Related papers: SphereUFormer: A U-Shaped Transformer for Spherica…

Reliable depth estimation from spherical images is crucial for 360{\deg} vision in robotic navigation and immersive scene understanding. However, the onboard spherical camera can experience unintentional pose variations in real-world…

360{\deg} spherical images have advantages of wide view field, and are typically projected on a planar plane for processing, which is known as equirectangular image. The object shape in equirectangular images can be distorted and lack…

Recent illumination estimation methods have focused on enhancing the resolution and improving the quality and diversity of the generated textures. However, few have explored tailoring the neural network architecture to the Equirectangular…

Omnidirectional images and spherical representations of $3D$ shapes cannot be processed with conventional 2D convolutional neural networks (CNNs) as the unwrapping leads to large distortion. Using fast implementations of spherical and…

Accurate 3D shape abstraction from a single 2D image is a long-standing problem in computer vision and graphics. By leveraging a set of primitives to represent the target shape, recent methods have achieved promising results. However, these…

The ascension of Unmanned Aerial Vehicles (UAVs) in various fields necessitates effective UAV image segmentation, which faces challenges due to the dynamic perspectives of UAV-captured images. Traditional segmentation algorithms falter as…

Medical image segmentation remains particularly challenging for complex and low-contrast anatomical structures. In this paper, we introduce the U-Transformer network, which combines a U-shaped architecture for image segmentation with self-…

Both CNN-based and Transformer-based object detection with bounding box representation have been extensively studied in computer vision and medical image analysis, but circular object detection in medical images is still underexplored.…

Numerous significant progress on fisheye image rectification has been achieved through CNN. Nevertheless, constrained by a fixed receptive field, the global distribution and the local symmetry of the distortion have not been fully…

Semantic segmentation usually benefits from global contexts, fine localisation information, multi-scale features, etc. To advance Transformer-based segmenters with these aspects, we present a simple yet powerful semantic segmentation…

Nowadays 360 video analysis has become a significant research topic in the field since the appearance of high-quality and low-cost 360 wearable devices. In this paper, we propose a novel LiteFlowNet360 architecture for 360 videos optical…

Transformers have recently gained attention in the computer vision domain due to their ability to model long-range dependencies. However, the self-attention mechanism, which is the core part of the Transformer model, usually suffers from…

Omnidirectional vision is becoming increasingly relevant as more efficient $360^o$ image acquisition is now possible. However, the lack of annotated $360^o$ datasets has hindered the application of deep learning techniques on spherical…

Due to the current lack of large-scale datasets at the million-scale level, tasks involving panoramic images predominantly rely on existing two-dimensional pre-trained image benchmark models as backbone networks. However, these networks are…

Automatically segmenting objects from optical remote sensing images (ORSIs) is an important task. Most existing models are primarily based on either convolutional or Transformer features, each offering distinct advantages. Exploiting both…

While Transformer has achieved remarkable performance in various high-level vision tasks, it is still challenging to exploit the full potential of Transformer in image restoration. The crux lies in the limited depth of applying Transformer…

Recently, horizontal representation-based panoramic semantic segmentation approaches outperform projection-based solutions, because the distortions can be effectively removed by compressing the spherical data in the vertical direction.…

This paper provides a comprehensive survey on pioneer and state-of-the-art 3D scene geometry estimation methodologies based on single, two, or multiple images captured under the omnidirectional optics. We first revisit the basic concepts of…

Many service computing applications require real-time dataset collection from multiple devices, necessitating efficient sampling techniques to reduce bandwidth and storage pressure. Compressive sensing (CS) has found wide-ranging…

Controllable spherical panoramic image generation holds substantial applicative potential across a variety of domains.However, it remains a challenging task due to the inherent spherical distortion and geometry characteristics, resulting in…