14 papers
InstructVVT: Instruction-Driven Video Virtual Try-On without Auxiliary Spatial Priors
Dingbao Shao, Song Wu, Xinyu Chen +18
Video virtual try-on is a highly constrained editing task requiring the precise replacement of a target person's clothing while strictly preserving the original video's spatial str…
SynVAR: Synergizing Spatial and Semantic Alignment in Visual Autoregressive Model
Zhennan Chen, Tianxing Shi, Pengcheng Xu +5
VAR has gained widespread popularity due to its next-scale prediction paradigm. However, it faces substantial performance bottlenecks when handling complex scenes with multiple obj…
Spiking Pyramid Wavelet Transformation for High-efficient and Low-energy Image Restoration
Chen Zhao, Xiantao Hu, Song Wu +5
Spiking neural networks (SNNs) have garnered significant interest in computer vision due to their potential for efficiency and biological inspiration. While spiking CNN-based metho…
VINS-120K: Ultra High-Resolution Image Editing with A Large-Scale Dataset
Zhizhou Chen, Shanyan Guan, Zhanxin Gao +6
Directly editing ultra-high-resolution (UHR) images is valuable but underexplored, primarily due to the lack of high-quality data and the challenge in modeling high-frequency textu…
TripVVT: A Large-Scale Triplet Dataset and a Coarse-Mask Baseline for In-the-Wild Video Virtual Try-On
Dingbao Shao, Song Wu, Shenyi Wang +9
Due to the scarcity of large-scale in-the-wild triplet data and the improper use of masks, the performance of video virtual try-on models remains limited. In this paper, we first i…
From Zero to Detail: A Progressive Spectral Decoupling Paradigm for UHD Image Restoration with New Benchmark
Chen Zhao, Yunzhe Xu, Zhizhou Chen +5
Ultra-high-definition (UHD) image restoration poses unique challenges due to the high spatial resolution, diverse content, and fine-grained structures present in UHD images. To add…
DiP: Taming Diffusion Models in Pixel Space
Zhennan Chen, Junwei Zhu, Xu Chen +6
Diffusion models face a fundamental trade-off between generation quality and computational efficiency. Latent Diffusion Models (LDMs) offer an efficient solution but suffer from po…
UltraHR-100K: Enhancing UHR Image Synthesis with A Large-Scale High-Quality Dataset
Chen Zhao, En Ci, Yunzhe Xu +5
Ultra-high-resolution (UHR) text-to-image (T2I) generation has seen notable progress. However, two key challenges remain : 1) the absence of a large-scale high-quality UHR T2I data…
Describe, Don't Dictate: Semantic Image Editing with Natural Language Intent
En Ci, Shanyan Guan, Yanhao Ge +5
Despite the progress in text-to-image generation, semantic image editing remains a challenge. Inversion-based algorithms unavoidably introduce reconstruction errors, while instruct…
CoDi: Subject-Consistent and Pose-Diverse Text-to-Image Generation
Zhanxin Gao, Beier Zhu, Liang Yao +2
Subject-consistent generation (SCG)-aiming to maintain a consistent subject identity across diverse scenes-remains a challenge for text-to-image (T2I) models. Existing training-fre…
From Zero to Detail: Deconstructing Ultra-High-Definition Image Restoration from Progressive Spectral Perspective
Chen Zhao, Zhizhou Chen, Yunzhe Xu +6
Ultra-high-definition (UHD) image restoration faces significant challenges due to its high resolution, complex content, and intricate details. To cope with these challenges, we ana…
Investigating Text Insulation and Attention Mechanisms for Complex Visual Text Generation
Ying Tai, Nikai Du, Rui Xie +5
In this paper, we present TextCrafter, a Complex Visual Text Generation (CVTG) framework inspired by selective visual attention in cognitive science, and introduce the "Text Insula…
Region-Aware Text-to-Image Generation via Hard Binding and Soft Refinement
Zhennan Chen, Yajie Li, Haofan Wang +6
Regional prompting, or compositional generation, which enables fine-grained spatial control, has gained increasing attention for its practicality in real-world applications. Howeve…
HybridBooth: Hybrid Prompt Inversion for Efficient Subject-Driven Generation
Shanyan Guan, Yanhao Ge, Ying Tai +3
Recent advancements in text-to-image diffusion models have shown remarkable creative capabilities with textual prompts, but generating personalized instances based on specific subj…