UniHuman: A Unified Model for Editing Human Images in the Wild

• URL: http://arxiv.org/abs/2312.14985v2
• Date: Mon, 1 Apr 2024 02:29:20 GMT
• Title: UniHuman: A Unified Model for Editing Human Images in the Wild
• Authors: Nannan Li, Qing Liu, Krishna Kumar Singh, Yilin Wang, Jianming Zhang, Bryan A. Plummer, Zhe Lin,
• Abstract summary: We propose UniHuman, a unified model that addresses multiple facets of human image editing in real-world settings. To enhance the model's generation quality and generalization capacity, we leverage guidance from human visual encoders. In user studies, UniHuman is preferred by the users in an average of 77% of cases.
• Score: 49.896715833075106
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Human image editing includes tasks like changing a person's pose, their clothing, or editing the image according to a text prompt. However, prior work often tackles these tasks separately, overlooking the benefit of mutual reinforcement from learning them jointly. In this paper, we propose UniHuman, a unified model that addresses multiple facets of human image editing in real-world settings. To enhance the model's generation quality and generalization capacity, we leverage guidance from human visual encoders and introduce a lightweight pose-warping module that can exploit different pose representations, accommodating unseen textures and patterns. Furthermore, to bridge the disparity between existing human editing benchmarks with real-world data, we curated 400K high-quality human image-text pairs for training and collected 2K human images for out-of-domain testing, both encompassing diverse clothing styles, backgrounds, and age groups. Experiments on both in-domain and out-of-domain test sets demonstrate that UniHuman outperforms task-specific models by a significant margin. In user studies, UniHuman is preferred by the users in an average of 77% of cases. Our project is available at https://github.com/NannanLi999/UniHuman.

Related papers

• Evaluating Multiview Object Consistency in Humans and Image Models [68.36073530804296]
  We leverage an experimental design from the cognitive sciences which requires zero-shot visual inferences about object shape. We collect 35K trials of behavioral data from over 500 participants. We then evaluate the performance of common vision models.
  arXiv  Detail & Related papers  (2024-09-09T17:59:13Z)
• Cross-view and Cross-pose Completion for 3D Human Understanding [22.787947086152315]
  We propose a pre-training approach based on self-supervised learning that works on human-centric data using only images. We pre-train a model for body-centric tasks and one for hand-centric tasks. With a generic transformer architecture, these models outperform existing self-supervised pre-training methods on a wide set of human-centric downstream tasks.
  arXiv  Detail & Related papers  (2023-11-15T16:51:18Z)
• PixelHuman: Animatable Neural Radiance Fields from Few Images [27.932366091437103]
  We propose PixelHuman, a novel rendering model that generates animatable human scenes from a few images of a person. Our method differs from existing methods in that it can generalize to any input image for animatable human synthesis. Our experiments show that our method achieves state-of-the-art performance in multiview and novel pose synthesis from few-shot images.
  arXiv  Detail & Related papers  (2023-07-18T08:41:17Z)
• Neural Novel Actor: Learning a Generalized Animatable Neural Representation for Human Actors [98.24047528960406]
  We propose a new method for learning a generalized animatable neural representation from a sparse set of multi-view imagery of multiple persons. The learned representation can be used to synthesize novel view images of an arbitrary person from a sparse set of cameras, and further animate them with the user's pose control.
  arXiv  Detail & Related papers  (2022-08-25T07:36:46Z)
• Hallucinating Pose-Compatible Scenes [55.064949607528405]
  We present a large-scale generative adversarial network for pose-conditioned scene generation. We curating a massive meta-dataset containing over 19 million frames of humans in everyday environments. We leverage our trained model for various applications: hallucinating pose-compatible scene(s) with or without humans, visualizing incompatible scenes and poses, placing a person from one generated image into another scene, and animating pose.
  arXiv  Detail & Related papers  (2021-12-13T18:59:26Z)
• HumanGAN: A Generative Model of Humans Images [78.6284090004218]
  We present a generative model for images of dressed humans offering control over pose, local body part appearance and garment style. Our model encodes part-based latent appearance vectors in a normalized pose-independent space and warps them to different poses, it preserves body and clothing appearance under varying posture.
  arXiv  Detail & Related papers  (2021-03-11T19:00:38Z)
• PISE: Person Image Synthesis and Editing with Decoupled GAN [64.70360318367943]
  We propose PISE, a novel two-stage generative model for Person Image Synthesis and Editing. For human pose transfer, we first synthesize a human parsing map aligned with the target pose to represent the shape of clothing. To decouple the shape and style of clothing, we propose joint global and local per-region encoding and normalization.
  arXiv  Detail & Related papers  (2021-03-06T04:32:06Z)
• Subject-independent Human Pose Image Construction with Commodity Wi-Fi [24.099783319415913]
  This paper focuses on solving the subject-generalization problem in human pose image construction. We design a Domain-Independent Neural Network (DINN) to extract subject-independent features and convert them into fine-grained human pose images. We build a prototype system and experimental results demonstrate that our system can construct fine-grained human pose images of new subjects with commodity Wi-Fi.
  arXiv  Detail & Related papers  (2020-12-22T03:15:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.