Related papers: Bending Reality: Distortion-aware Transformers for…

Deep convolutional neural networks (DCNNs) based remote sensing (RS) image semantic segmentation technology has achieved great success used in many real-world applications such as geographic element analysis. However, strong dependency on…

Text-to-image diffusion models excel at translating language prompts into photorealistic images by implicitly grounding textual concepts through their cross-modal attention mechanisms. Recent multi-modal diffusion transformers extend this…

In panorama understanding, the widely used equirectangular projection (ERP) entails boundary discontinuity and spatial distortion. It severely deteriorates the conventional CNNs and vision Transformers on panoramas. In this paper, we…

We show that it is possible to learn semantic segmentation from very limited amounts of manual annotations, by enforcing geometric 3D constraints between multiple views. More exactly, image locations corresponding to the same physical 3D…

Position emission tomography (PET) is widely used in clinics and research due to its quantitative merits and high sensitivity, but suffers from low signal-to-noise ratio (SNR). Recently convolutional neural networks (CNNs) have been widely…

Given the inherently costly and time-intensive nature of pixel-level annotation, the generation of synthetic datasets comprising sufficiently diverse synthetic images paired with ground-truth pixel-level annotations has garnered increasing…

Despite progress in geometry-aware domain adaptation, current methods such as GAMA still suffer from two unresolved issues: (1) insufficient disentanglement of task-relevant and task-irrelevant manifold dimensions, and (2) rigid…

We describe an unsupervised domain adaptation method for image content shift caused by viewpoint changes for a semantic segmentation task. Most existing methods perform domain alignment in a shared space and assume that the mapping from the…

Generalising deep models to new data from new centres (termed here domains) remains a challenge. This is largely attributed to shifts in data statistics (domain shifts) between source and unseen domains. Recently, gradient-based…

We propose a novel weakly-supervised semantic segmentation algorithm based on Deep Convolutional Neural Network (DCNN). Contrary to existing weakly-supervised approaches, our algorithm exploits auxiliary segmentation annotations available…

While fine-grained object recognition is an important problem in computer vision, current models are unlikely to accurately classify objects in the wild. These fully supervised models need additional annotated images to classify objects in…

Remote sensing image segmentation faces persistent challenges in distinguishing morphologically similar categories and adapting to diverse scene variations. While existing methods rely on implicit representation learning paradigms, they…

We present a novel domain adaptation framework that uses morphologic segmentation to translate images from arbitrary input domains (real and synthetic) into a uniform output domain. Our framework is based on an established image-to-image…

Diffusion models, known for their powerful generative capabilities, play a crucial role in addressing real-world super-resolution challenges. However, these models often focus on improving local textures while neglecting the impacts of…

Self-supervised learning approaches for unsupervised domain adaptation (UDA) of semantic segmentation models suffer from challenges of predicting and selecting reasonable good quality pseudo labels. In this paper, we propose a novel…

Absolute camera pose regressors estimate the position and orientation of a camera given the captured image alone. Typically, a convolutional backbone with a multi-layer perceptron (MLP) head is trained using images and pose labels to embed…

Dense pixel-wise classification maps output by deep neural networks are of extreme importance for scene understanding. However, these maps are often partially inaccurate due to a variety of possible factors. Therefore, we propose to…

3D point cloud semantic segmentation (PCSS) is a cornerstone for environmental perception in robotic systems and autonomous driving, enabling precise scene understanding through point-wise classification. While unsupervised domain…

Effectively parsing the facade is essential to 3D building reconstruction, which is an important computer vision problem with a large amount of applications in high precision map for navigation, computer aided design, and city generation…

Domain shift presents a significant challenge in applying Deep Learning to the segmentation of 3D medical images from sources like Magnetic Resonance Imaging (MRI) and Computed Tomography (CT). Although numerous Domain Adaptation methods…