← Search

SeungHwan Choi

7 accepted papers

2026

OPRO: Orthogonal Panel-Relative Operators for Panel-Aware In-Context Image Generation

CVPR 2026

We introduce a parameter-efficient adaptation method for panel-aware in-context image generation with pre-trained diffusion transformers. The key idea is to compose learnable, panel-specific orthogonal operators onto the backbone's frozen positional encodings. This design provides two desirable prop

Cited by 0SourceScholar
2026

Selectively Extracting and Injecting Visual Attributes into Text-to-Image Models

CVPR 2026

Text-to-image models are increasingly utilized in design workflows, but articulating nuanced design intentions solely through text remains a challenge. This work proposes a method that extracts visual attributes from a reference image and injects them directly into the generation pipeline. Specifica

Cited by 0SourceScholar
2025

FLEX: Expert-level False-Less EXecution Metric for Text-to-SQL Benchmark

NAACL 2025long

Text-to-SQL systems have become crucial for translating natural language into SQL queries in various industries, enabling non-technical users to perform complex data operations. The need for accurate evaluation methods has increased as these systems have grown more sophisticated. However, the Execut…

2023

Learning to Generate Semantic Layouts for Higher Text-Image Correspondence in Text-to-Image Synthesis

ICCV 2023poster

Existing text-to-image generation approaches have set high standards for photorealism and text-image correspondence, largely benefiting from web-scale text-image datasets, which can include up to 5 billion pairs. However, text-to-image generation models trained on domain-specific datasets, such as u…

Cited by 12PDFcodeScholar
2023

Shortcut-V2V: Compression Framework for Video-to-Video Translation Based on Temporal Redundancy Reduction

ICCV 2023poster

Video-to-video translation aims to generate video frames of a target domain from an input video. Despite its usefulness, the existing networks require enormous computations, necessitating their model compression for wide use. While there exist compression methods that improve computational efficienc…

Cited by 2PDFcodeScholar
2022

High-Resolution Virtual Try-On with Misalignment and Occlusion-Handled Conditions

ECCV 2022poster

"Image-based virtual try-on aims to synthesize an image of a person wearing a given clothing item. To solve the task, the existing methods warp the clothing item to fit the person’s body and generate the segmentation map of the person wearing the item before fusing the item with the person. However,…

2021

VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalization

CVPR 2021poster

The task of image-based virtual try-on aims to transfer a target clothing item onto the corresponding region of a person, which is commonly tackled by fitting the item to the desired body part and fusing the warped item with the person. While an increasing number of studies have been conducted, the…

Cited by 302PDFcodeScholar