9 papers
Recurrent Sinusoidal INRs for Efficient High-Fidelity Representation
Hyunmin Cho, Jaejun Yoo, Kyong Hwan Jin
We study sinusoidal recurrence as an iterative mechanism for harmonic spectral enrichment in implicit neural representations (INRs). Our analysis reveals that sinusoidal activation…
Balancing Fidelity and Diversity in Diffusion Models via Symmetric Attention Decomposition: Hopfield Perspective
Hyunmin Cho, Woo Kyoung Han, Kyong Hwan Jin
We characterize the pre-softmax attention matrix in transformers as an associative memory matrix encoding pairwise associations between input features. By decomp…
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…
Dual Recursive Feedback on Generation and Appearance Latents for Pose-Robust Text-to-Image Diffusion
Jiwon Kim, Pureum Kim, SeonHwa Kim +3
Recent advancements in controllable text-to-image (T2I) diffusion models, such as Ctrl-X and FreeControl, have demonstrated robust spatial and appearance control without requiring…
IM-LUT: Interpolation Mixing Look-Up Tables for Image Super-Resolution
Sejin Park, Sangmin Lee, Kyong Hwan Jin +1
Super-resolution (SR) has been a pivotal task in image processing, aimed at enhancing image resolution across various applications. Recently, look-up table (LUT)-based approaches h…
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…
BF-STVSR: B-Splines and Fourier-Best Friends for High Fidelity Spatial-Temporal Video Super-Resolution
Eunjin Kim, Hyeonjin Kim, Kyong Hwan Jin +1
While prior methods in Continuous Spatial-Temporal Video Super-Resolution (C-STVSR) employ Implicit Neural Representation (INR) for continuous encoding, they often struggle to capt…
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…
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…