Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
ISP: Multi-Layered Garment Draping with Implicit Sewing Patterns
Authors: Ren Li, Benoît Guillard, Pascal Fua
NeurIPS 2023 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | 4 Experiments, We compare our approach against recent and state-of-the-art methods DIG [29] and Drape Net [30], The quantitative results reported in Tab. 1 for the training and test sets confirm this. |
| Researcher Affiliation | Academia | Computer Vision Lab, EPFL Lausanne, Switzerland |
| Pseudocode | Yes | Algorithm 1: Multi-layer Draping |
| Open Source Code | Yes | Our code is available at https://github.com/liren2515/ISP. |
| Open Datasets | Yes | To create training and test sets, we used the software of [46] to generate sewing patterns and the corresponding 3D garment meshes in their rest state, that is draped over a T-Posed body. |
| Dataset Splits | No | The paper specifies a 'training set' and a 'test set' with specific counts, but does not explicitly mention a 'validation set' or its size/split proportion. |
| Hardware Specification | Yes | Our reconstruction time is 77 ms on an Nvidia V100 GPU |
| Software Dependencies | No | The paper does not provide specific version numbers for software dependencies such as deep learning frameworks (e.g., PyTorch, TensorFlow) or other libraries. |
| Experiment Setup | Yes | The batch sizes, the learning rates and the numbers of iterations for training are summarized in Table. 7. The hyperparameters of the training losses are summarized in Table. 8. |