-
Chapter and Conference Paper
PointFix: Learning to Fix Domain Bias for Robust Online Stereo Adaptation
Online stereo adaptation tackles the domain shift problem, caused by different environments between synthetic (training) and real (test) datasets, to promptly adapt stereo models in dynamic real-world applicat...
-
Chapter and Conference Paper
Guided Semantic Flow
Establishing dense semantic correspondences requires dealing with large geometric variations caused by the unconstrained setting of images. To address such severe matching ambiguities, we introduce a novel app...
-
Chapter and Conference Paper
PARN: Pyramidal Affine Regression Networks for Dense Semantic Correspondence
This paper presents a deep architecture for dense semantic correspondence, called pyramidal affine regression networks (PARN), that estimates locally-varying affine transformation fields across images. To deal...
-
Article
EMCCD color correction based on spectral sensitivity analysis
The sensor response function of a color camera is very essential to understand an overall camera imaging pipeline and to process captured images. It is also true when we characterize underlying imaging behavio...
-
Chapter and Conference Paper
Fast Guided Global Interpolation for Depth and Motion
We study the problems of upsampling a low-resolution depth map and interpolating an initial set of sparse motion matches, with the guidance from a corresponding high-resolution color image. The common objectiv...
-
Chapter and Conference Paper
Deep Self-correlation Descriptor for Dense Cross-Modal Correspondence
We present a novel descriptor, called deep self-correlation (DSC), designed for establishing dense correspondences between images taken under different imaging modalities, such as different spectral ranges or ...
-
Chapter and Conference Paper
Fast Dense Stereo Matching Using Adaptive Window in Hierarchical Framework
A new area-based stereo matching in hierarchical framework is proposed. Local methods generally measure the similarity between the image pixels using local support window. An appropriate support window, where ...
-
Chapter and Conference Paper
Segment-Based Stereo Matching Using Energy-Based Regularization
We propose a new stereo matching algorithm through energy-based regularization using color segmentation and visibility constraint. Plane parameters in the entire segments are modeled by robust least square alg...
