Prompt-Aware Controllable Shadow Removal

Authors: Kerui Chen, Zhiliang Wu, Wenjin Hou, Kun Li, Hehe Fan, Yi Yang

IJCAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experimental results demonstrate the effectiveness and superiority of PACSRNet.
Researcher Affiliation Academia Kerui Chen , Zhiliang Wu , Wenjin Hou , Kun Li , Hehe Fan and Yi Yang Re LER, CCAI, Zhejiang University, China
Pseudocode No The paper describes the network design and modules through text and mathematical formulations but does not include any explicitly labeled pseudocode or algorithm blocks.
Open Source Code No The paper states, "We will release it to facilitate subsequent research," referring to the dataset, not the source code for their methodology. There is no explicit statement about releasing their code or a link to a code repository.
Open Datasets Yes In this paper, we customize the prompt-based controllable shadow removal dataset, named PCSRD. ... Dataset: https://drive.google.com/drive/folders/1h AQJ4pfp C1m77vp Gihd NZJlebrx VTyf?usp=drivelink. In addition to our customized PCSRD dataset, we also introduce the ISTD+ [Le and Samaras, 2019] dataset to validate the effectiveness of our shadow removal module.
Dataset Splits Yes The final dataset PACSRD 1 consists of 11,900 complex scenes samples with resolution of 256 256, which are randomly divided into 10,000 for training, 1,000 for validation, and 900 for testing. ... ISTD+ [Le and Samaras, 2019] dataset includes 1,330 training and 540 testing triplets.
Hardware Specification No The paper does not provide any specific details about the hardware (e.g., GPU models, CPU types, memory) used for running the experiments.
Software Dependencies No The paper does not mention any specific software dependencies or library versions (e.g., Python, PyTorch, CUDA versions) required to replicate the experiments.
Experiment Setup Yes L = λLre + Lpr, (8) where Lre and Lpr denote shadow removal loss and shadow prediction loss, respectively. λ is a trade-off parameter. In real implementation, we empirically set λ = 3.