3D Copy-Paste: Physically Plausible Object Insertion for Monocular 3D Detection

Authors: Yunhao Ge, Hong-Xing Yu, Cheng Zhao, Yuliang Guo, Xinyu Huang, Liu Ren, Laurent Itti, Jiajun Wu

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

Reproducibility Variable Result LLM Response
Research Type Experimental This section presents experiments to assess the effectiveness of our proposed physically-plausible 3D object insertion method and evaluate how different insertion parameters affect the final performance of monocular 3D object detection. ... Table 2 presents the results of monocular 3D object detection on the SUN RGB-D dataset, utilizing various object insertion augmentation techniques.
Researcher Affiliation Collaboration Stanford University University of Southern California Bosch Research North America, Bosch Center for Artificial Intelligence (BCAI)
Pseudocode Yes Algorithm 1 details the Constrained Insertion Parameter Search algorithm.
Open Source Code Yes Project website: https://gyhandy.github. io/3D-Copy-Paste/.
Open Datasets Yes We utilize the SUN RGB-D dataset [Song et al., 2015] as our primary resource for indoor scenes. ... We also use Scan Net dataset [Dai et al., 2017]. ... Hence, we use Objaverse [Deitke et al., 2022], a robust dataset with over 800,000 annotated 3D objects.
Dataset Splits Yes The SUN RGB-D dataset is divided into 5,285 training scenes and 5,050 test scenes. ... Scan Net v2 is a large-scale RGB-D video dataset, which contains 1,201 videos/scenes in the training set and 312 scenes in the validation set.
Hardware Specification No The paper does not provide specific hardware details such as GPU models, CPU types, or cloud computing instance specifications used for running the experiments.
Software Dependencies No The paper mentions 'Imvoxel Net' and 'Blender' as software used, but it does not provide specific version numbers for these or any other software dependencies, making the setup unreproducible in terms of software environment.
Experiment Setup No The paper does not provide specific experimental setup details such as concrete hyperparameter values (e.g., learning rate, batch size, epochs), optimizer settings, or detailed training configurations in the main text.