No Shadow Left Behind: Removing Objects and Their Shadows Using Approximate Lighting and Geometry
Edward Zhang, Ricardo Martin-Brualla, Janne Kontkanen, Brian L. Curless
2021年份
1顶会引用
摘要
We present a method to remove an object and its shadows from an image, to enable applications like home refurnishing. Our method takes as input an image, approximate scene lighting and geometry, and an object mask, and generates a new version of the image that depicts the scene as if the object had not been present. This not only includes inpainting the occluded pixels, but removing any shadows cast by the object.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper1
问问它们各自怎么用它它引用的顶会 Paper4
- ARGAN: Attentive Recurrent Generative Adversarial Network for Shadow Detection and RemovalBin Ding, Chengjiang Long, Ling Zhang, Chunxia XiaoICCV 2019 · 被引用 171 次
- Contextual Residual Aggregation for Ultra High-Resolution Image InpaintingZili Yi, Qiang Tang, Shekoofeh Azizi, Daesik Jang 等CVPR 2020
- Lighthouse: Predicting Lighting Volumes for Spatially-Coherent IlluminationPratul P. Srinivasan, Ben Mildenhall, Matthew Tancik, Jonathan T. Barron 等CVPR 2020
- Instance Shadow DetectionTianyu Wang, Xiaowei Hu, Qiong Wang, Pheng-Ann Heng 等CVPR 2020
相关 Paper
- What You Can Reconstruct from a ShadowRuoshi Liu, Sachit Menon, Chengzhi Mao, Dennis Park 等CVPR 2023
- SmartEraser: Remove Anything from Images using Masked-Region GuidanceLongtao Jiang, Zhendong Wang, Jianmin Bao, Wengang Zhou 等CVPR 2025
- GeoRemover: Removing Objects and Their Causal Visual ArtifactsZixin Zhu, Haoxiang Li, Xuelu Feng, He Wu 等NeurIPS 2025 · 被引用 11 次
- SPIn-NeRF: Multiview Segmentation and Perceptual Inpainting with Neural Radiance FieldsAshkan Mirzaei, Tristan Aumentado-Armstrong, Konstantinos G. Derpanis, Jonathan Kelly 等CVPR 2023
- OmniSR: Shadow Removal Under Direct and Indirect LightingJiamin Xu, Zelong Li, Yuxin Zheng, Chenyu Huang 等AAAI 2025 · 被引用 18 次
