Related papers: FPCR-Net: Feature Pyramidal Correlation and Residu…

Monocular depth estimation is an essential task for scene understanding. The underlying structure of objects and stuff in a complex scene is critical to recovering accurate and visually-pleasing depth maps. Global structure conveys scene…

Feature pyramids have been proven powerful in image understanding tasks that require multi-scale features. State-of-the-art methods for multi-scale feature learning focus on performing feature interactions across space and scales using…

The performance of convolutional neural networks (CNNs) can be improved by adjusting the interrelationship between channels with attention mechanism. However, attention mechanism in recent advance has not fully utilized spatial information…

Residual connections are pivotal for deep neural networks, enabling greater depth by mitigating vanishing gradients. However, in standard residual updates, the module's output is directly added to the input stream. This can lead to updates…

Optical flow estimation is a crucial subfield of computer vision, serving as a foundation for video tasks. However, the real-world robustness is limited by animated synthetic datasets for training. This introduces domain gaps when applied…

Very deep convolutional neural networks (CNNs) yield state of the art results on a wide variety of visual recognition problems. A number of state of the the art methods for image recognition are based on networks with well over 100 layers…

Image downscaling and upscaling are two basic rescaling operations. Once the image is downscaled, it is difficult to be reconstructed via upscaling due to the loss of information. To make these two processes more compatible and improve the…

Deep-learning-based approaches to depth estimation are rapidly advancing, offering superior performance over existing methods. To estimate the depth in real-world scenarios, depth estimation models require the robustness of various noise…

Change detection typically involves identifying regions with changes between bitemporal images taken at the same location. Besides significant changes, slow changes in bitemporal images are also important in real-life scenarios. For…

Optical flow estimation with occlusion or large displacement is a problematic challenge due to the lost of corresponding pixels between consecutive frames. In this paper, we discover that the lost information is related to a large quantity…

Initializing optical flow field by either sparse descriptor matching or dense patch matches has been proved to be particularly useful for capturing large displacements. In this paper, we present a pyramidal gradient matching approach that…

Self-similarity refers to the image prior widely used in image restoration algorithms that small but similar patterns tend to occur at different locations and scales. However, recent advanced deep convolutional neural network based methods…

In this paper, we propose a pyramid network structure to improve the FCN-based segmentation solutions and apply it to label thyroid follicles in histology images. Our design is based on the notion that a hierarchical updating scheme, if…

The block-based coding structure in the hybrid video coding framework inevitably introduces compression artifacts such as blocking, ringing, etc. To compensate for those artifacts, extensive filtering techniques were proposed in the loop of…

Natural image quality is often degraded by adverse weather conditions, significantly impairing the performance of downstream tasks. Image restoration has emerged as a core solution to this challenge and has been widely discussed in the…

The FlowNet demonstrated that optical flow estimation can be cast as a learning problem. However, the state of the art with regard to the quality of the flow has still been defined by traditional methods. Particularly on small displacements…

Recently, convolutional neural network (CNN) based image super-resolution (SR) methods have achieved significant performance improvement. However, most CNN-based methods mainly focus on feed-forward architecture design and neglect to…

Coordinate networks like Multiplicative Filter Networks (MFNs) and BACON offer some control over the frequency spectrum used to represent continuous signals such as images or 3D volumes. Yet, they are not readily applicable to problems for…

In recent years, deformable medical image registration techniques have made significant progress. However, existing models still lack efficiency in parallel extraction of coarse and fine-grained features. To address this, we construct a new…

Optical flow estimation is a challenging problem remaining unsolved. Recent deep learning based optical flow models have achieved considerable success. However, these models often train networks from the scratch on standard optical flow…