• Publications
  • Influence
Learning Emphasis Selection for Written Text in Visual Media from Crowd-Sourced Label Distributions
A model that employs end-to-end label distribution learning (LDL) on crowd-sourced data and predicts a selection distribution is proposed, capturing the inter-subjectivity (common-sense) in the audience as well as the ambiguity of the input. Expand
MakeItTalk: Speaker-Aware Talking Head Animation
A method that generates expressive talking heads from a single facial image with audio as the only input that is able to synthesize photorealistic videos of entire talking heads with full range of motion and also animate artistic paintings, sketches, 2D cartoon characters, Japanese mangas, stylized caricatures in a single unified framework. Expand
SemEval-2020 Task 10: Emphasis Selection for Written Text in Visual Media
The analysis of systems submitted to the SemEval-2020 Emphasis Selection shared task indicates that BERT and RoBERTa were the most common choice of pre-trained models used, and part of speech tag (POS) was the most useful feature. Expand
SMAA: Enhanced Subpixel Morphological Antialiasing
This method shows for the first time how to combine morphological antialiasing (MLAA) with additional multi/supersampling strategies (MSAA, SSAA) for accurate subpixel features, and how to couple it with temporal reprojection; always preserving the sharpness of the image. Expand
Capturing and stylizing hair for 3D fabrication
The first method for stylized hair capture is presented, a technique to reconstruct an individual's actual hair-style in a manner suitable for physical reproduction, and the proposed technique fits naturally in traditional pipelines for figurine reproduction. Expand
Efficient palette-based decomposition and recoloring of images via RGBXY-space geometry
An extremely scalable and efficient yet simple palette-based image decomposition algorithm that can decompose 6 MP images into layers in 20 milliseconds and a real-time layer decomposition tool in which users can interactively edit the palette to adjust the layers. Expand
Practical Morphological Anti-Aliasing
The use of anti-aliasing techniques is crucial when producing high quality graphics. Up to now, multisampling anti-aliasing (MSAA) remains the most extended solution offering superior results in realExpand
Intrinsic Light Field Images
A new decomposition algorithm is proposed that jointly optimizes the whole light field data for proper angular coherence and provides 4D intrinsic decompositions difficult to achieve with previous state‐of‐the‐art algorithms. Expand
Practical and Realistic Facial Wrinkles Animation
A method to add expressive animated wrinkles to characters, helping enrich stories through subtle visual cues by allowing the animator to independently blend multiple wrinkle maps across regions of a character’s face. Expand
Intuitive, Interactive Beard and Hair Synthesis With Generative Models
A neural network pipeline is employed that synthesizes realistic and detailed images of facial hair directly in the target image in under one second, controlled by simple and sparse guide strokes from the user defining the general structural and color properties of the target hairstyle. Expand