Kun Sun

Kun Sun, Rong Wang

Semantic relevance metrics can capture both the inherent semantics of individual objects and their relationships to other elements within a visual scene. Numerous previous research has demonstrated that these metrics can influence human visual processing. However, these studies often did not fully account for contextual information or employ the recent deep learning models for more accurate computation. This study investigates human visual perception and processing by introducing the metrics of contextual semantic relevance. We evaluate semantic relationships between target objects and their surroundings from both vision-based and language-based perspectives. Testing a large eye-movement dataset from visual comprehension, we employ state-of-the-art deep learning techniques to compute these metrics and analyze their impacts on fixation measures on human visual processing through advanced statistical models. These metrics could also simulate top-down and bottom-up processing in visual perception. This study further integrates vision-based and language-based metrics into a novel combined metric, addressing a critical gap in previous research that often treated visual and semantic similarities separately. Results indicate that all metrics could precisely predict fixation measures in visual perception and processing, but with distinct roles in prediction. The combined metric outperforms other metrics, supporting theories that emphasize the interaction between semantic and visual information in shaping visual perception/processing. This finding aligns with growing recognition of the importance of multi-modal information processing in human cognition. These insights enhance our understanding of cognitive mechanisms underlying visual processing and have implications for developing more accurate computational models in fields such as cognitive science and human-computer interaction.

Qi Qi, Kunqian Li, Haiyong Zheng et al.

Due to the wavelength-dependent light attenuation, refraction and scattering, underwater images usually suffer from color distortion and blurred details. However, due to the limited number of paired underwater images with undistorted images as reference, training deep enhancement models for diverse degradation types is quite difficult. To boost the performance of data-driven approaches, it is essential to establish more effective learning mechanisms that mine richer supervised information from limited training sample resources. In this paper, we propose a novel underwater image enhancement network, called SGUIE-Net, in which we introduce semantic information as high-level guidance across different images that share common semantic regions. Accordingly, we propose semantic region-wise enhancement module to perceive the degradation of different semantic regions from multiple scales and feed it back to the global attention features extracted from its original scale. This strategy helps to achieve robust and visually pleasant enhancements to different semantic objects, which should thanks to the guidance of semantic information for differentiated enhancement. More importantly, for those degradation types that are not common in the training sample distribution, the guidance connects them with the already well-learned types according to their semantic relevance. Extensive experiments on the publicly available datasets and our proposed dataset demonstrated the impressive performance of SGUIE-Net. The code and proposed dataset are available at: https://trentqq.github.io/SGUIE-Net.html

Tao Xu, Kun Sun, Wenbing Tao

Image feature point matching is a key step in Structure from Motion(SFM). However, it is becoming more and more time consuming because the number of images is getting larger and larger. In this paper, we proposed a GPU accelerated image matching method with improved Cascade Hashing. Firstly, we propose a Disk-Memory-GPU data exchange strategy and optimize the load order of data, so that the proposed method can deal with big data. Next, we parallelize the Cascade Hashing method on GPU. An improved parallel reduction and an improved parallel hashing ranking are proposed to fulfill this task. Finally, extensive experiments show that our image matching is about 20 times faster than SiftGPU on the same graphics card, nearly 100 times faster than the CPU CasHash method and hundreds of times faster than the CPU Kd-Tree based matching method. Further more, we introduce the epipolar constraint to the proposed method, and use the epipolar geometry to guide the feature matching procedure, which further reduces the matching cost.

Kun Sun, Wenbing Tao

Accuracy and efficiency are two key problems in large scale incremental Structure from Motion (SfM). In this paper, we propose a unified framework to divide the image set into clusters suitable for reconstruction as well as find multiple reliable and stable starting points. Image partitioning performs in two steps. First, some small image groups are selected at places with high image density, and then all the images are clustered according to their optimal reconstruction paths to these image groups. This promises that the scene is always reconstructed from dense places to sparse areas, which can reduce error accumulation when images have weak overlap. To enable faster speed, images outside the selected group in each cluster are further divided to achieve a greater degree of parallelism. Experiments show that our method achieves significant speedup, higher accuracy and better completeness.

Yun Gu, Guang-Zhong Yang, Jie Yang et al.

Echocardiography plays an important part in diagnostic aid in cardiac diseases. A critical step in echocardiography-aided diagnosis is to extract the standard planes since they tend to provide promising views to present different structures that are benefit to diagnosis. To this end, this paper proposes a spatial-temporal embedding framework to extract the standard view planes from 4D STIC (spatial-temporal image corre- lation) volumes. The proposed method is comprised of three stages, the frame smoothing, spatial-temporal embedding and final classification. In first stage, an L 0 smoothing filter is used to preprocess the frames that removes the noise and preserves the boundary. Then a compact repre- sentation is learned via embedding spatial and temporal features into a latent space in the supervised scheme considering both standard plane information and diagnosis result. In last stage, the learned features are fed into support vector machine to identify the standard plane. We eval- uate the proposed method on a 4D STIC volume dataset with 92 normal cases and 93 abnormal cases in three standard planes. It demonstrates that our method outperforms the baselines in both classification accuracy and computational efficiency.