arXiv subjects

Junsung Lee

Publications and source records attributed to Junsung Lee.

4 recordsLinked to original sources

arXiv2025

Low-Resolution Editing is All You Need for High-Resolution Editing

High-resolution content creation is rapidly emerging as a central challenge in both the vision and graphics communities. Images serve as the most fundamental modality for visual expression, and content generation that aligns with the user intent requires effective, controllable high-resolution image manipulation mechanisms. However, existing approaches remain limited to low-resolution settings, typically supporting only up to 1K resolution. In this work, we introduce the task of high-resolution image editing and propose a test-time optimization framework to address it. Our method performs patch-wise optimization on high-resolution source images, followed by a fine-grained detail transfer module and a novel synchronization strategy to maintain consistency across patches. Extensive experiments show that our method produces high-quality edits, facilitating high-resolution content creation.

cs.CV↗

arXiv2025

STR-Match: Matching SpatioTemporal Relevance Score for Training-Free Video Editing

Previous text-guided video editing methods often suffer from temporal inconsistency, motion distortion, and-most notably-limited domain transformation. We attribute these limitations to insufficient modeling of spatiotemporal pixel relevance during the editing process. To address this, we propose STR-Match, a training-free video editing algorithm that produces visually appealing and spatiotemporally coherent videos through latent optimization guided by our novel STR score. The score captures spatiotemporal pixel relevance across adjacent frames by leveraging 2D spatial attention and 1D temporal modules in text-to-video (T2V) diffusion models, without the overhead of computationally expensive 3D attention mechanisms. Integrated into a latent optimization framework with a latent mask, STR-Match generates temporally consistent and visually faithful videos, maintaining strong performance even under significant domain transformations while preserving key visual attributes of the source. Extensive experiments demonstrate that STR-Match consistently outperforms existing methods in both visual quality and spatiotemporal consistency.

cs.CV↗

arXiv2024

Diffusion-Based Image-to-Image Translation by Noise Correction via Prompt Interpolation

We propose a simple but effective training-free approach tailored to diffusion-based image-to-image translation. Our approach revises the original noise prediction network of a pretrained diffusion model by introducing a noise correction term. We formulate the noise correction term as the difference between two noise predictions; one is computed from the denoising network with a progressive interpolation of the source and target prompt embeddings, while the other is the noise prediction with the source prompt embedding. The final noise prediction network is given by a linear combination of the standard denoising term and the noise correction term, where the former is designed to reconstruct must-be-preserved regions while the latter aims to effectively edit regions of interest relevant to the target prompt. Our approach can be easily incorporated into existing image-to-image translation methods based on diffusion models. Extensive experiments verify that the proposed technique achieves outstanding performance with low latency and consistently improves existing frameworks when combined with them.

cs.CV↗

arXiv2015

One-wave optical phase conjugation mirror by actively coupling arbitrary light fields into a single-mode reflector

Rewinding the arrow of time via phase conjugation is an intriguing phenomena made possible by the wave property of light. To exploit this phenomenon, diverse research fields have pursed the realization of an ideal phase conjugation mirror, but an optical system that requires a single-input and a single-output beam, like natural conventional mirrors has never been demonstrated. Here, we demonstrate the realization of a one-wave optical phase conjugation mirror using a spatial light modulator. An adaptable single-mode filter is created, and a phase-conjugate beam is then prepared by reverse propagation through this filter. Our method is simple, alignment free, and fast while allowing high power throughput in the time reversed wave, which have not been simultaneously demonstrated before. Using our method, we demonstrate high throughput full-field light delivery through highly scattering biological tissue and multimode fibers, even for quantum dot fluorescence.

physics.optics↗