Related papers: Uncertainty-Guided Spatial Pruning Architecture fo…
Using a deterministic framework allows us to estimate a function with the purpose of interpolating data in spatial statistics. Radial basis functions are commonly used for scattered data interpolation in a d-dimensional space, however,…
U-Net has been the go-to architecture for medical image segmentation tasks, however computational challenges arise when extending the U-Net architecture to 3D images. We propose the Implicit U-Net architecture that adapts the efficient…
We propose a new fast algorithm for solving one of the standard formulations of frame-based image deconvolution: an unconstrained optimization problem, involving an $\ell_2$ data-fidelity term and a non-smooth regularizer. Our approach is…
Ultra-high-definition (UHD) video denoising requires simultaneously suppressing complex spatio-temporal degradations, preserving fine textures and chromatic stability, and maintaining efficient full-resolution 4K deployment. In this paper,…
In general, deep learning-based video frame interpolation (VFI) methods have predominantly focused on estimating motion vectors between two input frames and warping them to the target time. While this approach has shown impressive…
Accurately quantifying vitiligo extent in routine clinical photographs is crucial for longitudinal monitoring of treatment response. We propose a trustworthy, frequency-aware segmentation framework built on three synergistic pillars: (1) a…
Video frame interpolation (VFI) is a challenging task that aims to generate intermediate frames between two consecutive frames in a video. Existing learning-based VFI methods have achieved great success, but they still suffer from limited…
We cast motion planning under uncertainty as a stochastic optimal control problem, where the optimal posterior distribution has an explicit form. To approximate this posterior, this work frames an optimization problem in the space of…
Visual place recognition (VPR) is crucial for robots to identify previously visited locations, playing an important role in autonomous navigation in both indoor and outdoor environments. However, most existing VPR datasets are limited to…
We introduce the Deep Spectral Prior (DSP), a new framework for unsupervised image reconstruction that operates entirely in the complex frequency domain. Unlike the Deep Image Prior (DIP), which optimises pixel-level errors and is highly…
The growing size of neural language models has led to increased attention in model compression. The two predominant approaches are pruning, which gradually removes weights from a pre-trained model, and distillation, which trains a smaller…
Video tasks are compute-heavy and thus pose a challenge when deploying in real-time applications, particularly for tasks that require state-of-the-art Vision Transformers (ViTs). Several research efforts have tried to address this challenge…
Global localisation from visual data is a challenging problem applicable to many robotics domains. Prior works have shown that neural networks can be trained to map images of an environment to absolute camera pose within that environment,…
To apply deep CNNs to mobile terminals and portable devices, many scholars have recently worked on the compressing and accelerating deep convolutional neural networks. Based on this, we propose a novel uniform channel pruning (UCP) method…
Reconstructing the 3D shape of a deformable environment from the information captured by a moving depth camera is highly relevant to surgery. The underlying challenge is the fact that simultaneously estimating camera motion and tissue…
Lightweight and effective models are essential for devices with limited resources, such as intelligent vehicles. Structured pruning offers a promising approach to model compression and efficiency enhancement. However, existing methods often…
Vision-Language Models require efficient adaptation to continually emerging downstream tasks. While Parameter-Efficient Fine-Tuning mitigates catastrophic forgetting, assigning isolated modules per task leads to parameter explosion.…
Recent years have witnessed the remarkable success of implicit neural representation methods. The recent work Local Implicit Image Function (LIIF) has achieved satisfactory performance for continuous image representation, where pixel values…
With the recent trend for ultra high definition displays, the demand for high quality and efficient video super-resolution (VSR) has become more important than ever. Previous methods adopt complex motion compensation strategies to exploit…
Recent advancements have highlighted the Mamba framework, a state-space model known for its efficiency in capturing long-range dependencies with linear computational complexity. While Mamba has shown competitive performance in medical image…