• Publications
  • Influence
Video magnification in presence of large motions
TLDR
We present a layer-based video magnification approach that can amplify small motions within large ones. Expand
  • 67
  • 10
  • PDF
Painting style transfer for head portraits using convolutional neural networks
TLDR
We present a new technique for transferring the painting from a head portrait onto another. Expand
  • 112
  • 7
  • PDF
Video Reflection Removal Through Spatio-Temporal Optimization
TLDR
We present a novel spatiotemporal optimization that takes n frames as input and directly estimates 2n frames as output, n for each layer. Expand
  • 20
  • 5
  • PDF
Large-scale, Fast and Accurate Shot Boundary Detection through Spatio-temporal Convolutional Neural Networks
TLDR
We present the largest evaluation to date for one SBD algorithm, on real and synthetic data, containing more than 4.85 million frames. Expand
  • 21
  • 4
  • PDF
On Learning Associations of Faces and Voices
TLDR
We learn the co-embedding of modal representations of human faces and voices, and evaluate the learned representations extensively, revealing unsupervised correlations to demographic, prosodic, and facial features. Expand
  • 27
  • 4
  • PDF
A Dataset of Flash and Ambient Illumination Pairs from the Crowd
TLDR
We present a dataset of thousands of ambient and flash illumination pairs to enable studying flash photography and other applications that can benefit from having separate illuminations. Expand
  • 14
  • 4
  • PDF
Learning-based Video Motion Magnification
TLDR
We present the first learning-based approach for the video motion magnification, which achieves high-quality magnification with fewer ringing artifacts and better noise characteristics than previous methods. Expand
  • 25
  • 3
  • PDF
StyleRig: Rigging StyleGAN for 3D Control Over Portrait Images
TLDR
We present the first method to provide a face rig-like control over a pretrained and fixed StyleGAN via a 3DMM. Expand
  • 13
  • 2
  • PDF
Neural Voice Puppetry: Audio-driven Facial Reenactment
TLDR
We present Neural Voice Puppetry, a novel approach for audio-driven facial video synthesis. Expand
  • 21
  • 1
  • PDF
Crowd-Guided Ensembles: How Can We Choreograph Crowd Workers for Video Segmentation?
TLDR
In this work, we propose two ensemble methods leveraging a crowd workforce to improve video annotation, with a focus on video object segmentation. Expand
  • 9
  • 1
  • PDF