ARTIC3D: Learning Robust Articulated 3D Shapes from Noisy Web Image Collections

Authors: Chun-Han Yao, Amit Raj, Wei-Chih Hung, Michael Rubinstein, Yuanzhen Li, Ming-Hsuan Yang, Varun Jampani

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

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive evaluations on multiple existing datasets as well as newly introduced noisy web image collections with occlusions and truncation demonstrate that ARTIC3D outputs are more robust to noisy images, higher quality in terms of shape and texture details, and more realistic when animated.
Researcher Affiliation Collaboration 1UC Merced 2Google Research 3Waymo 4Yonsei University
Pseudocode No The paper does not contain any clearly labeled pseudocode or algorithm blocks.
Open Source Code No The paper does not provide an explicit statement or link for the open-source code of the described methodology.
Open Datasets Yes Datasets. Following [39, 38], we evaluate ARTIC3D on the Pascal-Part [5] and LASSIE [39] images.
Dataset Splits No The paper mentions evaluating on Pascal-Part, LASSIE, and E-LASSIE datasets, but it does not specify explicit training, validation, or test dataset splits (e.g., percentages or counts) or refer to standard splits with citations for reproducibility.
Hardware Specification No The paper does not provide specific details about the hardware (e.g., GPU models, CPU types, memory) used for running the experiments.
Software Dependencies No The paper mentions software components like "Adam optimizer [10]", "Stable Diffusion (SD) [27]", "DINO-Vi T [4]", "Soft Ras [16]", and "CLIP [22]", but does not provide specific version numbers for these or other software dependencies.
Experiment Setup Yes All model parameters are updated using an Adam optimizer [10]. We render the images at 512 512 resolution and at 128 128 for the part texture images. More optimization details are described in the supplemental material.