DEPTH ESTIMATION: FROM MONOCULAR TO MULTIPLE VIEWS

The Hong Kong University of Science and Technology
Department of Computer Science and Engineering


MPhil Thesis Defence


Title: "DEPTH ESTIMATION: FROM MONOCULAR TO MULTIPLE VIEWS"

By

Mr. Zhuofei HUANG


Abstract:

Since it is challenging for us to acquire per-pixel ground-truth scene
depths in real world, it is significant for researchers to develop
self-supervised depth estimation frameworks. In recent years,
self-supervised monocular depth estimation has shown impressive results
where networks are trained to predict depth map for a single image frame
by using adjacent frames as supervision signal during training period.
Meanwhile, in many applications, information of video sequences are also
available at test time. Many researchers found that multi-view stereo
(MVS) depth estimation based on cost volume usually works better than
monocular schemes except for moving objects and lowtextured surfaces.
Based on these facts, we hope to combine advantages of monocular and
multiview schemes and design a new integrated depth estimation framework
with better performance.

In this paper, we first introduce several representative self-supervised
depth estimation frameworks in recent years, including monocular and
multi-view cases. Besides, to reduce the influence of observation noises
(e.g., occlusion and moving objects), we introduce the concept of Bayesian
uncertainty and explain how to improve the depth accuracy with uncertainty
estimation. Then we will propose a multi-frame depth estimation framework
where monocular depth map can be refined continuously by multi-frame
sequential constraints, leveraging a Bayesian fusion layer within several
iterations. Both monocular and multi-view networks can be trained with no
depth supervision. Our method also enhances the interpretability when
combining monocular estimation with multiview cost volume.


Date: 			Thursday, 1 June 2023

Time: 			2:30pm - 4:30pm

Venue: 			Room 3494
			lifts 25/26

Committee Members: 	Dr. Ming Liu (Supervisor)
			Prof. Long Quan (Supervisor)
			Prof. Chiew-Lan Tai (Chairperson)
			Dr. Dan Xu


**** ALL are Welcome ****