• Publications
  • Influence
DualGAN: Unsupervised Dual Learning for Image-to-Image Translation
TLDR
We develop a novel dual-GAN mechanism for general-purpose image-to-image translation, which enables image translators to be trained from two sets of unlabeled images from two domains. Expand
  • 1,062
  • 131
  • PDF
Bundled camera paths for video stabilization
TLDR
We present a novel video stabilization method which models camera motion with a bundle of (multiple) camera paths. Expand
  • 223
  • 47
  • PDF
A Benchmark Dataset and Evaluation for Non-Lambertian and Uncalibrated Photometric Stereo
TLDR
We first survey and categorize existing methods using a photometric stereo taxonomy emphasizing on non-Lambertian and uncalibrated methods, followed by a brief categorization for other extensions beyond the classic data capture setup. Expand
  • 109
  • 25
  • PDF
PanoContext: A Whole-Room 3D Context Model for Panoramic Scene Understanding
TLDR
The field-of-view of standard cameras is very small, which is one of the main reasons that contextual information is not as useful as it should be for object detection. Expand
  • 141
  • 22
  • PDF
CoSLAM: Collaborative Visual SLAM in Dynamic Environments
  • Danping Zou, P. Tan
  • Computer Science, Medicine
  • IEEE Transactions on Pattern Analysis and Machine…
  • 1 February 2013
TLDR
This paper studies the problem of vision-based simultaneous localization and mapping (SLAM) in dynamic environments with multiple cameras. Expand
  • 205
  • 18
  • PDF
A Closed-Form Solution to Retinex with Nonlocal Texture Constraints
TLDR
We propose a method for intrinsic image decomposition based on retinex theory and texture analysis. Expand
  • 151
  • 18
A Global Linear Method for Camera Pose Registration
TLDR
We present a linear method for global camera pose registration from pair wise relative poses encoded in essential matrices. Expand
  • 116
  • 17
  • PDF
SteadyFlow: Spatially Smooth Optical Flow for Video Stabilization
TLDR
We propose a novel motion model, SteadyFlow, to represent the motion between neighboring video frames for stabilization. Expand
  • 139
  • 16
  • PDF
Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching
TLDR
We propose a both memory and time efficient cost volume formulation that is complementary to existing multi-view stereo and stereo matching approaches based on 3D cost volumes. Expand
  • 57
  • 15
  • PDF
Sketch2Photo: internet image montage
TLDR
We present a system that composes a realistic picture from a simple freehand sketch annotated with text labels by seamlessly stitching several photographs in agreement with the sketch and text labels; these are found by searching the Internet. Expand
  • 336
  • 13
...
1
2
3
4
5
...