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].
Multi-body SE(3) Equivariance for Unsupervised Rigid Segmentation and Motion Estimation
Authors: Jia-Xing Zhong, Ta-Ying Cheng, Yuhang He, Kai Lu, Kaichen Zhou, Andrew Markham, Niki Trigoni
NeurIPS 2023 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We conduct experiments on four datasets to demonstrate the superiority of our method. The results show that our method excels in both model performance and computational efficiency, with only 0.25M parameters and 0.92G FLOPs. To the best of our knowledge, this is the first work designed for category-agnostic part-level SE(3) equivariance in dynamic point clouds. |
| Researcher Affiliation | Academia | Jia-Xing Zhong, Ta-Ying Cheng, Yuhang He, Kai Lu, Kaichen Zhou , Andrew Markham, Niki Trigoni Department of Computer Science, University of Oxford EMAIL EMAIL |
| Pseudocode | No | The paper describes its methodology using prose and mathematical equations but does not include any explicitly labeled pseudocode or algorithm blocks. |
| Open Source Code | Yes | The code is available at https://github.com/jx-zhong-for-academicpurpose/Multibody_SE3. |
| Open Datasets | Yes | We conduct comprehensive experiments on four datasets (SAPIEN [68], OGC-DR [61], OGC-DRSV [61], and KITTI-SF [48]) across three application scenarios (articulated objects, furniture arrangements, and vehicular traffic). |
| Dataset Splits | Yes | SAPIEN is a challenging dataset of articulated objects since its training, validation and testing sets comprise completely disjoint categories of objects. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used for experiments, such as GPU or CPU models. It only mentions computational efficiency in terms of FLOPs. |
| Software Dependencies | No | The paper does not specify any software dependencies with version numbers, which would be necessary for reproducibility. |
| Experiment Setup | No | The paper discusses the network architecture and training strategy conceptually but does not provide specific hyperparameter values (e.g., learning rate, batch size) or detailed system-level training configurations in the main text. It mentions "More implementation details can be found in Supp." but no specifics are in the provided text. |