9 citations · 30 across the 11 of their papers we have counts for
11 papers
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…
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…
Spatiotemporal Skip Guidance for Enhanced Video Diffusion Sampling
Junha Hyung, Kinam Kim, Susung Hong +2
Diffusion models have emerged as a powerful tool for generating high-quality images, videos, and 3D content. While sampling guidance techniques like CFG improve quality, they reduc…
Smoothed Energy Guidance: Guiding Diffusion Models with Reduced Energy Curvature of Attention
Susung Hong
Conditional diffusion models have shown remarkable success in visual content generation, producing high-quality samples across various domains, largely due to classifier-free guida…
Effective Rank Analysis and Regularization for Enhanced 3D Gaussian Splatting
Junha Hyung, Susung Hong, Sungwon Hwang +3
3D reconstruction from multi-view images is one of the fundamental challenges in computer vision and graphics. Recently, 3D Gaussian Splatting (3DGS) has emerged as a promising tec…
Retrieval-Augmented Score Distillation for Text-to-3D Generation
Junyoung Seo, Susung Hong, Wooseok Jang +4
Text-to-3D generation has achieved significant success by incorporating powerful 2D diffusion models, but insufficient 3D prior knowledge also leads to the inconsistency of 3D geom…
DirecT2V: Large Language Models are Frame-Level Directors for Zero-Shot Text-to-Video Generation
Susung Hong, Junyoung Seo, Heeseong Shin +2
In the paradigm of AI-generated content (AIGC), there has been increasing attention to transferring knowledge from pre-trained text-to-image (T2I) models to text-to-video (T2V) gen…
Debiasing Scores and Prompts of 2D Diffusion for View-consistent Text-to-3D Generation
Susung Hong, Donghoon Ahn, Seungryong Kim
Existing score-distilling text-to-3D generation techniques, despite their considerable promise, often encounter the view inconsistency problem. One of the most notable issues is th…
DAG: Depth-Aware Guidance with Denoising Diffusion Probabilistic Models
Gyeongnyeon Kim, Wooseok Jang, Gyuseong Lee +3
Generative models have recently undergone significant advancement due to the diffusion models. The success of these models can be often attributed to their use of guidance techniqu…
Neural Matching Fields: Implicit Representation of Matching Fields for Visual Correspondence
Sunghwan Hong, Jisu Nam, Seokju Cho +4
Existing pipelines of semantic correspondence commonly include extracting high-level semantic features for the invariance against intra-class variations and background clutters. Th…
Improving Sample Quality of Diffusion Models Using Self-Attention Guidance
Susung Hong, Gyuseong Lee, Wooseok Jang +1
Denoising diffusion models (DDMs) have attracted attention for their exceptional generation quality and diversity. This success is largely attributed to the use of class- or text-c…