12 papers · 1 filter
DNA-Prior: Unsupervised Denoise Anything via Dual-Domain Prior
Yanqi Cheng, Chun-Wun Cheng, Jim Denholm +5
Medical imaging pipelines critically rely on robust denoising to stabilise downstream tasks such as segmentation and reconstruction. However, many existing denoisers depend on larg…
Deep Spectral Prior
Yanqi Cheng, Xuxiang Zhao, Tieyong Zeng +3
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 Prio…
GeoSplat: A Deep Dive into Geometry-Constrained Gaussian Splatting
Yangming Li, Chaoyu Liu, Lihao Liu +2
A few recent works explored incorporating geometric priors to regularize the optimization of Gaussian splatting, further improving its performance. However, those early studies mai…
Bridging Annotation Gaps: Transferring Labels to Align Object Detection Datasets
Mikhail Kennerley, Angelica Aviles-Rivero, Carola-Bibiane Schönlieb +1
Combining multiple object detection datasets offers a path to improved generalisation but is hindered by inconsistencies in class semantics and bounding box annotations. Some metho…
DiTASK: Multi-Task Fine-Tuning with Diffeomorphic Transformations
Krishna Sri Ipsit Mantri, Carola-Bibiane Schönlieb, Bruno Ribeiro +2
Pre-trained Vision Transformers now serve as powerful tools for computer vision. Yet, efficiently adapting them for multiple tasks remains a challenge that arises from the need to…
You KAN Do It in a Single Shot: Plug-and-Play Methods with Single-Instance Priors
Yanqi Cheng, Carola-Bibiane Schönlieb, Angelica I Aviles-Rivero
The use of Plug-and-Play (PnP) methods has become a central approach for solving inverse problems, with denoisers serving as regularising priors that guide optimisation towards a c…