2020/05/31 by Lingbo Yang, Pan Wang, Chang Liu +8
Computer Science · Engineering · #3D Shape Modeling and Analysis #Artificial intelligence #Benchmark (surveying) #Computer science #Face recognition and analysis #Focus (optics) #Generative Adversarial Networks and Image Synthesis #Human–computer interaction #Quality (philosophy) #cs.CV
paper · pdf · doi:10.1109/tip.2021.3052364
published as in IEEE Transactions on Image Processing, vol. 30, pp. 2422-2435, 2021 · IEEE TIP accepted at 10.1109/TIP.2021.3052364
openalex publication_date 2021/01/01 · arxiv created 2021/05/07 · arxiv updated 2021/05/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Human pose transfer (HPT) is an emerging research topic with huge potential in fashion design, media production, online advertising and virtual reality. For these applications, the visual realism of fine-grained appearance details is crucial for production quality and user engagement. However, existing HPT methods often suffer from three fundamental issues: detail deficiency, content ambiguity and style inconsistency, which severely degrade the visual quality and realism of generated images. Aiming towards real-world applications, we develop a more challenging yet practical HPT setting, termed as Fine-grained Human Pose Transfer (FHPT), with a higher focus on semantic fidelity and detail replenishment. Concretely, we analyze the potential design flaws of existing methods via an illustrative example, and establish the core FHPT methodology by combing the idea of content synthesis and feature transfer together in a mutually-guided fashion. Thereafter, we substantiate the proposed methodology with a Detail Replenishing Network (DRN) and a corresponding coarse-to-fine model training scheme. Moreover, we build up a complete suite of fine-grained evaluation protocols to address the challenges of FHPT in a comprehensive manner, including semantic analysis, structural detection and perceptual quality assessment. Extensive experiments on the DeepFashion benchmark dataset have verified the power of proposed benchmark against start-of-the-art works, with 12%-14% gain on top-10 retrieval recall, 5% higher joint localization accuracy, and near 40% gain on face identity preservation. Our codes, models and evaluation tools will be released at https://github.com/Lotayou/RATE.