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].
Monocular 3D Hand Mesh Recovery via Dual Noise Estimation
Authors: Hanhui Li, Xiaojian Lin, Xuan Huang, Zejun Yang, Zhisheng Wang, Xiaodan Liang
AAAI 2024 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments on the large-scale Interhand2.6M dataset demonstrate that the proposed method not only improves the performance of its baseline by more than 10% but also achieves state-of-the-art performance. |
| Researcher Affiliation | Collaboration | 1Shenzhen Campus of Sun Yat-sen University, Shenzhen, China 2Tencent, Shenzhen, China 3Dark Matter AI Research, Guangzhou, China |
| Pseudocode | No | The paper does not contain any explicitly labeled 'Pseudocode' or 'Algorithm' blocks, nor does it present structured steps in a code-like format. |
| Open Source Code | Yes | Project page: https://github.com/hanhuili/DNE4Hand. |
| Open Datasets | Yes | Our experiments are conducted on the large-scale Interhand2.6M dataset (Moon et al. 2020) |
| Dataset Splits | No | The paper states 'We use all single-hand (SH) and interacting-hand (IH) images in the training set for training' and 'the whole test set is used for evaluation', but does not explicitly define a separate validation set or its specific split for reproduction. |
| Hardware Specification | Yes | Our networks are trained with 4 Ge Force RTX 4090 graphics cards. |
| Software Dependencies | No | The paper mentions software components like the Adam optimizer and ResNet-50, and refers to PyTorch3D for camera definitions, but does not provide specific version numbers for any software dependencies. |
| Experiment Setup | Yes | We adopt the Adam optimizer (Kingma and Ba 2014) with a batch size of 120 and 30 training epochs. ... The initial learning rate is 10 3 and is scaled by 0.5 after each epoch until it reaches 10 6. |