Single Motion Diffusion
Authors: Sigal Raab, Inbal Leibovitch, Guy Tevet, Moab Arar, Amit Haim Bermano, Daniel Cohen-Or
ICLR 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Our experiments are held on data from the Human ML3D (2022), Mixamo (2021), and Truebones Zoo (2022) datasets, and on an artist-created animation, using an NVIDIA Ge Force RTX 2080 Ti GPU. |
| Researcher Affiliation | Academia | Sigal Raab , Inbal Leibovitch , Guy Tevet, Moab Arar, Amit H. Bermano and Daniel Cohen-Or Tel Aviv University, Israel {sigal.raab,inbal.leibovitch}@gmail.com |
| Pseudocode | No | The paper does not contain any sections or figures explicitly labeled 'Pseudocode' or 'Algorithm'. |
| Open Source Code | Yes | Our project page, which includes links to the code and trained models, is accessible at https://sinmdm.github.io/Sin MDM-page. |
| Open Datasets | Yes | Our experiments are held on data from the Human ML33D (2022), Mixamo (2021), and Truebones Zoo (2022) datasets |
| Dataset Splits | No | The paper mentions using Human ML3D, Mixamo, and Truebones Zoo datasets but does not explicitly provide training/validation/test split percentages or sample counts, nor does it refer to predefined splits with citations. |
| Hardware Specification | Yes | Our experiments are held on data from the Human ML3D (2022), Mixamo (2021), and Truebones Zoo (2022) datasets, and on an artist-created animation, using an NVIDIA Ge Force RTX 2080 Ti GPU. |
| Software Dependencies | No | Table 4 lists various hyperparameters for the model and training (e.g., 'num channels 256', 'diffusion steps 1000'), but it does not specify software dependencies like programming languages, libraries, or frameworks with their version numbers (e.g., Python, PyTorch, TensorFlow, CUDA versions). |
| Experiment Setup | Yes | In Tab. 4 we detail the values of the hyperparameters that have been used to produce the results shown in this work. |