HiFi-Inpaint: Towards High-Fidelity Reference-Based Inpainting for Generating Detail-Preserving Human-Product Images
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917415361708032 |
|---|---|
| author | Liu, Yichen Zhou, Donghao Wang, Jie Gao, Xin Liu, Guisheng Li, Jiatong Zhang, Quanwei Lyu, Qiang Guo, Lanqing Wen, Shilei Wang, Weiqiang Heng, Pheng-Ann |
| author_facet | Liu, Yichen Zhou, Donghao Wang, Jie Gao, Xin Liu, Guisheng Li, Jiatong Zhang, Quanwei Lyu, Qiang Guo, Lanqing Wen, Shilei Wang, Weiqiang Heng, Pheng-Ann |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_02210 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | HiFi-Inpaint: Towards High-Fidelity Reference-Based Inpainting for Generating Detail-Preserving Human-Product Images Liu, Yichen Zhou, Donghao Wang, Jie Gao, Xin Liu, Guisheng Li, Jiatong Zhang, Quanwei Lyu, Qiang Guo, Lanqing Wen, Shilei Wang, Weiqiang Heng, Pheng-Ann Computer Vision and Pattern Recognition 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. |
| title | HiFi-Inpaint: Towards High-Fidelity Reference-Based Inpainting for Generating Detail-Preserving Human-Product Images |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.02210 |