Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 7 of 7 for “"Pose transfer"”.
-
Controllable human image synthesis and editing
… manipulations (e.g., the same person in pose A and pose B). However, collecting such data would be difficult due to several factors, including copyright restrictions, brand protection concerns, and the inherent difficulty in gathering high-quality, diverse data. Consequently, existing …
-
SIMPLIFYING 3D LEARNING: INTEGRATING PRIOR KNOWLEDGE AND DECOMPOSING COMPLEXITY
… (1) A weakly-supervised, keypoint-based pose transfer framework that disentangles pose and shape using cycle consistency, enabling cross-character transfer without extensive paired data. (2) Diffusion-Guided Generalizable Human Reconstruction employing a coarse-to-fine strategy that …
-
Weakly-supervised geometry-aware novel view synthesis
… This approach enables downstream tasks such as pose transfer, spatially-guided conditional image generation, and paves the way for commonsense reasoning. Our work has potential applications in augmented reality and visual effects, with further exploration of the model's capabilities and …
-
Structured Grounding for Relational Scene Understanding and Reference-Conditioned Generation
… to an entity pair; an image generator may transfer reference appearance to an incorrect region; and a video generator may lose reference identity over time. This thesis studies these failures through structured grounding: the explicit association of semantic or conditioning information with …
-
Controllable Visual Synthesis
… problem of controllable image synthesis. We propose several approaches that allow the user to synthesize realistic content and manipulate images to achieve their desired goals with ease and flexibility.
-
AI assisted visual communication through generative models
… Continuous Normalizing Flows.</p> <p>We first propose MAD-GAN, an intuitive generalization to the Generative Adversarial Networks (GANs) and its conditional variants to address the well known problem of mode collapse. First, MAD-GAN is a multi-agent GAN architecture incorporating multiple …
-
Metaverse in the Wild: Modeling, Adapting, and Rendering of 3D Human Avatars from a Single Camera
… such as identity, shape (slim vs. fat), pose, apparel style, viewpoint, and illumination. While a data-driven model requires to learn from the data that can span such diversity, no such data exists to date. I address this challenge by developing a set of self-supervised algorithms that …