Unsupervised Learning of Shape Programs with Repeatable Implicit Parts

Authors: Boyang Deng, Sumith Kulal, Zhengyang Dong, Congyue Deng, Yonglong Tian, Jiajun Wu

NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our empirical studies show that Pro GRIP outperforms existing structured representations in both shape reconstruction fidelity and segmentation accuracy of semantic parts.
Researcher Affiliation Academia Boyang Deng1, Sumith Kulal1, Zhengyang Dong1 Congyue Deng1 Yonglong Tian2 Jiajun Wu1 1Stanford University, 2MIT, equal contributions
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code No We plan to release our source code upon publication.
Open Datasets Yes We conduct all our experiments using the Shape Net [6] dataset following Shape Net Terms of Use.
Dataset Splits No The paper does not provide specific dataset split information (exact percentages, sample counts, or detailed splitting methodology) for training, validation, and test sets.
Hardware Specification No The paper does not provide specific hardware details (e.g., exact GPU/CPU models, processor types, or memory amounts) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details with version numbers (e.g., library or solver names with version numbers).
Experiment Setup Yes In our experiments, we use λs = 1, λv = 0.2, and λe = 0.8 for all categories.