• Publications
  • Influence
Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks
TLDR
We present the Inside-Outside Net (ION), an object detector that exploits information both inside and outside the region of interest. Expand
  • 689
  • 81
  • PDF
Deep Photo Style Transfer
TLDR
We introduce a deep-learning approach to photographic style transfer that is at the same time broad and faithful, i.e., it handles a large variety of image content while accurately transferring the reference style. Expand
  • 305
  • 48
  • PDF
Intrinsic images in the wild
TLDR
We introduce Intrinsic Images in the Wild, a large-scale, public dataset for evaluating intrinsic image decompositions of indoor scenes. Expand
  • 261
  • 47
  • PDF
Material recognition in the wild with the Materials in Context Database
TLDR
We introduce a new, large-scale, open dataset of materials in the wild, the Materials in Context Database (MINC), and combine this dataset with deep learning to achieve material recognition and segmentation of images in the Wild. Expand
  • 297
  • 44
  • PDF
Learning Visual Clothing Style with Heterogeneous Dyadic Co-Occurrences
TLDR
We use Siamese CNNs to learn a feature transformation from images of items into a latent space that expresses compatibility across categories. Expand
  • 183
  • 41
  • PDF
Lightcuts: a scalable approach to illumination
Lightcuts is a scalable framework for computing realistic illumination. It handles arbitrary geometry, non-diffuse materials, and illumination from a wide variety of sources including point lights,Expand
  • 225
  • 26
Learning visual similarity for product design with convolutional neural networks
TLDR
We use crowdsourcing to collect matching information between in-situ images and iconic product images to generate the data needed to train deep networks. Expand
  • 278
  • 24
  • PDF
Advanced global illumination
TLDR
This book provides a fundamental understanding of global illumination algorithms. Expand
  • 373
  • 23
  • PDF
OpenSurfaces: a richly annotated catalog of surface appearance
TLDR
We present OpenSurfaces, a rich, labeled database consisting of thousands of examples of surfaces segmented from consumer photographs of interiors, and annotated with material parameters (reflectance, material names), texture information (surface normals, rectified textures), and contextual information (scene category, and object names). Expand
  • 163
  • 12
  • PDF
Optimistic parallelism requires abstractions
The problem of writing software for multicore processors is greatly simplified if we could automatically parallelize sequential programs. Although auto-parallelization has been studied for manyExpand
  • 201
  • 12