A Bayesian Approach to Perceptual 3D Object-Part Decomposition Using Skeleton-Based Representations

Authors: Tarek El-Gaaly, Vicky Froyen, Ahmed Elgammal, Jacob Feldman, Manish Singh

AAAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We present results on shapes from a standard database illustrating the effectiveness of the approach. We experimented on the 3D Dataset from Chen, Golovinskiy, and Funkhouser (2009)
Researcher Affiliation Academia Tarek El-Gaaly Department of Computer Science, Rutgers University Piscataway, NJ 08854, USA Vicky Froyen Center for Cognitive Science, Department of Psychology, Rutgers University Piscataway, NJ 08854, USA Ahmed Elgammal Department of Computer Science, Rutgers University Piscataway, NJ 08854, USA Jacob Feldman and Manish Singh Center for Cognitive Science, Department of Psychology, Rutgers University Piscataway, NJ 08854, USA
Pseudocode No The paper describes the algorithm steps in prose (e.g., 'In our implementation the algorithm will initiate...', 'At each iteration the algorithm decides...') but does not provide a formal pseudocode block or algorithm figure.
Open Source Code No The paper does not provide any explicit statements about open-sourcing code, nor does it include links to a code repository.
Open Datasets Yes We experimented on the 3D Dataset from Chen, Golovinskiy, and Funkhouser (2009), which provides a large dataset of 3D meshes 380 objects across 19 different categories.
Dataset Splits No The paper mentions using a 3D dataset and subsampling points but does not provide specific details on training, validation, or test splits (e.g., percentages, counts, or predefined splits).
Hardware Specification No The paper does not provide any specific hardware details (e.g., CPU, GPU models, memory specifications) used for running the experiments.
Software Dependencies No The paper does not specify any software dependencies with version numbers (e.g., programming languages, libraries, or frameworks).
Experiment Setup No The paper describes the mathematical framework and mentions various parameters and priors (e.g., α, λ1, λ2, µ0, κ0, σ0, ν0) as well as methods like Simulated Annealing and Dirichlet processes, but it does not provide concrete numerical values for these hyperparameters or specific training configurations used in the experiments.