Search Results for author: John Collomosse

Found 33 papers, 9 papers with code

PARASOL: Parametric Style Control for Diffusion Image Synthesis

no code implementations11 Mar 2023 Gemma Canet Tarrés, Dan Ruta, Tu Bui, John Collomosse

We propose PARASOL, a multi-modal synthesis model that enables disentangled, parametric control of the visual style of the image by jointly conditioning synthesis on both content and a fine-grained visual style embedding.

Image Generation

Audio-Visual Contrastive Learning with Temporal Self-Supervision

no code implementations15 Feb 2023 Simon Jenni, Alexander Black, John Collomosse

We propose a self-supervised learning approach for videos that learns representations of both the RGB frames and the accompanying audio without human supervision.

Action Recognition Audio Classification +3

SceneComposer: Any-Level Semantic Image Synthesis

no code implementations21 Nov 2022 Yu Zeng, Zhe Lin, Jianming Zhang, Qing Liu, John Collomosse, Jason Kuen, Vishal M. Patel

We propose a new framework for conditional image synthesis from semantic layouts of any precision levels, ranging from pure text to a 2D semantic canvas with precise shapes.

Image Generation

Text-to-Image Generation via Implicit Visual Guidance and Hypernetwork

no code implementations17 Aug 2022 Xin Yuan, Zhe Lin, Jason Kuen, Jianming Zhang, John Collomosse

We develop an approach for text-to-image generation that embraces additional retrieval images, driven by a combination of implicit visual guidance loss and generative objectives.

Retrieval Text-to-Image Generation

HyperNST: Hyper-Networks for Neural Style Transfer

no code implementations9 Aug 2022 Dan Ruta, Andrew Gilbert, Saeid Motiian, Baldo Faieta, Zhe Lin, John Collomosse

We present HyperNST; a neural style transfer (NST) technique for the artistic stylization of images, based on Hyper-networks and the StyleGAN2 architecture.

Style Transfer

RepMix: Representation Mixing for Robust Attribution of Synthesized Images

1 code implementation5 Jul 2022 Tu Bui, Ning Yu, John Collomosse

Uniquely, we present a solution to this task capable of 1) matching images invariant to their semantic content; 2) robust to benign transformations (changes in quality, resolution, shape, etc.)

SImProv: Scalable Image Provenance Framework for Robust Content Attribution

no code implementations28 Jun 2022 Alexander Black, Tu Bui, Simon Jenni, Zhifei Zhang, Viswanathan Swaminanthan, John Collomosse

We present SImProv - a scalable image provenance framework to match a query image back to a trusted database of originals and identify possible manipulations on the query.

Re-Ranking Retrieval

CoGS: Controllable Generation and Search from Sketch and Style

no code implementations17 Mar 2022 Cusuh Ham, Gemma Canet Tarres, Tu Bui, James Hays, Zhe Lin, John Collomosse

CoGS enables exploration of diverse appearance possibilities for a given sketched object, enabling decoupled control over the structure and the appearance of the output.

StyleBabel: Artistic Style Tagging and Captioning

no code implementations10 Mar 2022 Dan Ruta, Andrew Gilbert, Pranav Aggarwal, Naveen Marri, Ajinkya Kale, Jo Briggs, Chris Speed, Hailin Jin, Baldo Faieta, Alex Filipkowski, Zhe Lin, John Collomosse

We present StyleBabel, a unique open access dataset of natural language captions and free-form tags describing the artistic style of over 135K digital artworks, collected via a novel participatory method from experts studying at specialist art and design schools.

Representation Learning Retrieval +1

VPN: Video Provenance Network for Robust Content Attribution

no code implementations21 Sep 2021 Alexander Black, Tu Bui, Simon Jenni, Vishy Swaminathan, John Collomosse

We present VPN - a content attribution method for recovering provenance information from videos shared online.

Contrastive Learning

Scene Designer: a Unified Model for Scene Search and Synthesis from Sketch

1 code implementation16 Aug 2021 Leo Sampaio Ferraz Ribeiro, Tu Bui, John Collomosse, Moacir Ponti

Scene Designer is a novel method for searching and generating images using free-hand sketches of scene compositions; i. e. drawings that describe both the appearance and relative positions of objects.

Contrastive Learning

OSCAR-Net: Object-centric Scene Graph Attention for Image Attribution

no code implementations ICCV 2021 Eric Nguyen, Tu Bui, Vishy Swaminathan, John Collomosse

Our key contribution is OSCAR-Net (Object-centric Scene Graph Attention for Image Attribution Network); a robust image hashing model inspired by recent successes of Transformers in the visual domain.

Contrastive Learning Graph Attention

Compositional Sketch Search

1 code implementation15 Jun 2021 Alexander Black, Tu Bui, Long Mai, Hailin Jin, John Collomosse

We present an algorithm for searching image collections using free-hand sketches that describe the appearance and relative positions of multiple objects.

Quantization Retrieval +1

Magic Layouts: Structural Prior for Component Detection in User Interface Designs

no code implementations CVPR 2021 Dipu Manandhar, Hailin Jin, John Collomosse

We present Magic Layouts; a method for parsing screenshots or hand-drawn sketches of user interface (UI) layouts.

Sketchformer: Transformer-based Representation for Sketched Structure

1 code implementation CVPR 2020 Leo Sampaio Ferraz Ribeiro, Tu Bui, John Collomosse, Moacir Ponti

Sketchformer is a novel transformer-based representation for encoding free-hand sketches input in a vector form, i. e. as a sequence of strokes.

Cross-Modal Retrieval Dictionary Learning +3

Neural Architecture Search for Deep Image Prior

2 code implementations14 Jan 2020 Kary Ho, Andrew Gilbert, Hailin Jin, John Collomosse

We present a neural architecture search (NAS) technique to enhance the performance of unsupervised image de-noising, in-painting and super-resolution under the recently proposed Deep Image Prior (DIP).

Image Restoration Neural Architecture Search +1

An Internal Learning Approach to Video Inpainting

1 code implementation ICCV 2019 Haotian Zhang, Long Mai, Ning Xu, Zhaowen Wang, John Collomosse, Hailin Jin

We propose a novel video inpainting algorithm that simultaneously hallucinates missing appearance and motion (optical flow) information, building upon the recent 'Deep Image Prior' (DIP) that exploits convolutional network architectures to enforce plausible texture in static images.

Optical Flow Estimation Video Inpainting

Semantic Estimation of 3D Body Shape and Pose using Minimal Cameras

no code implementations8 Aug 2019 Andrew Gilbert, Matthew Trumble, Adrian Hilton, John Collomosse

We aim to simultaneously estimate the 3D articulated pose and high fidelity volumetric occupancy of human performance, from multiple viewpoint video (MVV) with as few as two views.

3D Human Pose Estimation

Robust Synthesis of Adversarial Visual Examples Using a Deep Image Prior

no code implementations3 Jul 2019 Thomas Gittings, Steve Schneider, John Collomosse

We present a novel method for generating robust adversarial image examples building upon the recent `deep image prior' (DIP) that exploits convolutional network architectures to enforce plausible texture in image synthesis.

Image Generation

TAPESTRY: A Blockchain based Service for Trusted Interaction Online

no code implementations15 May 2019 Yifan Yang, Daniel Cooper, John Collomosse, Constantin C. Drăgan, Mark Manulis, Jamie Steane, Arthi Manohar, Jo Briggs, Helen Jones, Wendy Moncur

We present a novel blockchain based service for proving the provenance of online digital identity, exposed as an assistive tool to help non-expert users make better decisions about whom to trust online.

Privacy Preserving

LiveSketch: Query Perturbations for Guided Sketch-based Visual Search

no code implementations CVPR 2019 John Collomosse, Tu Bui, Hailin Jin

LiveSketch is a novel algorithm for searching large image collections using hand-sketched queries.

Volumetric performance capture from minimal camera viewpoints

no code implementations ECCV 2018 Andrew Gilbert, Marco Volino, John Collomosse, Adrian Hilton

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 of camera views.

Disentangling Structure and Aesthetics for Style-Aware Image Completion

no code implementations CVPR 2018 Andrew Gilbert, John Collomosse, Hailin Jin, Brian Price

Content-aware image completion or in-painting is a fundamental tool for the correction of defects or removal of objects in images.

Sketching With Style: Visual Search With Sketches and Aesthetic Context

no code implementations ICCV 2017 John Collomosse, Tu Bui, Michael J. Wilber, Chen Fang, Hailin Jin

We propose a novel measure of visual similarity for image retrieval that incorporates both structural and aesthetic (style) constraints.

Image Retrieval Retrieval

BAM! The Behance Artistic Media Dataset for Recognition Beyond Photography

no code implementations ICCV 2017 Michael J. Wilber, Chen Fang, Hailin Jin, Aaron Hertzmann, John Collomosse, Serge Belongie

Furthermore, we carry out baseline experiments to show the value of this dataset for artistic style prediction, for improving the generality of existing object classifiers, and for the study of visual domain adaptation.

Domain Adaptation

Generalisation and Sharing in Triplet Convnets for Sketch based Visual Search

no code implementations16 Nov 2016 Tu Bui, Leonardo Ribeiro, Moacir Ponti, John Collomosse

We propose and evaluate several triplet CNN architectures for measuring the similarity between sketches and photographs, within the context of the sketch based image retrieval (SBIR) task.

Data Augmentation Dimensionality Reduction +3

Cannot find the paper you are looking for? You can Submit a new open access paper.