MPhil Thesis Defence


"A Markov Random Field Formulation for Dense Photometric Stereo:
Theory, Practice and Applications"

By

Mr. Kam-Lun Tang


Abstract

In this thesis, we address the problem of normal reconstruction by
photometric stereo using a dense set of photometric images captured at
fixed viewpoint (CVPR 2005). Our method is robust to spurious noises
caused by highlight, shadows and non-Lambertian reflections which are
problematic to traditional approaches. To simultaneously recover normal
orientations and preserve discontinuities, we model the dense photometric
stereo problem into two coupled Markov Random Fields(MRFs): a smooth field
for normal orientations, and a spatial line process for normal orientation
discontinuities. We propose a very fast tensorial belief propagation
method to approximate the maximum a posteriori (MAP) solution of the
Markov network. Our tensor-based message passing scheme not only improves
the normal orientation estimation from one of discrete to continuous, but
also drastically reduces the storage requirement and running time. We
propose a simple image acquisition system that consists of a spherical
mirror, a spotlight and a DV camera to collect photometric samples. Using
this setup, we can infer a dense set of unbiased but noisy photometric
data roughly distributed uniformly on the light direction sphere. We
present very encouraging results on a wide range of difficult objects to
show the efficacy of our approach.

We apply our accurate normal map we produced in an application in computer
graphics. A robust depth map is inferred from the reconstructed normal map
which allows for relighting the scene uniformly regardless distant or
point light sources. Unlike other model based approaches where parameter
estimation is performed, a compact, illumination-adjustable and
hardware-friendly representation is proposed to encode the versatile
reflectance of a complex scene for relighting at very high frame rate. The
dense input is first encoded using the principal component analysis (PCA),
which compactly encodes the captured data into a set of eigenimages with
the corresponding relighting coefficients. Both are then transformed into
a set of texture maps, thus allowing for real-time, per-pixel table-lookup
and multiplication by exploiting the state-of-the-art technology in
graphics processing unit (GPU). Our experiments show that good visual
quality of the relit images and very high frame rate can be achieved
simultaneously.


Date:			Tuesday, 31 May 2005

Time:			2:00p.m.-4:00p.m.

Venue:			Room 2406
                        Lifts 17-18

Committee Members:	Dr. Chi-Keung Tang (Supervisor)
                        Dr. Albert Chung (Chairperson)
                       	Dr. Tien-Tsin Wong (CUHK)


**** ALL are Welcome ****