Search Results for author:
Found 8 papers, 5 papers with code
TI2V-Zero: Zero-Shot Image Conditioning for Text-to-Video Diffusion Models
To guide video generation with the additional image input, we propose a "repeat-and-slide" strategy that modulates the reverse denoising process, allowing the frozen diffusion model to synthesize a video frame-by-frame starting from the provided image.
ANCHOR: LLM-driven News Subject Conditioning for Text-to-Image Synthesis
With Large Language Models (LLM) achieving success in language and commonsense reasoning tasks, we explore the ability of different LLMs to identify and understand key subjects from abstractive captions.
3D-Aware Talking-Head Video Motion Transfer
In this paper, we propose a novel 3D-aware talking-head video motion transfer network, Head3D, which fully exploits the subject appearance information by generating a visually-interpretable 3D canonical head from the 2D subject frames with a recurrent network.
NeRF-Enhanced Outpainting for Faithful Field-of-View Extrapolation
In various applications, such as robotic navigation and remote visual assistance, expanding the field of view (FOV) of the camera proves beneficial for enhancing environmental perception.
Synthetic Augmentation with Large-scale Unconditional Pre-training
To further reduce the dependency on annotated data, we propose a synthetic augmentation method called HistoDiffusion, which can be pre-trained on large-scale unlabeled datasets and later applied to a small-scale labeled dataset for augmented training.
Conditional Image-to-Video Generation with Latent Flow Diffusion Models
In this paper, we propose an approach for cI2V using novel latent flow diffusion models (LFDM) that synthesize an optical flow sequence in the latent space based on the given condition to warp the given image.
ANNA: Abstractive Text-to-Image Synthesis with Filtered News Captions
Advancements in Text-to-Image synthesis over recent years have focused more on improving the quality of generated samples on datasets with descriptive captions.
Cross-identity Video Motion Retargeting with Joint Transformation and Synthesis
The novel design of dual branches combines the strengths of deformation-grid-based transformation and warp-free generation for better identity preservation and robustness to occlusion in the synthesized videos.
