4 papers
Vid-CamEdit: Video Camera Trajectory Editing with Generative Rendering from Estimated Geometry
Junyoung Seo, Jisang Han, Jaewoo Jung +9
We introduce Vid-CamEdit, a novel framework for video camera trajectory editing, enabling the re-synthesis of monocular videos along user-defined camera paths. This task is challen…
Where and How to Perturb: On the Design of Perturbation Guidance in Diffusion and Flow Models
Donghoon Ahn, Jiwon Kang, Sanghyun Lee +7
Recent guidance methods in diffusion models steer reverse sampling by perturbing the model to construct an implicit weak model and guide generation away from it. Among these approa…
Identity-preserving Distillation Sampling by Fixed-Point Iterator
SeonHwa Kim, Jiwon Kim, Soobin Park +5
Score distillation sampling (SDS) demonstrates a powerful capability for text-conditioned 2D image and 3D object generation by distilling the knowledge from learned score functions…
A Noise is Worth Diffusion Guidance
Donghoon Ahn, Jiwon Kang, Sanghyun Lee +9
Diffusion models excel in generating high-quality images. However, current diffusion models struggle to produce reliable images without guidance methods, such as classifier-free gu…