Fetching the paper…

Reading the bibliography…

2023

DESOBAv2: Towards Large-scale Real-world Dataset for Shadow Generation

Liu, Qingyang, Wang, Jianting, Niu, Li

Original
PDF
Post on X

Understand

Image composition refers to inserting a foreground object into a background image to obtain a composite image.

In this work, we focus on generating plausible shadow for the inserted foreground object to make the composite image more realistic.
To supplement the existing small-scale dataset DESOBA, we create a large-scale dataset called DESOBAv2 by using object-shadow detection and inpainting techniques.
Specifically, we collect a large number of outdoor scene images with object-shadow pairs.

DESOBAv2: Towards Large-scale Real-world Dataset for Shadow Generation · Around

Built on

St-gan: Spatial transformer generative adversarial networks for image compositing
Chen-Hsuan Lin, Ersin Yumer, Oliver Wang, Eli Shechtman, and Simon Lucey · 2018
Earlier work this paper cites.
Toward realistic image compositing with adversarial learning
Bor-Chun Chen and Andrew Kae · 2019
Earlier work this paper cites.
Compositional gan: Learning image-conditional binary composition
Samaneh Azadi, Deepak Pathak, Sayna Ebrahimi, and Trevor Darrell · 2020
Earlier work this paper cites.
Investigating object compositionality in generative adversarial networks
Sjoerd van Steenkiste, Karol Kurach, Jürgen Schmidhuber, and Sylvain Gelly · 2020
Earlier work this paper cites.

Similar

Misc: Multi-condition injection and spatially-adaptive compositing for conditional person image synthesis
Shuchen Weng, Wenbo Li, Dawei Li, Hongxia Jin, and Boxin Shi · 2020
Cited alongside, same era.
What and where: A context-based recommendation system for object insertion
Song-Hai Zhang, Zheng-Ping Zhou, Bin Liu, Xi Dong, and Peter Hall · 2020
Cited alongside, same era.
Shadow generation for composite image in real-world scenes
Yan Hong, Li Niu, and Jianfu Zhang · 2022
Cited alongside, same era.

Then

High-resolution image synthesis with latent diffusion models
Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Björn Ommer · 2022
Later among the works it cites.
Instance shadow detection with a single-stage detector
Tianyu Wang, Xiaowei Hu, Pheng-Ann Heng, and Chi-Wing Fu · 2022
Later among the works it cites.
Shadowformer: Global context helps image shadow removal
Lanqing Guo, Siyu Huang, Ding Liu, Hao Cheng, and Bihan Wen · 2023
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…