Large-Vocabulary 3D Diffusion Model with Transformer
Authors: Ziang Cao, Fangzhou Hong, Tong Wu, Liang Pan, Ziwei Liu
ICLR 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments on Shape Net and Omni Object3D (over 200 diverse real-world categories) convincingly demonstrate that a single Diff TF model achieves state-of-the-art large-vocabulary 3D object generation performance with large diversity, rich semantics, and high quality. More results are available at https://difftf.github.io/. |
| Researcher Affiliation | Academia | Ziang Cao1, Fangzhou Hong1, Tong Wu2,3, Liang Pan1,3, Ziwei Liu1 1S-Lab, Nanyang Technological University, 2The Chinese University of Hong Kong, 3Shanghai Artificial Intelligence Laboratory {ziang.cao,fangzhou.hong,liang.pan,ziwei.liu}@ntu.edu.sg wt020@ie.cuhk.edu.hk |
| Pseudocode | No | The paper describes methods in text and uses figures to illustrate architecture, but does not contain clearly labeled 'Pseudocode' or 'Algorithm' blocks. |
| Open Source Code | No | The paper states 'More results are available at https://difftf.github.io/', which points to a project webpage, but it does not explicitly state that the source code for their methodology is released or provide a direct link to a code repository. |
| Open Datasets | Yes | Datasets. Following most previous works, we use the Shape Net (Chang et al., 2015) including Chair, Airplane, and Car for evaluating the 3D generation which contains 6770, 4045, and 3514 objects, respectively. Additionally, to evaluate the large-vocabulary 3D object generation, we conduct the experiments on a most recent 3D dataset, Omni Object3D (Wu et al., 2023). |
| Dataset Splits | No | The paper references datasets and mentions evaluation metrics but does not specify exact split percentages, absolute sample counts for each split, or reference predefined splits for training, validation, or testing. |
| Hardware Specification | No | The paper does not provide any specific hardware details (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, such as library or solver names with version numbers, needed to replicate the experiment. |
| Experiment Setup | No | The paper has an 'Implementation Details' section but does not provide specific hyperparameter values, training configurations, or system-level settings within the main text. It mentions 'More details about the two-step training process are released in the Appendix', but the question refers to details in the main text. |