Ting Liu

Consistent Feature Transport for Image Relighting

Bohan Zhang, Huanwei Liang, Yuhan He +5

Image relighting modifies illumination while preserving non-lighting content such as identity and geometry. Existing diffusion-based methods often suffer from unstable illumination…

StructGen: Disambiguating Multi-Reference Image Generation via Structured Context Modeling

Jianing Peng, Mengyu Wang, Henghui Ding +6

Multi-reference image generation aims to synthesize images by integrating attributes from multiple reference images under textual instructions. As the number of references increase…

TextFake: Benchmarking AI-Generated Image Detection on Text-Rich Images

Yuning Zhang, Changtao Miao, Mingyu Liao +5

Recent AI-generated image (AIGI) detectors perform well on natural-image benchmarks, but their behavior on text-rich forgeries, such as fabricated screenshots, documents, and news…

Self-Prompting Diffusion Transformer for Open-Vocabulary Scene Text Editing via In-Context Learning

Hongxi Li, Tong Wang, Chengjing Wu +6

Scene text editing aims to modify text in a target region of an image while preserving surrounding background style and texture. Existing methods rely solely on image background in…

PortraitCraft: A Benchmark for Portrait Composition Understanding and Generation

Yuyang Sha, Zijie Lou, Youyun Tang +6

Portrait composition plays a central role in portrait aesthetics and visual communication, yet existing datasets and benchmarks mainly focus on coarse aesthetic scoring, generic im…

MTADiffusion: Mask Text Alignment Diffusion Model for Object Inpainting

Jun Huang, Ting Liu, Yihang Wu +3

Advancements in generative models have enabled image inpainting models to generate content within specific regions of an image based on provided prompts and masks. However, existin…

AlignGen: Boosting Personalized Image Generation with Cross-Modality Prior Alignment

Yiheng Lin, Shifang Zhao, Ting Liu +4

Personalized image generation aims to integrate user-provided concepts into text-to-image models, enabling the generation of customized content based on a given prompt. Recent zero…

GlyphMastero: A Glyph Encoder for High-Fidelity Scene Text Editing

Tong Wang, Ting Liu, Xiaochao Qu +3

Scene text editing, a subfield of image editing, requires modifying texts in images while preserving style consistency and visual coherence with the surrounding environment. While…

DCEdit: Dual-Level Controlled Image Editing via Precisely Localized Semantics

Yihan Hu, Jianing Peng, Yiheng Lin +5

This paper presents a novel approach to improving text-guided image editing using diffusion-based models. Text-guided image editing task poses key challenge of precisly locate and…

Memory Efficient Matting with Adaptive Token Routing

Yiheng Lin, Yihan Hu, Chenyi Zhang +5

Transformer-based models have recently achieved outstanding performance in image matting. However, their application to high-resolution images remains challenging due to the quadra…

Draw Like an Artist: Complex Scene Generation with Diffusion Model via Composition, Painting, and Retouching

Minghao Liu, Le Zhang, Yingjie Tian +3

Recent advances in text-to-image diffusion models have demonstrated impressive capabilities in image quality. However, complex scene generation remains relatively unexplored, and e…

Rethinking Video Segmentation with Masked Video Consistency: Did the Model Learn as Intended?

Chen Liang, Qiang Guo, Xiaochao Qu +2

Video segmentation aims at partitioning video sequences into meaningful segments based on objects or regions of interest within frames. Current video segmentation models are often…

TextMastero: Mastering High-Quality Scene Text Editing in Diverse Languages and Styles

Tong Wang, Xiaochao Qu, Ting Liu

Scene text editing aims to modify texts on images while maintaining the style of newly generated text similar to the original. Given an image, a target area, and target text, the t…