Three-dimensional reconstruction and editing from single images with generative models

Date

2025-05

Editor(s)

Advisor

Boral, Ayşegül Dündar

Supervisor

Co-Advisor

Co-Supervisor

Instructor

BUIR Usage Stats
12
views
11
downloads

Series

Abstract

Advancements in generative networks have significantly improved visual synthesis, particularly in three-dimensional (3D) applications. However, key challenges remain in achieving high-fidelity 3D reconstruction, preserving identity in 3D stylization, and enabling reference-based edits with 3D consistency. This thesis attempts to address these gaps through three interconnected studies. First, a framework of high-fidelity 3D head reconstruction from single images is introduced, leveraging dual encoder GAN inversion to reconstruct full 360-degree heads. By integrating an occlusion-aware triplane discriminator, this approach ensures seamless blending of visible and occluded regions, surpassing existing methods in realism and structural accuracy. Next, an identity-preserving 3D head stylization method is developed to balance artistic transformation with facial identity retention. Through multi-view score distillation and likelihood distillation, this technique enhances stylization diversity while maintaining subjectspecific features, outperforming prior diffusion-to-GAN adaptation strategies. Finally, a single image reference-based 3D-aware image editing method extends these advancements by enabling precise, high-quality edits using triplane representations. By incorporating automatic feature localization, spatial disentanglement, and fusion learning, this work achieves state-of-the-art performance in 3D-consistent, 2D reference-guided edits across various domains. Together, these contributions attempt to advance the field of 3D-aware generative modeling, providing robust solutions for reconstruction, stylization, and editing with greater fidelity, consistency, and control.

Source Title

Publisher

Course

Other identifiers

Book Title

Degree Discipline

Computer Engineering

Degree Level

Master's

Degree Name

MS (Master of Science)

Citation

Published Version (Please cite this version)

Language

English

Type