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 20 of 74 for “"video generation"”.
-
Diverse Video Generation
… It requires modeling the temporal coherence of videos and multi-modality in terms of diversity in the potential future states. Current variational approaches for video generation tend to marginalize over multi-modal future outcomes. Instead, in this thesis, we propose to explicitly model the …
-
Layered controllable video generation
… have led to impressive results in image and video synthesis. However, synthesis of realistic images/videos, without the ability to control the depicted content in them, has limited practical utility. We introduce layered controllable video generation, where we, without any supervision, …
-
Towards controllable image and video generation
Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2025-08-01
-
Video Generation and Understanding with Multimodal Learning
Capturing diverse events and interactions, videos are essential for understanding our world. Advances in video generation enable immersive, realistic content for virtual reality and interactive media, and robust video understanding decodes complex scenes for applications in surveillance, …
-
Concept Vectors for Zero-Shot Video Generation
Zero-shot video generation involves generating videos of concepts (action classes) that are not seen in the training phase. Even though the research community has explored conditional video generation for long high-resolution videos, zero-shot video remains a fairly unexplored and challenging task. …
-
Synthetic Ultrasound Video Generation with Generative Adversarial Networks
… in different clinical settings. Ultrasound video analysis can benefit from the rise of AI-powered applications in healthcare. However, access to ultrasound data remains the main challenge for the development of state-of-the-art machine learning models. Synthetic data generation can provide …
-
Long video generation using the VAE-GAN method
Video generation has emerged as a critical area in machine learning, with applications spanning entertainment, virtual reality, and surveillance. However, generating realistic and temporally coherent videos, especially for long-term sequences, remains challenging. This thesis addresses these …
-
Generative adversarial networks for pose-guided human video generation
Generation of realistic high-resolution videos of human subjects is a challenging and important task in computer vision. In this thesis, we focus on human motion transfer -- generation of a video depicting a particular subject, observed in a single image, performing a series of motions exemplified …
-
Cross-Geometry Material Transfer for Physics-Guided Video Generation
Generative video models such as CogVideoX and Wan~2.2 have demonstrated remarkable photorealistic synthesis from a single image and a text prompt, and a parallel line of work has begun to inject physics priors into them. Existing physics-aware video generators, however, are tied to the specific 3D …
-
Advance Video Modeling Techniques for Video Generation and Enhancement Tasks
… advanced techniques that are useful in video modeling for generation and enhancement tasks. In the first part of the thesis, we explore generative modeling that exploits the external corpus for learning priors. The task here is of video prediction, i.e., to extrapolate future sequences …
-
Deep Learning Methods for Medical Image Segmentation and Realistic Video Generation
… both medical image segmentation and realistic video synthesis, offering new capabilities in precision diagnostics and generative modeling. This dissertation investigates the role of generative modeling as a unifying framework across these two domains, presenting methods that enable adaptable, …
-
ConsID-Gen: View-Consistent and Identity-Preserving Image-to-Video Generation
Image-to-Video (I2V) generation often struggles to preserve fine-grained object identities across changing viewpoints, suffering from appearance drift and geometric distortion due to the sparsity of single-view 2D observations and weak cross-modal alignment. First, we introduce ConsID-Vid, a …
-
ConsID-Gen: View-Consistent and Identity-Preserving Image-to-Video Generation
Image-to-Video (I2V) generation often struggles to preserve fine-grained object identities across changing viewpoints, suffering from appearance drift and geometric distortion due to the sparsity of single-view 2D observations and weak cross-modal alignment. First, we introduce ConsID-Vid, a …
-
Video Generation Techniques for Novel View Synthesis with Flow-Matching Transformers
… pose-conditioned view synthesis by incorporating video-generation techniques with camera conditioning. In this thesis, we introduce MVFlow, a new NVS model that extends this approach to a different image generation architecture: a flow-matching diffusion transformer, specifically FLUX.1, which has …
-
RIT-Eyes: Realistic Eye Image and Video Generation for Eye Tracking Applications
Deep neural networks for video-based eye tracking have demonstrated resilience to noisy environments, stray reflections, and low resolution. However, to train these networks, a large number of manually annotated images are required. To alleviate the cumbersome process of manual labeling, computer …
-
Evaluating Multimodal AI Systems: A Comparative Analysis of Large Languagel Model-Based Models for Text, Image, and Video Generation
… technological advancement, efficient content generation, application development, and data management are crucial for meeting the demands of dynamic digital environments. This thesis uses state-of-the-art models to explore three core areas: AI-driven video content creation, …
-
Audio-to-Video Synthesis using Generative Adversarial Network
Video generation is often perceived as stringing several image generators. However, in addition to visual quality, video generators must also consider motion smoothness and synchronicity with audio and text. Audio plays a crucial role in guiding visual content, as even slight discrepancies between …
-
Multimodal understanding and generation : bridging vision and language
… transformed visual understanding and generation. However, traditional vision models are single-modal, failing to generalize to real-world scenarios. In contrast, humans naturally leverage language to both comprehend and create visual content. This dissertation presents several …
-
Toward Adaptive and Efficient Synthesis of Appearance, Dynamics and Semantics
… enabling both the synthesis of novel images and videos and the transformation of existing visual assets. Among recent approaches, diffusion-based methods have played a major role due to their high-fidelity generation quality, robust scalability, and broad generalization across tasks. Despite …
-
TOWARDS EFFICIENT VIDEO PERCEPTION AND GENERATION
Video is a high-dimensional and temporally dynamic modality, yet its practical deployment is constrained by costly annotation, heavy computation, and unreliable evaluation. This thesis addresses these challenges through three complementary contributions to efficient video perception, generation, …
Page 1 of 4