Approximately Piecewise E(3) Equivariant Point Networks

Authors: Matan Atzmon, Jiahui Huang, Francis Williams, Or Litany

ICLR 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our empirical results demonstrate the advantage of integrating piecewise E(3) symmetry into network design, showing a distinct improvement in generalization accuracy compared to prior works for both classification and segmentation tasks.
Researcher Affiliation Collaboration Matan Atzmon 1 Jiahui Huang 1 Francis Williams 1 Or Litany1 2 1 NVIDIA 2 Technion {matzmon,jiahuih,fwilliams,olitany}@nvidia.com
Pseudocode Yes Algorithm 1 Q prediction
Open Source Code No The paper does not contain an explicit statement about releasing source code or provide a link to a code repository for the described methodology.
Open Datasets Yes We conducted experiments using datasets comprising of (i) articulated objects consisting of human subjects performing various sequence movements (Bogo et al., 2017), and (ii) real-world room scans of furniture-type objects (Huang et al., 2021a).
Dataset Splits Yes The first consists of a random (90%/10%) train/test split of 41,461 human models from the SMPL dataset (Loper et al., 2015) consisting of 10 different human subjects as in (Huang et al., 2021b).
Hardware Specification Yes Training was done on a single Nvidia V-100 GPU
Software Dependencies No The paper mentions 'using PYTORCH deep learning framework (Paszke et al., 2019)' but does not specify a version number for PyTorch or any other software dependency.
Experiment Setup Yes We set σl = (0.002,0.005,0.008,0.1). The number of iterations for the EM was 16. We trained our networks using the ADAM (Kingma & Ba, 2014) optimizer, setting the batch size to 8. We set a fixed learning rate of 0.001. All models were trained for 3000 epochs.