Adaptive Domain Learning for Cross-domain Image Denoising

Authors: Zian Qian, Chenyang Qi, Ka Law, Hao Fu, Chenyang Lei, Qifeng Chen

NeurIPS 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We conduct extensive experiments on public datasets with various smartphone and DSLR cameras, which show our proposed model outperforms prior work on cross-domain image denoising, given a small amount of image data from the target domain sensor.
Researcher Affiliation Collaboration Zian Qian1 Chenyang Qi1 Ka Lung Law2 Hao Fu2 Chenyang Lei3 Qifeng Chen1 1HKUST 2Sense Time 3CAIR, HKISI-CAS
Pseudocode Yes Algorithm 1 Adaptive domain learning (ADL)
Open Source Code No Justification: We will release the code in the future.
Open Datasets Yes We conduct extensive experiments on public datasets with various smartphone and DSLR cameras... SIDD [2] is a popular RAW denoising dataset... ELD Dataset [42] contains RAW data... SID dataset [5] captured RAW data...
Dataset Splits Yes At the beginning of the training, k is set to 20% of the size of T adp and increases during the training process. At the end of the training, 50% of T adp will be used.
Hardware Specification No No specific hardware details (like GPU/CPU models, memory, or cloud instance types) are provided for the experimental setup.
Software Dependencies No The paper mentions 'Adam W as the optimizer' but does not provide version numbers for any software dependencies, libraries, or programming languages.
Experiment Setup Yes We train our ADL in 300k iterations, using Adam W as the optimizer with a learning rate of 3 10 3.