• Publications
  • Influence
Photographic Image Synthesis with Cascaded Refinement Networks
  • Qifeng Chen, V. Koltun
  • Computer Science
  • IEEE International Conference on Computer Vision…
  • 28 July 2017
TLDR
We present an approach to synthesizing photographic images conditioned on semantic layouts. Expand
  • 528
  • 64
  • PDF
Learning to See in the Dark
TLDR
We propose a new image processing pipeline that addresses the challenges of extreme low-light photography via a data-driven approach, based on end-to-end training of a fully-convolutional network. Expand
  • 298
  • 59
  • PDF
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
  • 297
  • 44
  • PDF
Single Image Reflection Separation with Perceptual Losses
TLDR
We present an approach to separating reflection from a single image. Expand
  • 106
  • 43
  • PDF
Fast Image Processing with Fully-Convolutional Networks
TLDR
We present an approach to accelerating a wide variety of image processing operators. Expand
  • 149
  • 33
  • PDF
A Simple Model for Intrinsic Image Decomposition with Depth Cues
  • Qifeng Chen, V. Koltun
  • Computer Science
  • IEEE International Conference on Computer Vision
  • 1 December 2013
TLDR
We present a model for intrinsic decomposition of RGB-D images. Expand
  • 152
  • 28
  • PDF
Semi-Parametric Image Synthesis
TLDR
We present a semi-parametric approach to photographic image synthesis from semantic layouts. Expand
  • 76
  • 19
  • PDF
Speech Denoising with Deep Feature Losses
TLDR
We present an end-to-end deep learning approach to denoising speech signals by processing the raw waveform directly. Expand
  • 72
  • 19
  • PDF
Interactive Image Segmentation with Latent Diversity
TLDR
We present an end-to-end learning approach to interactive image segmentation that tackles the multimodality problem head-on. Expand
  • 57
  • 17
  • PDF
Full Flow: Optical Flow Estimation By Global Optimization over Regular Grids
  • Qifeng Chen, V. Koltun
  • Computer Science
  • IEEE Conference on Computer Vision and Pattern…
  • 12 April 2016
TLDR
We show that one-shot global optimization of a classical Horn-Schunck-type objective over regular grids at a single resolution is sufficient to initialize continuous interpolation and achieve state-of-the-art performance on challenging modern benchmarks. Expand
  • 121
  • 14
  • PDF