中文
相关论文

相关论文: Optimizing ID Consistency in Multimodal Large Mode…

200 篇论文

Text-driven multi-object image editing which aims to precisely modify multiple objects within an image based on text descriptions, has recently attracted considerable interest. Existing works primarily follow the localize-editing paradigm,…

计算机视觉与模式识别 · 计算机科学 2025-11-12 Fengyi Fu , Mengqi Huang , Lei Zhang , Zhendong Mao

We study the problem of learning disentangled representations for data across multiple domains and its applications in human retargeting. Our goal is to map an input image to an identity-invariant latent representation that captures…

计算机视觉与模式识别 · 计算机科学 2019-12-16 Chao Yang , Xiaofeng Liu , Qingming Tang , C. -C. Jay Kuo

In this paper, we propose a new deep learning-based approach for disentangling face identity representations from expressive 3D faces. Given a 3D face, our approach not only extracts a disentangled identity representation but also generates…

计算机视觉与模式识别 · 计算机科学 2021-04-22 Anis Kacem , Kseniya Cherenkova , Djamila Aouada

Face attribute editing plays a pivotal role in various applications. However, existing methods encounter challenges in achieving high-quality results while preserving identity, editing faithfulness, and temporal consistency. These…

计算机视觉与模式识别 · 计算机科学 2024-04-15 Guangzhi Wang , Tianyi Chen , Kamran Ghasedi , HsiangTao Wu , Tianyu Ding , Chris Nuesmeyer , Ilya Zharkov , Mohan Kankanhalli , Luming Liang

Recently, personalized portrait generation with a text-to-image diffusion model has significantly advanced with Textual Inversion, emerging as a promising approach for creating high-fidelity personalized images. Despite its potential,…

计算机视觉与模式识别 · 计算机科学 2025-07-17 Hyun-Jun Jin , Young-Eun Kim , Seong-Whan Lee

Recently, the success of text-to-image synthesis has greatly advanced the development of identity customization techniques, whose main goal is to produce realistic identity-specific photographs based on text prompts and reference face…

计算机视觉与模式识别 · 计算机科学 2024-12-24 Zhaoyang Sun , Fei Du , Weihua Chen , Fan Wang , Yaxiong Chen , Yi Rong , Shengwu Xiong

Diffusion models have recently shown strong progress in generative tasks, offering a more stable alternative to GAN-based approaches for makeup transfer. Existing methods often suffer from limited datasets, poor disentanglement between…

计算机视觉与模式识别 · 计算机科学 2026-02-03 Qihe Pan , Yiming Wu , Xing Zhao , Liang Xie , Guodao Sun , Ronghua Liang

Deep learning vision models excel with abundant supervision, but many applications face label scarcity and class imbalance. Controllable image editing can augment scarce labeled data, yet edits often introduce artifacts and entangle…

计算机视觉与模式识别 · 计算机科学 2026-02-24 Joris Kirchner , Amogh Gudi , Marian Bittner , Chirag Raman

Balancing fidelity and editability is essential in text-based image editing (TIE), where failures commonly lead to over- or under-editing issues. Existing methods typically rely on attention injections for structure preservation and…

计算机视觉与模式识别 · 计算机科学 2025-04-09 Qi Mao , Lan Chen , Yuchao Gu , Mike Zheng Shou , Ming-Hsuan Yang

Person re-identification (Re-ID) is a crucial task in computer vision, aiming to recognize individuals across non-overlapping camera views. While recent advanced vision-language models (VLMs) excel in logical reasoning and multi-task…

计算机视觉与模式识别 · 计算机科学 2025-06-03 Ke Niu , Haiyang Yu , Mengyang Zhao , Teng Fu , Siyang Yi , Wei Lu , Bin Li , Xuelin Qian , Xiangyang Xue

Facial makeup editing aims to realistically transfer makeup from a reference to a target face. Existing methods often produce low-quality results with coarse makeup details and struggle to preserve both identity and makeup fidelity, mainly…

计算机视觉与模式识别 · 计算机科学 2025-08-11 Huadong Wu , Yi Fu , Yunhao Li , Yuan Gao , Kang Du

Privacy protection has become a top priority as the proliferation of AI techniques has led to widespread collection and misuse of personal data. Anonymization and visual identity information hiding are two important facial privacy…

计算机视觉与模式识别 · 计算机科学 2023-09-12 Xiao He , Mingrui Zhu , Dongxin Chen , Nannan Wang , Xinbo Gao

In unconstrained scenarios, face recognition and person re-identification are subject to distortions such as motion blur, atmospheric turbulence, or upsampling artifacts. To improve robustness in these scenarios, we propose a methodology…

计算机视觉与模式识别 · 计算机科学 2023-02-14 Wes Robbins , Gabriel Bertocco , Terrance E. Boult

Existing diffusion models show great potential for identity-preserving generation. However, personalized portrait generation remains challenging due to the diversity in user profiles, including variations in appearance and lighting…

计算机视觉与模式识别 · 计算机科学 2025-02-03 Han Yang , Enis Simsar , Sotiris Anagnostidis , Yanlong Zang , Thomas Hofmann , Ziwei Liu

Recent facial image synthesis methods have been mainly based on conditional generative models. Sketch-based conditions can effectively describe the geometry of faces, including the contours of facial components, hair structures, as well as…

图形学 · 计算机科学 2021-07-20 Shu-Yu Chen , Feng-Lin Liu , Yu-Kun Lai , Paul L. Rosin , Chunpeng Li , Hongbo Fu , Lin Gao

Current diffusion models for human image animation often struggle to maintain identity (ID) consistency, especially when the reference image and driving video differ significantly in body size or position. We introduce StableAnimator++, the…

计算机视觉与模式识别 · 计算机科学 2025-07-22 Shuyuan Tu , Zhen Xing , Xintong Han , Zhi-Qi Cheng , Qi Dai , Chong Luo , Zuxuan Wu , Yu-Gang Jiang

Restoring real-world degraded images, such as old photographs or low-resolution images, presents a significant challenge due to the complex, mixed degradations they exhibit, such as scratches, color fading, and noise. Recent data-driven…

计算机视觉与模式识别 · 计算机科学 2025-05-28 Peng Xiao , Hongbo Zhao , Yijun Wang , Jianxin Lin

Face restoration has achieved remarkable advancements through the years of development. However, ensuring that restored facial images exhibit high fidelity, preserve authentic features, and avoid introducing artifacts or biases remains a…

计算机视觉与模式识别 · 计算机科学 2025-05-27 Jingkai Wang , Wu Miao , Jue Gong , Zheng Chen , Xing Liu , Hong Gu , Yutong Liu , Yulun Zhang

We present ENTED, a new framework for blind face restoration that aims to restore high-quality and realistic portrait images. Our method involves repairing a single degraded input image using a high-quality reference image. We utilize a…

计算机视觉与模式识别 · 计算机科学 2024-01-17 Yuen-Fui Lau , Tianjia Zhang , Zhefan Rao , Qifeng Chen

Recent diffusion-based image editing approaches have exhibited impressive editing capabilities in images with simple compositions. However, localized editing in complex scenarios has not been well-studied in the literature, despite its…

计算机视觉与模式识别 · 计算机科学 2023-12-22 Qi Mao , Lan Chen , Yuchao Gu , Zhen Fang , Mike Zheng Shou