• Publications
  • Influence
KNN Matting
TLDR
We are interested in a general alpha matting approach for the simultaneous extraction of multiple image layers; each layer may have disjoint segments for material matting not limited to foreground mattes typical of natural image matting. Expand
  • 306
  • 45
  • PDF
Unified Multisensory Perception: Weakly-Supervised Audio-Visual Video Parsing
TLDR
We introduce a new problem, named audio-visual video parsing, which aims to parse a video into temporal event segments and label them as either audible, visible, or both. Expand
  • 12
  • 4
  • PDF
AirCode: Unobtrusive Physical Tags for Digital Fabrication
TLDR
We present AirCode, a technique that allows the user to tag physically fabricated objects with given information in imperceptible yet machinereadable tags. Expand
  • 31
  • 3
  • PDF
Motion-Aware KNN Laplacian for Video Matting
TLDR
This paper demonstrates how the nonlocal principle benefits video matting via the KNN Laplacian, which comes with a straightforward implementation using motion-aware K nearest neighbors. Expand
  • 31
  • 3
  • PDF
MakeItTalk: Speaker-Aware Talking Head Animation
TLDR
We present a method that generates expressive talking heads from a single facial image with audio as the only input. Expand
  • 9
  • 3
  • PDF
Expediting precomputation for reduced deformable simulation
TLDR
We present a complete system of precomputation pipeline as a faster alternative to the classic linear and nonlinear modal analysis. Expand
  • 33
  • 2
  • PDF
Crumpling sound synthesis
TLDR
We propose a physically based algorithm that automatically synthesizes crumpling sounds for a given thin shell animation, and instantiate visually insignificant buckling events. Expand
  • 12
  • 1
  • PDF
LayerCode: optical barcodes for 3D printed shapes
TLDR
We present LayerCode, a tagging scheme that embeds a carefully designed barcode pattern in 3D printed objects as a deliberate byproduct of the 3D printing process. Expand
  • 7
  • 1
  • PDF
Deep Audio Prior
TLDR
A randomly-initialized neural network can be used with carefully designed audio prior to tackle challenging audio problems such as universal blind source separation, interactive audio editing, audio texture synthesis, and audio co-separation. Expand
  • 5
  • 1
  • PDF
Acoustic voxels
TLDR
We present a computational approach that automates the design of acoustic filters with complex geometries. Expand
  • 44
  • PDF
...
1
2
3
...