GANSpace: Discovering Interpretable GAN Controls
Authors: Erik Härkönen, Aaron Hertzmann, Jaakko Lehtinen, Sylvain Paris
NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We show results on different GANs trained on various datasets, and demonstrate good qualitative matches to edit directions found through earlier supervised approaches. |
| Researcher Affiliation | Collaboration | Erik Härkönen1,2 Aaron Hertzmann2 Jaakko Lehtinen1,3 Sylvain Paris2 1Aalto University 2Adobe Research 3NVIDIA |
| Pseudocode | No | The paper does not contain any clearly labeled pseudocode or algorithm blocks. |
| Open Source Code | Yes | The runnable Python code is attached as supplemental material. |
| Open Datasets | Yes | We show edits discovered on state-of-the-art pretrained GANs, including Big GAN512-deep, Style GAN (Bedrooms, Landscapes, Wiki Art training sets), and Style GAN2 (FFHQ, Cars, Cats, Church, Horse training sets). Details of the computation and the pretrained model sources are found in SM 3. |
| Dataset Splits | No | The paper does not explicitly provide details about training, validation, and test dataset splits, such as percentages, sample counts, or predefined split references. |
| Hardware Specification | No | The paper states: This work was created using computational resources provided by the Aalto Science-IT project. However, it does not provide specific hardware details (e.g., GPU/CPU models, memory amounts). |
| Software Dependencies | No | The paper mentions "runnable Python code is attached as supplemental material" but does not specify Python version numbers or any other software dependencies with their versions. |
| Experiment Setup | No | The paper does not explicitly provide specific experimental setup details, such as hyperparameter values (e.g., learning rate, batch size, number of epochs) or specific optimizer settings. It refers to pretrained models and their sources in SM 3, but does not detail the setup for the experiments conducted in *this* paper. |