5 papers
Training-Free Multi-Concept Image Editing
Niki Foteinopoulou, Ignas Budvytis, Stephan Liwicki
Training-free image editing with diffusion models is highly desirable yet is complex and remains a significant challenge. While recent optimisation-based methods achieve strong zer…
LoRAtorio: An intrinsic approach to LoRA Skill Composition
Niki Foteinopoulou, Ignas Budvytis, Stephan Liwicki
Low-Rank Adaptation (LoRA) has become a widely adopted technique in text-to-image diffusion models, enabling the personalisation of visual concepts such as characters, styles, and…
PRAM: Place Recognition Anywhere Model for Efficient Visual Localization
Fei Xue, Ignas Budvytis, Roberto Cipolla
Visual localization is a key technique to a variety of applications, e.g., autonomous driving, AR/VR, and robotics. For these real applications, both efficiency and accuracy are im…
LUCES-MV: A Multi-View Dataset for Near-Field Point Light Source Photometric Stereo
Fotios Logothetis, Ignas Budvytis, Stephan Liwicki +1
The biggest improvements in Photometric Stereo (PS) field has recently come from adoption of differentiable volumetric rendering techniques such as NeRF or Neural SDF achieving imp…
NPLMV-PS: Neural Point-Light Multi-View Photometric Stereo
Fotios Logothetis, Ignas Budvytis, Roberto Cipolla
In this work we present a novel multi-view photometric stereo (MVPS) method. Like many works in 3D reconstruction we are leveraging neural shape representations and learnt renderer…