IEEE Transactions on Image Processing最新文献

Deep learning approaches for Image Aesthetics Assessment (IAA) have shown promising results in recent years, but the internal mechanisms of these models remain unclear. Previous studies have demonstrated that image aesthetics can be predicted using semantic features, such as pre-trained object classification features. However, these semantic features are learned implicitly, and therefore, previous works have not elucidated what the semantic features are representing. In this work, we aim to create a more transparent deep learning framework for IAA by introducing explainable semantic features. To achieve this, we propose Tag-based Content Descriptors (TCDs), where each value in a TCD describes the relevance of an image to a human-readable tag that refers to a specific type of image content. This allows us to build IAA models from explicit descriptions of image contents. We first propose the explicit matching process to produce TCDs that adopt predefined tags to describe image contents. We show that a simple MLP-based IAA model with TCDs only based on predefined tags can achieve an SRCC of 0.767, which is comparable to most state-of-the-art methods. However, predefined tags may not be sufficient to describe all possible image contents that the model may encounter. Therefore, we further propose the implicit matching process to describe image contents that cannot be described by predefined tags. By integrating components obtained from the implicit matching process into TCDs, the IAA model further achieves an SRCC of 0.817, which significantly outperforms existing IAA methods. Both the explicit matching process and the implicit matching process are realized by the proposed TCD generator. To evaluate the performance of the proposed TCD generator in matching images with predefined tags, we also labeled 5101 images with photography-related tags to form a validation set. And experimental results show that the proposed TCD generator can meaningfully assign photography-related tags to images.

360° cameras have gained popularity over the last few years. In this paper, we propose two fundamental techniques-Field-of-View IoU (FoV-IoU) and 360Augmentation for object detection in 360° images. Although most object detection neural networks designed for perspective images are applicable to 360° images in equirectangular projection (ERP) format, their performance deteriorates owing to the distortion in ERP images. Our method can be readily integrated with existing perspective object detectors and significantly improves the performance. The FoV-IoU computes the intersection-over-union of two Field-of-View bounding boxes in a spherical image which could be used for training, inference, and evaluation while 360Augmentation is a data augmentation technique specific to 360° object detection task which randomly rotates a spherical image and solves the bias due to the sphere-to-plane projection. We conduct extensive experiments on the 360° indoor dataset with different types of perspective object detectors and show the consistent effectiveness of our method.

The end-to-end image fusion framework has achieved promising performance, with dedicated convolutional networks aggregating the multi-modal local appearance. However, long-range dependencies are directly neglected in existing CNN fusion approaches, impeding balancing the entire image-level perception for complex scenario fusion. In this paper, therefore, we propose an infrared and visible image fusion algorithm based on the transformer module and adversarial learning. Inspired by the global interaction power, we use the transformer technique to learn the effective global fusion relations. In particular, shallow features extracted by CNN are interacted in the proposed transformer fusion module to refine the fusion relationship within the spatial scope and across channels simultaneously. Besides, adversarial learning is designed in the training process to improve the output discrimination via imposing competitive consistency from the inputs, reflecting the specific characteristics in infrared and visible images. The experimental performance demonstrates the effectiveness of the proposed modules, with superior improvement against the state-of-the-art, generalising a novel paradigm via transformer and adversarial learning in the fusion task.

Underwater salient object detection (USOD) attracts increasing interest for its promising performance in various underwater visual tasks. However, USOD research is still in its early stages due to the lack of large-scale datasets within which salient objects are well-defined and pixel-wise annotated. To address this issue, this paper introduces a new dataset named USOD10K. It consists of 10,255 underwater images, covering 70 categories of salient objects in 12 different underwater scenes. In addition, salient object boundaries and depth maps of all images are provided in this dataset. The USOD10K is the first large-scale dataset in the USOD community, making a significant leap in diversity, complexity, and scalability. Secondly, a simple but strong baseline termed TC-USOD is designed for the USOD10K. The TC-USOD adopts a hybrid architecture based on an encoder-decoder design that leverages transformer and convolution as the basic computational building block of the encoder and decoder, respectively. Thirdly, we make a comprehensive summarization of 35 cutting-edge SOD/USOD methods and benchmark them over the existing USOD dataset and the USOD10K. The results show that our TC-USOD obtained superior performance on all datasets tested. Finally, several other use cases of the USOD10K are discussed, and future directions of USOD research are pointed out. This work will promote the development of the USOD research and facilitate further research on underwater visual tasks and visually-guided underwater robots. To pave the road in this research field, all the dataset, code, and benchmark results are publicly available: https://github.com/LinHong-HIT/USOD10K.

Video watermarking embeds a message into a cover video in an imperceptible manner, which can be retrieved even if the video undergoes certain modifications or distortions. Traditional watermarking methods are often manually designed for particular types of distortions and thus cannot simultaneously handle a broad spectrum of distortions. To this end, we propose a robust deep learning-based solution for video watermarking that is end-to-end trainable. Our model consists of a novel multiscale design where the watermarks are distributed across multiple spatial-temporal scales. Extensive evaluations on a wide variety of distortions show that our method outperforms traditional video watermarking methods as well as deep image watermarking models by a large margin. We further demonstrate the practicality of our method on a realistic video-editing application.