记录一些看到过的其它topic的论文
- Relighting
- Image Harmonization
- Image Matting
- Image Stitching
- Image Decomposition
- Image Fusion (Archived)
- VLM
- Uncategorized)
-
Face Relighting with Geometrically Consistent Shadows
Andrew Hou, Michel Sarkis, Ning Bi, Yiying Tong, Xiaoming Liu
[CVPR 2022] [Pytorch-Code] -
Total Relighting: Learning to Relight Portraits for Background Replacemen
Rohit Pandey, Sergio Orts-Escolano, Chloe LeGendre, Christian Haene, Sofien Bouaziz, Christoph Rhemann, Paul Debevec, Sean Fanello
[SIGGRAPH 2021] [Project]
-
Semi-supervised Parametric Real-world Image Harmonization
Ke Wang, Michaël Gharbi, He Zhang, Zhihao Xia, Eli Shechtman
[CVPR 2023] [Project] [Pytorch-Code] -
High-Resolution Image Harmonization via Collaborative Dual Transformations
Wenyan Cong, Xinhao Tao, Li Niu, Jing Liang, Xuesong Gao, Qihao Sun, Liqing Zhang
[CVPR 2022] [Pytorch-Code]
[CDTNet] -
SCS-Co: Self-Consistent Style Contrastive Learning for Image Harmonization
Yucheng Hang, Bin Xia, Wenming Yang, Qingmin Liao
[CVPR 2022] [Pytorch-Code] -
SSH: A Self-Supervised Framework for Image Harmonization
Yifan Jiang, He Zhang, Jianming Zhang, Yilin Wang, Zhe Lin, Kalyan Sunkavalli, Simon Chen, Sohrab Amirghodsi, Sarah Kong, Zhangyang Wang
[ICCV 2021] [PyTorch-Code]
-
Adaptive Human Matting for Dynamic Videos
Chung-Ching Lin, Jiang Wang, Kun Luo, Kevin Lin, Linjie Li, Lijuan Wang, Zicheng Liu
[CVPR 2023] [Pytorch-Code] -
Referring Image Matting
Jizhizi Li, Jing Zhang, Dacheng Tao
[CVPR 2023] [Pytorch-Code] -
Human Instance Matting via Mutual Guidance and Multi-Instance Refinement
Yanan Sun, Chi-Keung Tang, Yu-Wing Tai
[CVPR 2022] [Code] -
MatteFormer: Transformer-Based Image Matting via Prior-Tokens
GyuTae Park, SungJoon Son, JaeYoung Yoo, SeHo Kim, Nojun Kwak
[CVPR 2022] [Pytorch-Code] -
Boosting Robustness of Image Matting with Context Assembling and Strong Data Augmentation
Yutong Dai, Brian Price, He Zhang, Chunhua Shen
[CVPR 2022] [Project]
- Deep Rectangling for Image Stitching: A Learning Baseline
Lang Nie, Chunyu Lin, Kang Liao, Shuaicheng Liu, Yao Zhao
[CVPR 2022 Oral] [Pytorch-Code]
-
PIE-Net: Photometric Invariant Edge Guided Network for Intrinsic Image Decomposition
Partha Das, Sezer Karaoglu, Theo Gevers
[CVPR 2022] [Pytorch-Code] -
Deformable Sprites for Unsupervised Video Decomposition
Vickie Ye, Zhengqi Li, Richard Tucker, Angjoo Kanazawa, Noah Snavely
[CVPR 2022] [Pytorch-Code]
-
Learning a Deep Convolutional Network for Colorization in Monochrome-Color Dual-Lens System
Xuan Dong, Weixin Li, Xiaojie Wang, Yunhong Wang
[AAAI 2019]
[★] 1) 提出了一个Mono和Color图像融合的网络, 将融合看做对Mono图像的上色问题. 未开源, 非轻量级. 2) 分为rough和fine两部分, 首先将color图像在x方向加权求和作为rough result, 其中权值是使用3D卷积预测的weight volume; 接下来再用rough result和mono图像作为输入进行refine. -
Stereoscopic Dark Flash for Low-light Photography
Jian Wang, Tianfan Xue, Jonathan T. Barron, Jiawen Chen
[Siggraph 2017]
[★] 1) 大致浏览, 提出了一个RGB和NIR-NUV双相机成像方案, 以增强低光照条件下的图像质量. 2) 分为registration, 基于scalemap的融合, 基于HDRNet的tone correction三部分. -
Enhancement of low light level images using color-plus-mono dual camera
Yong Ju Jung
[Optics express 2017]
[★☆] 1) 提出了一个融合Mono和Color图像的流程, 包括直方图匹配, 配准, Color+Color和Color+Mono的引导滤波, BJND-aware merge和detail trainsfer几个步骤. 2) 大致流程与 Digital Photography with Flash and No-Flash Image Pairs 这篇paper类似, 创新点是提出用BJND引导detail transfer. BJND即binocular just-noticeable-difference, 是根据人眼视觉系统的特性提出的. 具体方法中有很多参数和细节. -
Stereo Matching with Color and Monochrome Cameras in Low-light Conditions
Hae-Gon Jeon, Joon-Young Lee, Sunghoon Im, Hyowon Ha, In So Kweon
[CVPR 2016]
[★] -
Exposure Fusion
Tom Mertens，Jan Kautz，Frank Van Reeth
[PG 2017] [Code]
[★★] 1) 提出了一个融合exposure bracketing图像的经典方案, 可以直接融合图像序列而无需现将其转换为HDR图像再tone mapping. 2) 使用三个指标确定每张图像的权重图, 三个指标为对比度, 饱和度和well-exposureness, 最后的权重为三个指标相乘. 3) 为消除直接逐像素融合产生的seam, 将图像和权重图分别计算分解为拉普拉斯和高斯金字塔, 在每个level做融合. -
Digital Photography with Flash and No-Flash Image Pairs
Georg Petschnigg, Maneesh Agrawala, Hugues Hoppe, Richard Szeliski, Michael Cohen, Kentaro Toyama
[SIGGRAPH 2004] [Project] [Code]
[★★] 提出了一个融合Flash和Non-Flash照片的流程, 包括双边滤波, 联合双边滤波, detail提取和detail transfer. 可用于去躁, 白平衡, 去红眼, 调整flash强度等多种图像增强应用中.
- Images Speak in Images: A Generalist Painter for In-Context Visual Learning
Xinlong Wang, Wen Wang, Yue Cao, Chunhua Shen, Tiejun Huang
[CVPR 2023] [Pytorch-Code]
🔥 智源
-
High-resolution image reconstruction with latent diffusion models from human brain activity
Yu Takagi, Shinji Nishimoto
[CVPR 2023] [Project] [Pytorch-Code] -
Perspective Fields for Single Image Camera Calibration
Linyi Jin, Jianming Zhang, Yannick Hold-Geoffroy2, Oliver Wang, Kevin Matzen, Matthew Sticha, David Fouhey
[CVPR 2023] [Project] [Pytorch-Code] -
DC2: Dual-Camera Defocus Control by Learning to Refocus
Hadi Alzayer, Abdullah Abuolaim, Leung Chun Chan, Yang Yang, Ying Chen Lou, Jia-Bin Huang, Abhishek Kar
[CVPR 2023] [Project]
Google