Back to search

Democritus University of Thrace (DUTH)

Learning depth from two-dimensional images

Abstract

dc:description

Monocular Depth Estimation (MDE) aims to infer a dense depth map from a single image. Because a three-dimensional scene is reduced to a two-dimensional projection, the inverse mapping is fundamentally ill-posed, since multiple geometries can be consistent with the same image evidence. As a result, high benchmark performance may coexist with solutions that are difficult to audit with respect to the depth cues on which the model relies, the internal organization of its computations, and the regions where failures concentrate. This dissertation approaches MDE through three complementary pillars: interpretability, performance, and explainability. Under the first pillar, it introduces the SVDA attention mechanism, inspired by singular value decomposition, which factorizes attention into directional alignment and spectral emphasis, enabling the study of its structure through quantitative indicators. Under the second pillar, it investigates a segmentation-based approach in which compact class-conditioned depth predictors are combined to improve depth discontinuities at semantic boundaries. Under the third pillar, it proposes a cue-based explainability framework and the Visual Depth Cue (VDC) dataset for the controlled evaluation of model behavior with respect to human visual depth cues. The results show that SVDA preserves competitive predictive performance while revealing structured and analyzable attention behavior, that semantically aware decomposition improves prediction quality at object boundaries, and that controlled experiments on VDC reveal a gap between benchmark performance and cue-consistent behavior. The study focuses on static monocular images and Transformer-based architectures, leaving the investigation of temporal sequences, stereo constraints, and robustness under imperfect segmentation as directions for future work.

Degree

thesis:*
Grantor dc:publisher
Democritus University of Thrace (DUTH)
Year dc:date
2026

Author and committee

dc:creator, dc:contributor.*
Authors dc:creator
  • Arampatzakis, Vasileios
  • Αραμπατζάκης, Βασίλειος

Subjects

dc:subject × 16

Rights

Language dc:language
eng

Identifiers

dc:identifier.*
Identifier
10.12681/eadd/61501

Chain of custody

source
Harvested from
Greek National Archive of PhD Theses
Base URL
phdtheses.ekt.gr/eadd_oai/request
Last updated
2026-11-18
Source record
OAI-PMH GetRecord
citation

Arampatzakis, Vasileios; Αραμπατζάκης, Βασίλειος. Learning depth from two-dimensional images. Democritus University of Thrace (DUTH), 2026. http://hdl.handle.net/10442/hedi/61501