153 citations · 259 across the 26 of their papers we have counts for
29 papers
DP-RFT: Learning to Generate Synthetic Text via Differentially Private Reinforcement Fine-Tuning
Fangyuan Xu, Sihao Chen, Zinan Lin +13
Differentially private (DP) synthetic data generation plays a pivotal role in developing large language models (LLMs) on private data, where data owners cannot provide eyes-on acce…
DAViD: Data-efficient and Accurate Vision Models from Synthetic Data
Fatemeh Saleh, Sadegh Aliakbarian, Charlie Hewitt +5
The state of the art in human-centric computer vision achieves high accuracy and robustness across a diverse range of tasks. The most effective models in this domain have billions…
Total-Editing: Head Avatar with Editable Appearance, Motion, and Lighting
Yizhou Zhao, Chunjiang Liu, Haoyu Chen +6
Face reenactment and portrait relighting are essential tasks in portrait editing, yet they are typically addressed independently, without much synergy. Most face reenactment method…
Differentially Private Synthetic Data via APIs 3: Using Simulators Instead of Foundation Model
Zinan Lin, Tadas Baltrusaitis, Wenyu Wang +1
Differentially private (DP) synthetic data enables the use of sensitive datasets while providing strong privacy guarantees. Recently, Private Evolution (PE) has emerged as a promis…
GASP: Gaussian Avatars with Synthetic Priors
Jack Saunders, Charlie Hewitt, Yanan Jian +8
Gaussian Splatting has changed the game for real-time photo-realistic rendering. One of the most popular applications of Gaussian Splatting is to create animatable avatars, known a…
SympCam: Remote Optical Measurement of Sympathetic Arousal
Björn Braun, Daniel McDuff, Tadas Baltrusaitis +3
Recent work has shown that a person's sympathetic arousal can be estimated from facial videos alone using basic signal processing. This opens up new possibilities in the field of t…
Eyelid Fold Consistency in Facial Modeling
Lohit Petikam, Charlie Hewitt, Fatemeh Saleh +1
Eyelid shape is integral to identity and likeness in human facial modeling. Human eyelids are diverse in appearance with varied skin fold and epicanthal fold morphology between ind…
Hairmony: Fairness-aware hairstyle classification
Givi Meishvili, James Clemoes, Charlie Hewitt +9
We present a method for prediction of a person's hairstyle from a single image. Despite growing use cases in user digitization and enrollment for virtual experiences, available met…
Look Ma, no markers: holistic performance capture without the hassle
Charlie Hewitt, Fatemeh Saleh, Sadegh Aliakbarian +8
We tackle the problem of highly-accurate, holistic performance capture for the face, body and hands simultaneously. Motion-capture technologies used in film and game production typ…
Video-based sympathetic arousal assessment via peripheral blood flow estimation
Bjoern Braun, Daniel McDuff, Tadas Baltrusaitis +1
Electrodermal activity (EDA) is considered a standard marker of sympathetic activity. However, traditional EDA measurement requires electrodes in steady contact with the skin. Can…
HiFace: High-Fidelity 3D Face Reconstruction by Learning Static and Dynamic Details
Zenghao Chai, Tianke Zhang, Tianyu He +7
3D Morphable Models (3DMMs) demonstrate great potential for reconstructing faithful and animatable 3D facial surfaces from a single image. The facial surface is influenced by the c…
Procedural Humans for Computer Vision
Charlie Hewitt, Tadas Baltrušaitis, Erroll Wood +3
Recent work has shown the benefits of synthetic data for use in computer vision, with applications ranging from autonomous driving to face landmark detection and reconstruction. Th…
Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusion
Tengfei Wang, Bo Zhang, Ting Zhang +8
This paper presents a 3D generative model that uses diffusion models to automatically generate 3D digital avatars represented as neural radiance fields. A significant challenge in…
Photo-realistic 360 Head Avatars in the Wild
Stanislaw Szymanowicz, Virginia Estellers, Tadas Baltrusaitis +1
Delivering immersive, 3D experiences for human communication requires a method to obtain 360 degree photo-realistic avatars of humans. To make these experiences accessible to all,…
Mesh-Tension Driven Expression-Based Wrinkles for Synthetic Faces
Chirag Raman, Charlie Hewitt, Erroll Wood +1
Recent advances in synthesizing realistic faces have shown that synthetic training data can replace real data for various face-related computer vision tasks. A question arises: how…
DigiFace-1M: 1 Million Digital Face Images for Face Recognition
Gwangbin Bae, Martin de La Gorce, Tadas Baltrusaitis +5
State-of-the-art face recognition models show impressive accuracy, achieving over 99.8% on Labeled Faces in the Wild (LFW) dataset. Such models are trained on large-scale datasets…
SCAMPS: Synthetics for Camera Measurement of Physiological Signals
Daniel McDuff, Miah Wander, Xin Liu +4
The use of cameras and computational algorithms for noninvasive, low-cost and scalable measurement of physiological (e.g., cardiac and pulmonary) vital signs is very attractive. Ho…
3D face reconstruction with dense landmarks
Erroll Wood, Tadas Baltrusaitis, Charlie Hewitt +11
Landmarks often play a key role in face analysis, but many aspects of identity or expression cannot be represented by sparse landmarks alone. Thus, in order to reconstruct faces mo…
Synthetic Data for Multi-Parameter Camera-Based Physiological Sensing
Daniel McDuff, Xin Liu, Javier Hernandez +2
Synthetic data is a powerful tool in training data hungry deep learning algorithms. However, to date, camera-based physiological sensing has not taken full advantage of these techn…
Advancing Non-Contact Vital Sign Measurement using Synthetic Avatars
Daniel McDuff, Javier Hernandez, Erroll Wood +2
Non-contact physiological measurement has the potential to provide low-cost, non-invasive health monitoring. However, machine vision approaches are often limited by the availabilit…
A high fidelity synthetic face framework for computer vision
Tadas Baltrusaitis, Erroll Wood, Virginia Estellers +6
Analysis of faces is one of the core applications of computer vision, with tasks ranging from landmark alignment, head pose estimation, expression recognition, and face recognition…
CONFIG: Controllable Neural Face Image Generation
Marek Kowalski, Stephan J. Garbin, Virginia Estellers +3
Our ability to sample realistic natural images, particularly faces, has advanced by leaps and bounds in recent years, yet our ability to exert fine-tuned control over the generativ…
Multimodal Sentiment Analysis with Word-Level Fusion and Reinforcement Learning
Minghai Chen, Sen Wang, Paul Pu Liang +3
With the increasing popularity of video sharing websites such as YouTube and Facebook, multimodal sentiment analysis has received increasing attention from the scientific community…
Attended End-to-end Architecture for Age Estimation from Facial Expression Videos
Wenjie Pei, Hamdi Dibeklioğlu, Tadas Baltrušaitis +1
The main challenges of age estimation from facial expression videos lie not only in the modeling of the static facial appearance, but also in the capturing of the temporal facial d…