LEPARD: Learning Explicit Part Discovery for 3D Articulated Shape Reconstruction

Authors: Di Liu, Anastasis Stathopoulos, Qilong Zhangli, Yunhe Gao, Dimitris Metaxas

NeurIPS 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments on 3D animal shape reconstruction, demonstrate significant improvement over existing alternatives in terms of both the overall reconstruction performance as well as the ability to discover semantically meaningful and consistent parts.
Researcher Affiliation Academia Di Liu Qilong Zhangli Yunhe Gao Dimitris N. Metaxas Rutgers University
Pseudocode No The paper does not contain pseudocode or clearly labeled algorithm blocks.
Open Source Code No The paper does not contain an explicit statement about releasing source code or a link to a code repository for the described methodology.
Open Datasets Yes The Pascal-part [7] and LASSIE datasets [67] are used for training and evaluation following prior work [67, 68]. For horses, we train our model using 11k images collected from Pascal [15], LASSIE [67] and DOVE [59] datasets.
Dataset Splits No The paper mentions using datasets for 'training and evaluation' but does not specify explicit splits for training, validation, and test sets (e.g., percentages, absolute counts, or references to predefined splits).
Hardware Specification No The paper does not explicitly describe the hardware used for running its experiments, such as specific GPU/CPU models or memory configurations.
Software Dependencies No The paper does not provide specific version numbers for software dependencies or libraries used in the experiments.
Experiment Setup No The paper does not provide specific details about the experimental setup, such as hyperparameter values (e.g., learning rate, batch size, number of epochs) or optimizer settings.