activity
20242026
collaborators

6 papers

cs.CV2026

TAG: Tangential Amplifying Guidance for Hallucination-Resistant Sampling

Hyunmin Cho, Donghoon Ahn, Susung Hong +3

Diffusion models achieve state-of-the-art image generation but often produce semantic inconsistencies, or hallucinations. Existing inference-time guidance methods rely on external…

cs.CV2025

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…

cs.CV2025

Self-Rectifying Diffusion Sampling with Perturbed-Attention Guidance

Donghoon Ahn, Hyoungwon Cho, Jaewon Min +6

Recent studies have demonstrated that diffusion models are capable of generating high-quality samples, but their quality heavily depends on sampling guidance techniques, such as cl…

cs.CV2025

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…

cs.CV2025

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…

cs.CV2024

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…