44 citations · 115 across the 26 of their papers we have counts for
28 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…
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…
VRS-NeRF: Visual Relocalization with Sparse Neural Radiance Field
Fei Xue, Ignas Budvytis, Daniel Olmeda Reino +1
Visual relocalization is a key technique to autonomous driving, robotics, and virtual/augmented reality. After decades of explorations, absolute pose regression (APR), scene coordi…
Task Agnostic Architecture for Algorithm Induction via Implicit Composition
Sahil J. Sindhi, Ignas Budvytis
Different fields in applied machine learning such as computer vision, speech or natural language processing have been building domain-specialised solutions. Currently, we are witne…
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…
DiaLoc: An Iterative Approach to Embodied Dialog Localization
Chao Zhang, Mohan Li, Ignas Budvytis +1
Multimodal learning has advanced the performance for many vision-language tasks. However, most existing works in embodied dialog research focus on navigation and leave the localiza…
Function-constrained Program Synthesis
Patrick Hajali, Ignas Budvytis
This work introduces (1) a technique that allows large language models (LLMs) to leverage user-provided code when solving programming tasks and (2) a method to iteratively generate…
A Neural Height-Map Approach for the Binocular Photometric Stereo Problem
Fotios Logothetis, Ignas Budvytis, Roberto Cipolla
In this work we propose a novel, highly practical, binocular photometric stereo (PS) framework, which has same acquisition speed as single view PS, however significantly improves t…
Sparse Multi-Object Render-and-Compare
Florian Langer, Ignas Budvytis, Roberto Cipolla
Reconstructing 3D shape and pose of static objects from a single image is an essential task for various industries, including robotics, augmented reality, and digital content creat…
HuManiFlow: Ancestor-Conditioned Normalising Flows on SO(3) Manifolds for Human Pose and Shape Distribution Estimation
Akash Sengupta, Ignas Budvytis, Roberto Cipolla
Monocular 3D human pose and shape estimation is an ill-posed problem since multiple 3D solutions can explain a 2D image of a subject. Recent approaches predict a probability distri…
SFD2: Semantic-guided Feature Detection and Description
Fei Xue, Ignas Budvytis, Roberto Cipolla
Visual localization is a fundamental task for various applications including autonomous driving and robotics. Prior methods focus on extracting large amounts of often redundant loc…
IMP: Iterative Matching and Pose Estimation with Adaptive Pooling
Fei Xue, Ignas Budvytis, Roberto Cipolla
Previous methods solve feature matching and pose estimation using a two-stage process by first finding matches and then estimating the pose. As they ignore the geometric relationsh…
A CNN Based Approach for the Point-Light Photometric Stereo Problem
Fotios Logothetis, Roberto Mecca, Ignas Budvytis +1
Reconstructing the 3D shape of an object using several images under different light sources is a very challenging task, especially when realistic assumptions such as light propagat…
IronDepth: Iterative Refinement of Single-View Depth using Surface Normal and its Uncertainty
Gwangbin Bae, Ignas Budvytis, Roberto Cipolla
Single image surface normal estimation and depth estimation are closely related problems as the former can be calculated from the latter. However, the surface normals computed from…
SPARC: Sparse Render-and-Compare for CAD model alignment in a single RGB image
Florian Langer, Gwangbin Bae, Ignas Budvytis +1
Estimating 3D shapes and poses of static objects from a single image has important applications for robotics, augmented reality and digital content creation. Often this is done thr…
Multi-View Depth Estimation by Fusing Single-View Depth Probability with Multi-View Geometry
Gwangbin Bae, Ignas Budvytis, Roberto Cipolla
Multi-view depth estimation methods typically require the computation of a multi-view cost-volume, which leads to huge memory consumption and slow inference. Furthermore, multi-vie…
Probabilistic Estimation of 3D Human Shape and Pose with a Semantic Local Parametric Model
Akash Sengupta, Ignas Budvytis, Roberto Cipolla
This paper addresses the problem of 3D human body shape and pose estimation from RGB images. Some recent approaches to this task predict probability distributions over human body m…
Leveraging Geometry for Shape Estimation from a Single RGB Image
Florian Langer, Ignas Budvytis, Roberto Cipolla
Predicting 3D shapes and poses of static objects from a single RGB image is an important research area in modern computer vision. Its applications range from augmented reality to r…
Hierarchical Kinematic Probability Distributions for 3D Human Shape and Pose Estimation from Images in the Wild
Akash Sengupta, Ignas Budvytis, Roberto Cipolla
This paper addresses the problem of 3D human body shape and pose estimation from an RGB image. This is often an ill-posed problem, since multiple plausible 3D bodies may match the…
Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimation
Gwangbin Bae, Ignas Budvytis, Roberto Cipolla
Surface normal estimation from a single image is an important task in 3D scene understanding. In this paper, we address two limitations shared by the existing methods: the inabilit…
LUCES: A Dataset for Near-Field Point Light Source Photometric Stereo
Roberto Mecca, Fotios Logothetis, Ignas Budvytis +1
Three-dimensional reconstruction of objects from shading information is a challenging task in computer vision. As most of the approaches facing the Photometric Stereo problem use s…
Probabilistic 3D Human Shape and Pose Estimation from Multiple Unconstrained Images in the Wild
Akash Sengupta, Ignas Budvytis, Roberto Cipolla
This paper addresses the problem of 3D human body shape and pose estimation from RGB images. Recent progress in this field has focused on single images, video or multi-view images…