One-Shot Stylization for Full-Body Human Images
Not on the map. Why?
Abstract (arXiv)
The goal of human stylization is to transfer full-body human photos to a style specified by a single art character reference image. Although previous work has succeeded in example-based stylization of faces and generic scenes, full-body human stylization is a more complex domain. This work addresses several unique challenges of stylizing full-body human images. We propose a method for one-shot fine-tuning of a pose-guided human generator to preserve the "content" (garments, face, hair, pose) of the input photo and the "style" of the artistic reference. Since body shape deformation is an essential component of an art character's style, we incorporate a novel skeleton deformation module to reshape the pose of the input person and modify the DiOr pose-guided person generator to be more robust to the rescaled poses falling outside the distribution of the realistic poses that the generator is originally trained on. Several human studies verify the effectiveness of our approach.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 36 of its 41 references that are in the map. First posted on arXiv 14 Apr 2023.
Builds on
36 of 41 references.
References · 36
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
- 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
- 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
- 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,614
- 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
- 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,300
- 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
- 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,611
- 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 2,010
- 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,937
24 more
- 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,162
- 2022Multi-Concept Customization of Text-to-Image Diffusioncited by 1,106
- 2020Encoding in Style: a StyleGAN Encoder for Image-to-Image Translationcited by 727
- 2018DensePose: Dense Human Pose Estimation In The Wildcited by 575
- 2017Universal Style Transfer via Feature Transformscited by 354
- 2019Self-Correction for Human Parsingcited by 180
- 2020Controllable Person Image Synthesis with Attribute-Decomposed GANcited by 150
- 2022StyleGAN-Human: A Data-Centric Odyssey of Human Generationcited by 144
- 2019Progressive Pose Attention Transfer for Person Image Generationcited by 138
- 2020Deep Image Spatial Transformation for Person Image Generationcited by 100
- 2020XingGAN for Person Image Generationcited by 81
- 2021Mind the Gap: Domain Gap Control for Single Shot Domain Adaptation for Generative Adversarial Networkscited by 68
- 2022Neural Texture Extraction and Distribution for Controllable Person Image Synthesiscited by 55
- 2021Dressing in Order: Recurrent Person Image Generation for Pose Transfer, Virtual Try-on and Outfit Editingcited by 54
- 2021JoJoGAN: One Shot Face Stylizationcited by 49
- 2021Pose with Style: Detail-Preserving Pose-Guided Image Synthesis with Conditional StyleGANcited by 45
- 2022InsetGAN for Full-Body Image Generationcited by 45
- 2022Cross Attention Based Style Distribution for Controllable Person Image Synthesiscited by 45
- 2020Deformable Style Transfercited by 31
- 2021TryOnGAN: Body-Aware Try-On via Layered Interpolationcited by 31
- 2022One-Shot Adaptation of GAN in Just One CLIPcited by 31
- 2022Neural Neighbor Style Transfercited by 23
- 2022WebtoonMe: A Data-Centric Approach for Full-Body Portrait Stylizationcited by 6
- 2022MultiStyleGAN: Multiple One-shot Image Stylizations using a Single GANcited by 3
Built on by
Not cited yet.