasets have biased positive-negative distributions which are different than real-world distributions. To this end, we propose a novel kinship identification approach based on joint training of kinship verification ensembles and classification modules. We propose to rebalance the training dataset to become more realistic. Large scale experiments demonstrate the appealing performance on kinship identification. The experiments further show significant performance improvement of kinship verification when trained on the same dataset with more realistic distributions.

Hao Yang, Dan Yan, Li Zhang et al.

Skeleton-based action recognition has attracted considerable attention in computer vision since skeleton data is more robust to the dynamic circumstance and complicated background than other modalities. Recently, many researchers have used the Graph Convolutional Network (GCN) to model spatial-temporal features of skeleton sequences by an end-to-end optimization. However, conventional GCNs are feedforward networks which are impossible for low-level layers to access semantic information in the high-level layers. In this paper, we propose a novel network, named Feedback Graph Convolutional Network (FGCN). This is the first work that introduces the feedback mechanism into GCNs and action recognition. Compared with conventional GCNs, FGCN has the following advantages: (1) a multi-stage temporal sampling strategy is designed to extract spatial-temporal features for action recognition in a coarse-to-fine progressive process; (2) A dense connections based Feedback Graph Convolutional Block (FGCB) is proposed to introduce feedback connections into the GCNs. It transmits the high-level semantic features to the low-level layers and flows temporal information stage by stage to progressively model global spatial-temporal features for action recognition; (3) The FGCN model provides early predictions. In the early stages, the model receives partial information about actions. Naturally, its predictions are relatively coarse. The coarse predictions are treated as the prior to guide the feature learning of later stages for a accurate prediction. Extensive experiments on the datasets, NTU-RGB+D, NTU-RGB+D120 and Northwestern-UCLA, demonstrate that the proposed FGCN is effective for action recognition. It achieves the state-of-the-art performance on the three datasets.

Yunfei Liu, Yu Li, Shaodi You et al.

Intrinsic image decomposition, which is an essential task in computer vision, aims to infer the reflectance and shading of the scene. It is challenging since it needs to separate one image into two components. To tackle this, conventional methods introduce various priors to constrain the solution, yet with limited performance. Meanwhile, the problem is typically solved by supervised learning methods, which is actually not an ideal solution since obtaining ground truth reflectance and shading for massive general natural scenes is challenging and even impossible. In this paper, we propose a novel unsupervised intrinsic image decomposition framework, which relies on neither labeled training data nor hand-crafted priors. Instead, it directly learns the latent feature of reflectance and shading from unsupervised and uncorrelated data. To enable this, we explore the independence between reflectance and shading, the domain invariant content constraint and the physical constraint. Extensive experiments on both synthetic and real image datasets demonstrate consistently superior performance of the proposed method.

Yunfei Liu, Yu Li, Shaodi You et al.

Reflection is common in images capturing scenes behind a glass window, which is not only a disturbance visually but also influence the performance of other computer vision algorithms. Single image reflection removal is an ill-posed problem because the color at each pixel needs to be separated into two values, i.e., the desired clear background and the reflection. To solve it, existing methods propose priors such as smoothness, color consistency. However, the low-level priors are not reliable in complex scenes, for instance, when capturing a real outdoor scene through a window, both the foreground and background contain both smooth and sharp area and a variety of color. In this paper, inspired by the fact that human can separate the two layers easily by recognizing the objects, we use the object semantic as guidance to force the same semantic object belong to the same layer. Extensive experiments on different datasets show that adding the semantic information offers a significant improvement to reflection separation. We also demonstrate the applications of the proposed method to other computer vision tasks.

Shaodi You, Erqi Huang, Shuaizhe Liang et al.

This document introduces the background and the usage of the Hyperspectral City Dataset and the benchmark. The documentation first starts with the background and motivation of the dataset. Follow it, we briefly describe the method of collecting the dataset and the processing method from raw dataset to the final release dataset, specifically, the version 1.0. We also provide the detailed usage of the dataset and the evaluation metric for submitted the result for the 2019 Hyperspectral City Challenge.

Tianxiu Yu, Shijie Zhang, Cong Lin et al.

This document introduces the background and the usage of the Dunhuang Grottoes Dataset and the benchmark. The documentation first starts with the background of the Dunhuang Grotto, which is widely recognised as an priceless heritage. Given that digital method is the modern trend for heritage protection and restoration. Follow the trend, we release the first public dataset for Dunhuang Grotto Painting restoration. The rest of the documentation details the painting data generation. To enable a data driven fashion, this dataset provided a large number of training and testing example which is sufficient for a deep learning approach. The detailed usage of the dataset as well as the benchmark is described.

Kenta Moriwaki, Ryota Yoshihashi, Rei Kawakami et al.

This paper tackles high-dynamic-range (HDR) image reconstruction given only a single low-dynamic-range (LDR) image as input. While the existing methods focus on minimizing the mean-squared-error (MSE) between the target and reconstructed images, we minimize a hybrid loss that consists of perceptual and adversarial losses in addition to HDR-reconstruction loss. The reconstruction loss instead of MSE is more suitable for HDR since it puts more weight on both over- and under- exposed areas. It makes the reconstruction faithful to the input. Perceptual loss enables the networks to utilize knowledge about objects and image structure for recovering the intensity gradients of saturated and grossly quantized areas. Adversarial loss helps to select the most plausible appearance from multiple solutions. The hybrid loss that combines all the three losses is calculated in logarithmic space of image intensity so that the outputs retain a large dynamic range and meanwhile the learning becomes tractable. Comparative experiments conducted with other state-of-the-art methods demonstrated that our method produces a leap in image quality.

Lu Liu, Robby T. Tan, Shaodi You

One significant problem of deep-learning based human action recognition is that it can be easily misled by the presence of irrelevant objects or backgrounds. Existing methods commonly address this problem by employing bounding boxes on the target humans as part of the input, in both training and testing stages. This requirement of bounding boxes as part of the input is needed to enable the methods to ignore irrelevant contexts and extract only human features. However, we consider this solution is inefficient, since the bounding boxes might not be available. Hence, instead of using a person bounding box as an input, we introduce a human-mask loss to automatically guide the activations of the feature maps to the target human who is performing the action, and hence suppress the activations of misleading contexts. We propose a multi-task deep learning method that jointly predicts the human action class and human location heatmap. Extensive experiments demonstrate our approach is more robust compared to the baseline methods under the presence of irrelevant misleading contexts. Our method achieves 94.06\% and 40.65\% (in terms of mAP) on Stanford40 and MPII dataset respectively, which are 3.14\% and 12.6\% relative improvements over the best results reported in the literature, and thus set new state-of-the-art results. Additionally, unlike some existing methods, we eliminate the requirement of using a person bounding box as an input during testing.

Zhixiang Hao, Yu Li, Shaodi You et al.

Convolutional Neural Networks have demonstrated superior performance on single image depth estimation in recent years. These works usually use stacked spatial pooling or strided convolution to get high-level information which are common practices in classification task. However, depth estimation is a dense prediction problem and low-resolution feature maps usually generate blurred depth map which is undesirable in application. In order to produce high quality depth map, say clean and accurate, we propose a network consists of a Dense Feature Extractor (DFE) and a Depth Map Generator (DMG). The DFE combines ResNet and dilated convolutions. It extracts multi-scale information from input image while keeping the feature maps dense. As for DMG, we use attention mechanism to fuse multi-scale features produced in DFE. Our Network is trained end-to-end and does not need any post-processing. Hence, it runs fast and can predict depth map in about 15 fps. Experiment results show that our method is competitive with the state-of-the-art in quantitative evaluation, but can preserve better structural details of the scene depth.

Xiang Wang, Shaodi You, Xi Li et al.

Weakly-supervised semantic segmentation under image tags supervision is a challenging task as it directly associates high-level semantic to low-level appearance. To bridge this gap, in this paper, we propose an iterative bottom-up and top-down framework which alternatively expands object regions and optimizes segmentation network. We start from initial localization produced by classification networks. While classification networks are only responsive to small and coarse discriminative object regions, we argue that, these regions contain significant common features about objects. So in the bottom-up step, we mine common object features from the initial localization and expand object regions with the mined features. To supplement non-discriminative regions, saliency maps are then considered under Bayesian framework to refine the object regions. Then in the top-down step, the refined object regions are used as supervision to train the segmentation network and to predict object masks. These object masks provide more accurate localization and contain more regions of object. Further, we take these object masks as initial localization and mine common object features from them. These processes are conducted iteratively to progressively produce fine object masks and optimize segmentation networks. Experimental results on Pascal VOC 2012 dataset demonstrate that the proposed method outperforms previous state-of-the-art methods by a large margin.

Hongru Liang, Haozheng Wang, Jun Wang et al.

Learning social media content is the basis of many real-world applications, including information retrieval and recommendation systems, among others. In contrast with previous works that focus mainly on single modal or bi-modal learning, we propose to learn social media content by fusing jointly textual, acoustic, and visual information (JTAV). Effective strategies are proposed to extract fine-grained features of each modality, that is, attBiGRU and DCRNN. We also introduce cross-modal fusion and attentive pooling techniques to integrate multi-modal information comprehensively. Extensive experimental evaluation conducted on real-world datasets demonstrates our proposed model outperforms the state-of-the-art approaches by a large margin.

Seiichiro Fukuda, Ryota Yoshihashi, Rei Kawakami et al.

Multi-task learning improves generalization performance by sharing knowledge among related tasks. Existing models are for task combinations annotated on the same dataset, while there are cases where multiple datasets are available for each task. How to utilize knowledge of successful single-task CNNs that are trained on each dataset has been explored less than multi-task learning with a single dataset. We propose a cross-connected CNN, a new architecture that connects single-task CNNs through convolutional layers, which transfer useful information for the counterpart. We evaluated our proposed architecture on a combination of detection and segmentation using two datasets. Experiments on pedestrians show our CNN achieved a higher detection performance compared to baseline CNNs, while maintaining high quality for segmentation. It is the first known attempt to tackle multi-task learning with different training datasets between detection and segmentation. Experiments with wild birds demonstrate how our CNN learns general representations from limited datasets.

Ziang Cheng, Shaodi You, Viorela Ila et al.

Single-image haze-removal is challenging due to limited information contained in one single image. Previous solutions largely rely on handcrafted priors to compensate for this deficiency. Recent convolutional neural network (CNN) models have been used to learn haze-related priors but they ultimately work as advanced image filters. In this paper we propose a novel semantic ap- proach towards single image haze removal. Unlike existing methods, we infer color priors based on extracted semantic features. We argue that semantic context can be exploited to give informative cues for (a) learning color prior on clean image and (b) estimating ambient illumination. This design allowed our model to recover clean images from challenging cases with strong ambiguity, e.g. saturated illumination color and sky regions in image. In experiments, we validate our ap- proach upon synthetic and real hazy images, where our method showed superior performance over state-of-the-art approaches, suggesting semantic information facilitates the haze removal task.

Junxuan Li, Shaodi You, Antonio Robles-Kelly

In this paper, we present a frequency domain neural network for image super-resolution. The network employs the convolution theorem so as to cast convolutions in the spatial domain as products in the frequency domain. Moreover, the non-linearity in deep nets, often achieved by a rectifier unit, is here cast as a convolution in the frequency domain. This not only yields a network which is very computationally efficient at testing but also one whose parameters can all be learnt accordingly. The network can be trained using back propagation and is devoid of complex numbers due to the use of the Hartley transform as an alternative to the Fourier transform. Moreover, the network is potentially applicable to other problems elsewhere in computer vision and image processing which are often cast in the frequency domain. We show results on super-resolution and compare against alternatives elsewhere in the literature. In our experiments, our network is one to two orders of magnitude faster than the alternatives with an imperceptible loss of performance.

Kaiyue Lu, Shaodi You, Nick Barnes

Image smoothing is a fundamental task in computer vision, that aims to retain salient structures and remove insignificant textures. In this paper, we aim to address the fundamental shortcomings of existing image smoothing methods, which cannot properly distinguish textures and structures with similar low-level appearance. While deep learning approaches have started to explore the preservation of structure through image smoothing, existing work does not yet properly address textures. To this end, we generate a large dataset by blending natural textures with clean structure-only images, and then build a texture prediction network (TPN) that predicts the location and magnitude of textures. We then combine the TPN with a semantic structure prediction network (SPN) so that the final texture and structure aware filtering network (TSAFN) is able to identify the textures to remove ("texture-awareness") and the structures to preserve ("structure-awareness"). The proposed model is easy to understand and implement, and shows excellent performance on real images in the wild as well as our generated dataset.

Ryota Yoshihashi, Tu Tuan Trinh, Rei Kawakami et al.

While generic object detection has achieved large improvements with rich feature hierarchies from deep nets, detecting small objects with poor visual cues remains challenging. Motion cues from multiple frames may be more informative for detecting such hard-to-distinguish objects in each frame. However, how to encode discriminative motion patterns, such as deformations and pose changes that characterize objects, has remained an open question. To learn them and thereby realize small object detection, we present a neural model called the Recurrent Correlational Network, where detection and tracking are jointly performed over a multi-frame representation learned through a single, trainable, and end-to-end network. A convolutional long short-term memory network is utilized for learning informative appearance change for detection, while learned representation is shared in tracking for enhancing its performance. In experiments with datasets containing images of scenes with small flying objects, such as birds and unmanned aerial vehicles, the proposed method yielded consistent improvements in detection performance over deep single-frame detectors and existing motion-based detectors. Furthermore, our network performs as well as state-of-the-art generic object trackers when it was evaluated as a tracker on the bird dataset.

Riku Shigematsu, David Feng, Shaodi You et al.

Recently, deep Convolutional Neural Networks (CNN) have demonstrated strong performance on RGB salient object detection. Although, depth information can help improve detection results, the exploration of CNNs for RGB-D salient object detection remains limited. Here we propose a novel deep CNN architecture for RGB-D salient object detection that exploits high-level, mid-level, and low level features. Further, we present novel depth features that capture the ideas of background enclosure and depth contrast that are suitable for a learned approach. We show improved results compared to state-of-the-art RGB-D salient object detection methods. We also show that the low-level and mid-level depth features both contribute to improvements in the results. Especially, F-Score of our method is 0.848 on RGBD1000 dataset, which is 10.7% better than the second place.

Shijie Zhang, Lizhen Qu, Shaodi You et al.

In this paper, we propose the first model to be able to generate visually grounded questions with diverse types for a single image. Visual question generation is an emerging topic which aims to ask questions in natural language based on visual input. To the best of our knowledge, it lacks automatic methods to generate meaningful questions with various types for the same visual input. To circumvent the problem, we propose a model that automatically generates visually grounded questions with varying types. Our model takes as input both images and the captions generated by a dense caption model, samples the most probable question types, and generates the questions in sequel. The experimental results on two real world datasets show that our model outperforms the strongest baseline in terms of both correctness and diversity with a wide margin.

Zhichen Zhao, Huimin Ma, Shaodi You

In this paper, we propose a novel single image action recognition algorithm which is based on the idea of semantic body part actions. Unlike existing bottom up methods, we argue that the human action is a combination of meaningful body part actions. In detail, we divide human body into five parts: head, torso, arms, hands and legs. And for each of the body parts, we define several semantic body part actions, e.g., hand holding, hand waving. These semantic body part actions are strongly related to the body actions, e.g., writing, and jogging. Based on the idea, we propose a deep neural network based system: first, body parts are localized by a Semi-FCN network. Second, for each body parts, a Part Action Res-Net is used to predict semantic body part actions. And finally, we use SVM to fuse the body part actions and predict the entire body action. Experiments on two dataset: PASCAL VOC 2012 and Stanford-40 report mAP improvement from the state-of-the-art by 3.8% and 2.6% respectively.

Xiang Wang, Huimin Ma, Xiaozhi Chen et al.

In this paper, we propose a novel edge preserving and multi-scale contextual neural network for salient object detection. The proposed framework is aiming to address two limits of the existing CNN based methods. First, region-based CNN methods lack sufficient context to accurately locate salient object since they deal with each region independently. Second, pixel-based CNN methods suffer from blurry boundaries due to the presence of convolutional and pooling layers. Motivated by these, we first propose an end-to-end edge-preserved neural network based on Fast R-CNN framework (named RegionNet) to efficiently generate saliency map with sharp object boundaries. Later, to further improve it, multi-scale spatial context is attached to RegionNet to consider the relationship between regions and the global scenes. Furthermore, our method can be generally applied to RGB-D saliency detection by depth refinement. The proposed framework achieves both clear detection boundary and multi-scale contextual robustness simultaneously for the first time, and thus achieves an optimized performance. Experiments on six RGB and two RGB-D benchmark datasets demonstrate that the proposed method achieves state-of-the-art performance.

Yu Li, Shaodi You, Michael S. Brown et al.

This paper provides a comprehensive survey of methods dealing with visibility enhancement of images taken in hazy or foggy scenes. The survey begins with discussing the optical models of atmospheric scattering media and image formation. This is followed by a survey of existing methods, which are grouped to multiple image methods, polarizing filters based methods, methods with known depth, and single-image methods. We also provide a benchmark of a number of well known single-image methods, based on a recent dataset provided by Fattal and our newly generated scattering media dataset that contains ground truth images for quantitative evaluation. To our knowledge, this is the first benchmark using numerical metrics to evaluate dehazing techniques. This benchmark allows us to objectively compare the results of existing methods and to better identify the strengths and limitations of each method.

Shaodi You, Yasuyuki Matsushita, Sudipta Sinha et al.

Digitally unwrapping images of paper sheets is crucial for accurate document scanning and text recognition. This paper presents a method for automatically rectifying curved or folded paper sheets from a few images captured from multiple viewpoints. Prior methods either need expensive 3D scanners or model deformable surfaces using over-simplified parametric representations. In contrast, our method uses regular images and is based on general developable surface models that can represent a wide variety of paper deformations. Our main contribution is a new robust rectification method based on ridge-aware 3D reconstruction of a paper sheet and unwrapping the reconstructed surface using properties of developable surfaces via $\ell_1$ conformal mapping. We present results on several examples including book pages, folded letters and shopping receipts.

Shaodi You, Nick Barnes, Janine Walker

In this paper, we propose a color to grayscale image conversion algorithm (C2G) that aims to preserve the perceptual properties of the color image as much as possible. To this end, we propose measures for two perceptual properties based on contemporary research in vision science: brightness and multi-scale contrast. The brightness measurement is based on the idea that the brightness of a grayscale image will affect the perception of the probability of color information. The color contrast measurement is based on the idea that the contrast of a given pixel to its surroundings can be measured as a linear combination of color contrast at different scales. Based on these measures we propose a graph based optimization framework to balance the brightness and contrast measurements. To solve the optimization, an $\ell_1$-norm based method is provided which converts color discontinuities to brightness discontinuities. To validate our methods, we evaluate against the existing \cadik and Color250 datasets, and against NeoColor, a new dataset that improves over existing C2G datasets. NeoColor contains around 300 images from typical C2G scenarios, including: commercial photograph, printing, books, magazines, masterpiece artworks and computer designed graphics. We show improvements in metrics of performance, and further through a user study, we validate the performance of both the algorithm and the metric.

Shaodi You, Robby T. Tan, Rei Kawakami et al.

This paper introduces depth estimation from water drops. The key idea is that a single water drop adhered to window glass is totally transparent and convex, and thus optically acts like a fisheye lens. If we have more than one water drop in a single image, then through each of them we can see the environment with different view points, similar to stereo. To realize this idea, we need to rectify every water drop imagery to make radially distorted planar surfaces look flat. For this rectification, we consider two physical properties of water drops: (1) A static water drop has constant volume, and its geometric convex shape is determined by the balance between the tension force and gravity. This implies that the 3D geometric shape can be obtained by minimizing the overall potential energy, which is the sum of the tension energy and the gravitational potential energy. (2) The imagery inside a water-drop is determined by the water-drop 3D shape and total reflection at the boundary. This total reflection generates a dark band commonly observed in any adherent water drops. Hence, once the 3D shape of water drops are recovered, we can rectify the water drop images through backward raytracing. Subsequently, we can compute depth using stereo. In addition to depth estimation, we can also apply image refocusing. Experiments on real images and a quantitative evaluation show the effectiveness of our proposed method. To our best knowledge, never before have adherent water drops been used to estimate depth.