paper-with-me

홈 › Papers

IA-FaceS: A Bidirectional Method for Semantic Face Editing

2022-03-24 · Wenjing Huang, Shikui Tu, Lei Xu

Semantic face editing has achieved substantial progress in recent years. Known as a growingly popular method, latent space manipulation performs face editing by changing the latent code of an input face to liberate users from painting skills. However, previous latent space manipulation methods usually encode an entire face into a single low-dimensional embedding, which constrains the reconstruction capacity and the control flexibility of facial components, such as eyes and nose. This paper proposes IA-FaceS as a bidirectional method for disentangled face attribute manipulation as well as flexible, controllable component editing without the need for segmentation masks or sketches in the original image. To strike a balance between the reconstruction capacity and the control flexibility, the encoder is designed as a multi-head structure to yield embeddings for reconstruction and control, respectively: a high-dimensional tensor with spatial properties for consistent reconstruction and four low-dimensional facial component embeddings for semantic face editing. Manipulating the separate component embeddings can help achieve disentangled attribute manipulation and flexible control of facial components. To further disentangle the highly-correlated components, a component adaptive modulation (CAM) module is proposed for the decoder. The semantic single-eye editing is developed for the first time without any input visual guidance, such as segmentation masks or sketches. According to the experimental results, IA-FaceS establishes a good balance between maintaining image details and performing flexible face manipulation. Both quantitative and qualitative results indicate that the proposed method outperforms the other techniques in reconstruction, face attribute manipulation, and component transfer.

📄 PDF Abstract BibTeX arXiv:2203.13097

Code (1)

CMACH508/IA-FaceS 공식 구현 pytorch

Tasks

Attribute

Similar Papers 제목 키워드 기반

FaceShapeGene: A Disentangled Shape Representation for Flexible Face Image Editing

2019-05-06 · Sen-Zhe Xu, Hao-Zhi Huang, Shi-Min Hu, Wei Liu

Existing methods for face image manipulation generally focus on editing the expression, changing some predefined attributes, or applying different filters. However, users lack the flexibility of controlling the shapes of…

Image Manipulation

SmartEdit: Exploring Complex Instruction-based Image Editing with Multimodal Large Language Models

2023-12-11 · CVPR 2024 1 · Yuzhou Huang, Liangbin Xie, Xintao Wang, Ziyang Yuan 외

Current instruction-based editing methods, such as InstructPix2Pix, often fail to produce satisfactory results in complex scenarios due to their dependence on the simple CLIP text encoder in diffusion models. To rectify …

Brain-Supervised Image Editing

2022-01-01 · CVPR 2022 1 · Keith M. Davis III, Carlos de la Torre-Ortiz, Tuukka Ruotsalo

Despite recent advances in deep neural models for semantic image editing, present approaches are dependent on explicit human input. Previous work assumes the availability of manually curated datasets for supervised l…

EEGElectroencephalogram (EEG)Generative Adversarial Network

Towards Realistic Generative 3D Face Models

2023-04-24 · Aashish Rai, Hiresh Gupta, Ayush Pandey, Francisco Vicente Carrasco 외

In recent years, there has been significant progress in 2D generative face models fueled by applications such as animation, synthetic data generation, and digital avatars. However, due to the absence of 3D information, t…

3D Face ReconstructionFace ModelSynthetic Data Generation

IntrinsicEdit: Precise generative image manipulation in intrinsic space

2025-05-13 · Linjie Lyu, Valentin Deschaintre, Yannick Hold-Geoffroy, Miloš Hašan 외

Generative diffusion models have advanced image editing with high-quality results and intuitive interfaces such as prompts and semantic drawing. However, these interfaces lack precise control, and the associated methods …

Image Manipulation