3 citations · 8 across the 13 of their papers we have counts for
16 papers
Efficient 3D Gaussian Head Avatars for Edge Devices
Umar Farooq, Jean-Yves Guillemaut, Adrian Hilton +1
Generative 3D Gaussian head avatars provide high-quality, efficient rendering, but synthesising the Gaussian representation remains computationally expensive, limiting deployment o…
Image-based Facial Rig Inversion
Tianxiang Yang, Marco Volino, Armin Mustafa +2
We present an image-based rig inversion framework that leverages two modalities: RGB appearance and RGB-encoded normal maps. Each modality is processed by an independent Hiera tran…
Realistic Clothed Human and Object Joint Reconstruction from a Single Image
Ayushi Dutta, Marco Pesavento, Marco Volino +2
Recent approaches to jointly reconstruct 3D humans and objects from a single RGB image represent 3D shapes with template-based or coarse models, which fail to capture details of lo…
Optimized 3D Gaussian Splatting using Coarse-to-Fine Image Frequency Modulation
Umar Farooq, Jean-Yves Guillemaut, Adrian Hilton +1
The field of Novel View Synthesis has been revolutionized by 3D Gaussian Splatting (3DGS), which enables high-quality scene reconstruction that can be rendered in real-time. 3DGS-b…
COSMU: Complete 3D human shape from monocular unconstrained images
Marco Pesavento, Marco Volino, Adrian Hilton
We present a novel framework to reconstruct complete 3D human shapes from a given target image by leveraging monocular unconstrained images. The objective of this work is to reprod…
Improving Gaussian Splatting with Localized Points Management
Haosen Yang, Chenhao Zhang, Wenqing Wang +4
Point management is critical for optimizing 3D Gaussian Splatting models, as point initiation (e.g., via structure from motion) is often distributionally inappropriate. Typically,…
ANIM: Accurate Neural Implicit Model for Human Reconstruction from a single RGB-D image
Marco Pesavento, Yuanlu Xu, Nikolaos Sarafianos +7
Recent progress in human shape learning, shows that neural implicit models are effective in generating 3D human surfaces from limited number of views, and even from a single RGB im…
Tragic Talkers: A Shakespearean Sound- and Light-Field Dataset for Audio-Visual Machine Learning Research
Davide Berghi, Marco Volino, Philip J. B. Jackson
3D audio-visual production aims to deliver immersive and interactive experiences to the consumer. Yet, faithfully reproducing real-world 3D scenes remains a challenging task. This…
Super-resolution 3D Human Shape from a Single Low-Resolution Image
Marco Pesavento, Marco Volino, Adrian Hilton
We propose a novel framework to reconstruct super-resolution human shape from a single low-resolution input image. The approach overcomes limitations of existing approaches that re…
Super-Resolution Appearance Transfer for 4D Human Performances
Marco Pesavento, Marco Volino, Adrian Hilton
A common problem in the 4D reconstruction of people from multi-view video is the quality of the captured dynamic texture appearance which depends on both the camera resolution and…
Attention-based Multi-Reference Learning for Image Super-Resolution
Marco Pesavento, Marco Volino, Adrian Hilton
This paper proposes a novel Attention-based Multi-Reference Super-resolution network (AMRSR) that, given a low-resolution image, learns to adaptively transfer the most similar text…
Naturalistic audio-visual volumetric sequences dataset of sounding actions for six degree-of-freedom interaction
Hanne Stenzel, Davide Berghi, Marco Volino +1
As audio-visual systems increasingly bring immersive and interactive capabilities into our work and leisure activities, so the need for naturalistic test material grows. New volume…
Audio-Visual Spatial Aligment Requirements of Central and Peripheral Object Events
Davide Berghi, Hanne Stenzel, Marco Volino +2
Immersive audio-visual perception relies on the spatial integration of both auditory and visual information which are heterogeneous sensing modalities with different fields of rece…
Temporally Coherent General Dynamic Scene Reconstruction
Armin Mustafa, Marco Volino, Hansung Kim +2
Existing techniques for dynamic scene reconstruction from multiple wide-baseline cameras primarily focus on reconstruction in controlled environments, with fixed calibrated cameras…
Volumetric performance capture from minimal camera viewpoints
Andrew Gilbert, Marco Volino, John Collomosse +1
We present a convolutional autoencoder that enables high fidelity volumetric reconstructions of human performance to be captured from multi-view video comprising only a small set o…
4D Temporally Coherent Light-field Video
Armin Mustafa, Marco Volino, Jean-yves Guillemaut +1
Light-field video has recently been used in virtual and augmented reality applications to increase realism and immersion. However, existing light-field methods are generally limite…