Fwd: RI Ph.D. Thesis Proposal: Chao Liu

[Artur Dubrawski]

Team,

Please come see Chao give his thesis proposal presentation this Friday at
2pm.

Cheers
Artur

---------- Forwarded message ---------
From: Suzanne Muth <lyonsmuth at cmu.edu>
Date: Wed, Nov 21, 2018 at 10:07 AM
Subject: RI Ph.D. Thesis Proposal: Chao Liu
To: ri-people at cs.cmu.edu <ri-people at cs.cmu.edu>


Date: 30 November 2018

Time: 2:00 p.m.

Place: NSH 4305

Type: Ph.D. Thesis Proposal

Who: Chao Liu

Topic: Vision with Small Baselines


Abstract:

Portable camera sensor systems are becoming more and more popular in
computer vision applications such as autonomous driving, virtual reality,
robotics manipulation and surveillance, due to the decreasing expense and
size of RGB camera. Despite the compactness and portability of the small
baseline vision systems, it is well-known that the uncertainty in range
finding using multiple views and the sensor baselines are inversely
related. For small baseline vision systems, this means high depth
uncertainties even for close range objects. On the other hand, besides
compactness,
small baseline vision system has its unique advantages such as easier
correspondence
and large overlapping regions across views. How to utilize those advantages
for small baseline vision setup while avoiding the limitations as much as
possible? In this thesis proposal, we approach this question in terms of
three aspects: scene complexity, uncertainties in the estimations and
baseline distance in the setup.



We first present a method for matting and depth recovery of 3D thin
structures with self-occlusions using a single-view camera with finite
aperture lens. In this work, we take advantage of the small camera
baselines that makes the correspondence easier. We apply the proposed
method to scenes at both macro and microscales. For macro-scale, we
evaluate our method on scenes with complex 3D thin structures such as tree
branches and grass. For micro-scale, we apply our method to *in-vivo*
microscopic images of micro-vessels with diameters less than 50 *um*.



We also utilize the small baselines for circularly placed point light
sources (commonly seen in consumer devices like NESTcam, Amazon Cloudcam).
We propose a two-stage near-light photometric stereo method. In the first
stage, we optimizethe vertex positions using the differential images
induced by small changes in lightsource position. This procedure yields a
strong initial guess for the second stage that refines the estimations
using the raw captured images.



To handle the estimation uncertainties inherent in the small baseline
setup, we propose a learning-based method to estimate per-pixel depth and
its uncertainty continuously from a monocular video stream. Compared to
prior work, the proposed approach achieves more accurate and stable
results, generalizes better to new datasets, and yields per-pixel depth
probability map that accounts for the estimation uncertainties due to
specular surface, occlusions in the scene and objects with large distance.



To deal with the subsurface light scattering in the tissue, we propose a
projector-camera setup with small baseline that works in a small scale and
a method that combines the approximated model for subsurface light
scattering, in order to see through skins and perform *in-vivo* blood flow
analysis on human skin.



We also propose to combine the benefits of small and large baseline vision
systems, in order to handle large region occlusion and depth estimation for
fine-grained structures at the same time.


Thesis Committee Members:

Srinivasa Narasimhan, Co-chair

Artur Dubrawski, Co-chair

Aswin Sankaranarayanan

Manmohan Chandraker, University of California, San Diego


A copy of thesis document is available at:

https://www.dropbox.com/s/wwxe7mqy7mf947q/small-baseline.pdf?dl=0
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20181126/c07a3f09/attachment-0001.html>