Separate in Latent Space: Unsupervised Single Image Layer Separation
Authors: Yunfei Liu, Feng Lu11661-11668
AAAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results demonstrate its successfulness in outperforming existing unsupervised methods in both synthetic and real world tasks. |
| Researcher Affiliation | Academia | State Key Laboratory of VR Technology and Systems, School of CSE, Beihang University, Beijing, China |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide concrete access to source code (specific repository link, explicit code release statement, or code in supplementary materials) for the methodology described. |
| Open Datasets | Yes | For intrinsic image decomposition, we use 220 images in the MIT intrinsic dataset (Grosse et al. 2011). For reflection removal, we use the reflection removal benchmark dataset (Wan et al. 2017) |
| Dataset Splits | No | The paper mentions training and test sets ("The training set includes 4000 images and the test set has 1000 images.") but does not explicitly provide details about a validation dataset split. |
| Hardware Specification | No | The paper does not provide specific hardware details (exact GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments. |
| Software Dependencies | No | The paper does not provide specific ancillary software details, such as library or solver names with version numbers, needed to replicate the experiment. |
| Experiment Setup | Yes | We use ADAM (Kingma and Ba 2015) optimizer with a learning rate of 0.0001 and momentums of 0.0 and 0.9. The default values of hyper-parameters in Equ. (5)(8) are set to λ0 = 5.0, λ1 = 0.5, λ2 = 0.5, λ3 = 1.0, λ4 = 1.0, λ5 = 1.0, λ6 = 1.0 and α = 1.4. Each mini-batch in training contains one input image from the domain X, one layer image from the domain Y and another one from domain Z. |