Related papers: Reg-TTR, Test-Time Refinement for Fast, Robust and…

Session types express and enforce safe communication in concurrent message-passing systems by statically capturing the interaction protocols between processes in the type. Recent works extend session types with arithmetic refinements, which…

Custom and natural lighting conditions can be emulated in images of the scene during post-editing. Extraordinary capabilities of the deep learning framework can be utilized for such purpose. Deep image relighting allows automatic photo…

Medical image analysis tasks often focus on regions or structures located in a particular location within the patient's body. Often large parts of the image may not be of interest for the image analysis task. When using deep-learning based…

Retrieval augmented generation (RAG) pipelines are commonly used in tasks such as question-answering (QA), relying on retrieving relevant documents from a vector store computed using a pretrained embedding model. However, if the retrieved…

A novel non-rigid image registration algorithm is built upon fully convolutional networks (FCNs) to optimize and learn spatial transformations between pairs of images to be registered in a self-supervised learning framework. Different from…

Image registration is a fundamental medical image analysis task, and a wide variety of approaches have been proposed. However, only a few studies have comprehensively compared medical image registration approaches on a wide range of…

Deep neural networks have become popular in many supervised learning tasks, but they may suffer from overfitting when the training dataset is limited. To mitigate this, many researchers use data augmentation, which is a widely used and…

Deep Learning-based 2D/3D registration enables fast, robust, and accurate X-ray to CT image fusion when large annotated paired datasets are available for training. However, the need for paired CT volume and X-ray images with ground truth…

Diffusion models achieve superior generation quality but suffer from slow generation speed due to the iterative nature of denoising. In contrast, consistency models, a new generative family, achieve competitive performance with…

Multi-view 3D reconstruction has remained an essential yet challenging problem in the field of computer vision. While DUSt3R and its successors have achieved breakthroughs in 3D reconstruction from unposed images, these methods exhibit…

Robust traffic sign detection and recognition (TSDR) is of paramount importance for the successful realization of autonomous vehicle technology. The importance of this task has led to a vast amount of research efforts and many promising…

Image Registration (IR) is the process of aligning two (or more) images of the same scene taken at different times, different viewpoints and/or by different sensors. It is an important, crucial step in various image analysis tasks where…

While language models have shown remarkable performance across diverse tasks, they still encounter challenges in complex reasoning scenarios. Recent research suggests that language models trained on linearized search traces toward…

Image restoration faces challenges including ineffective feature fusion, computational bottlenecks and inefficient diffusion processes. To address these, we propose DiffRWKVIR, a novel framework unifying Test-Time Training (TTT) with…

In this paper, we introduce Technical-Embeddings, a novel framework designed to optimize semantic retrieval in technical documentation, with applications in both hardware and software development. Our approach addresses the challenges of…

With technological advances leading to an increase in mechanisms for image tampering, fraud detection methods must continue to be upgraded to match their sophistication. One problem with current methods is that they require prior knowledge…

Image registration is the inference of transformations relating noisy and distorted images. It is fundamental in computer vision, experimental physics, and medical imaging. Many algorithms and analyses exist for inferring shift, rotation,…

Deep learning (DL) image registration methods amortize the costly pair-wise iterative optimization by training deep neural networks to predict the optimal transformation in one fast forward-pass. In this work, we bridge the gap between…

The success of modern deep learning is attributed to two key elements: huge amounts of training data and large model sizes. Where a vast amount of data allows the model to learn more features, the large model architecture boosts the…

The visual models pretrained on large-scale benchmarks encode general knowledge and prove effective in building more powerful representations for downstream tasks. Most existing approaches follow the fine-tuning paradigm, either by…