HiFi-Inpaint: Towards High-Fidelity Reference-Based Inpainting for Generating Detail-Preserving Human-Product Images
2026-03-02 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors created a new method called HiFi-Inpaint to make pictures that show people using products, like in ads or online stores. Their approach focuses on keeping product details very clear by using examples of the products to guide the image creation. They introduced special techniques to better capture tiny product features and make the images more accurate. They also made a new large dataset to help train their system. Tests showed their method works better than others at preserving product details in these images.
reference-based inpaintinghigh-fidelity image generationhuman-product imagesShared Enhancement Attention (SEA)Detail-Aware Loss (DAL)pixel-level supervisionhigh-frequency mapsimage synthesis datasetproduct detail preservationdigital marketing imagery
Authors
Yichen Liu, Donghao Zhou, Jie Wang, Xin Gao, Guisheng Liu, Jiatong Li, Quanwei Zhang, Qiang Lyu, Lanqing Guo, Shilei Wen, Weiqiang Wang, Pheng-Ann Heng
Abstract
Human-product images, which showcase the integration of humans and products, play a vital role in advertising, e-commerce, and digital marketing. The essential challenge of generating such images lies in ensuring the high-fidelity preservation of product details. Among existing paradigms, reference-based inpainting offers a targeted solution by leveraging product reference images to guide the inpainting process. However, limitations remain in three key aspects: the lack of diverse large-scale training data, the struggle of current models to focus on product detail preservation, and the inability of coarse supervision for achieving precise guidance. To address these issues, we propose HiFi-Inpaint, a novel high-fidelity reference-based inpainting framework tailored for generating human-product images. HiFi-Inpaint introduces Shared Enhancement Attention (SEA) to refine fine-grained product features and Detail-Aware Loss (DAL) to enforce precise pixel-level supervision using high-frequency maps. Additionally, we construct a new dataset, HP-Image-40K, with samples curated from self-synthesis data and processed with automatic filtering. Experimental results show that HiFi-Inpaint achieves state-of-the-art performance, delivering detail-preserving human-product images.