TransFill: Reference-Guided Image Inpainting by Merging Multiple Color and Spatial Transformations
Yuqian Zhou, Connelly Barnes, Eli Shechtman, Sohrab Amirghodsi
Abstract
Figure 1: Results of our reference-guided inpainting for user-provided images. We show multiple practical applications like replacing and removing foreground people and objects. Each triad shows the target image with the hole, the source image used as a reference, and the inpainting result. Our method has strong performance and addresses challenging real-world issues such as parallax, 90 degree image rotations, and lighting inconsistency between the source and target images.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 3151d1b7-4f4e-4b13-95cd-e96316826cd6Cited by top-tier papers15
- Emergent Correspondence from Image DiffusionLuming Tang, Menglin Jia, Qianqian Wang, Cheng Perng Phoo et al.NeurIPS 2023 · 555 citations
- SketchEdit: Mask-Free Local Image Manipulation with Partial SketchesYu Zeng, Zhe Lin, Vishal M. PatelCVPR 2022 · 50 citations
- Reference-guided Controllable Inpainting of Neural Radiance FieldsAshkan Mirzaei, Tristan Aumentado-Armstrong, Marcus A. Brubaker, Jonathan Kelly et al.ICCV 2023 · 49 citations
- RealFill: Reference-Driven Generation for Authentic Image CompletionLuming Tang, Nataniel Ruiz, Qinghao Chu, Yuanzhen Li et al.SIGGRAPH 2024 · 37 citations
- MVInpainter: Learning Multi-View Consistent Inpainting to Bridge 2D and 3D EditingChenjie Cao, Chaohui Yu, Fan Wang, Xiangyang Xue et al.NeurIPS 2024 · 36 citations
Builds on10
- Free-Form Image Inpainting With Gated ConvolutionJiahui Yu, Zhe Lin, Jimei Yang, Xiaohui Shen et al.ICCV 2019 · 1,990 citations
- Learning Two-View Correspondences and Geometry Using Order-Aware NetworkJiahui Zhang, Dawei Sun, Zixin Luo, Anbang Yao et al.ICCV 2019 · 362 citations
- StructureFlow: Image Inpainting via Structure-Aware Appearance FlowYurui Ren, Xiaoming Yu, Ruonan Zhang, Thomas H. Li et al.ICCV 2019 · 356 citations
- Copy-and-Paste Networks for Deep Video InpaintingSungho Lee, Seoung Wug Oh, DaeYeun Won, Seon Joo KimICCV 2019 · 137 citations
- Onion-Peel Networks for Deep Video CompletionSeoung Wug Oh, Sungho Lee, Joon-Young Lee, Seon Joo KimICCV 2019 · 112 citations
Related papers
- No Shadow Left Behind: Removing Objects and Their Shadows Using Approximate Lighting and GeometryEdward Zhang, Ricardo Martin-Brualla, Janne Kontkanen, Brian L. CurlessCVPR 2021
- SmartEraser: Remove Anything from Images using Masked-Region GuidanceLongtao Jiang, Zhendong Wang, Jianmin Bao, Wengang Zhou et al.CVPR 2025
- Large-Scale Text-to-Image Model with Inpainting is a Zero-Shot Subject-Driven Image GeneratorChaehun Shin, Jooyoung Choi, Heeseung Kim, Sungroh YoonCVPR 2025
- Disentangled Pose and Appearance Guidance for Multi-Pose GenerationTengfei Xiao, Yue Wu, Yuelong Li, Can Qin et al.CVPR 2025
- AIR-DR: Adaptive Image Retargeting with Instance Relocation and Dual-guidance RepaintingZhitong Dong, Chao Li, Yongjian Deng, Hao ChenAAAI 2026
