EVA3D: Compositional 3D Human Generation from 2D Image Collections
Authors: Fangzhou Hong, Zhaoxi Chen, Yushi LAN, Liang Pan, Ziwei Liu
ICLR 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments validate that EVA3D achieves state-of-the-art 3D human generation performance regarding both geometry and texture quality. Quantitative and qualitative experiments are performed on two fashion datasets (Liu et al., 2016; Fu et al., 2022) to demonstrate the advantages of EVA3D. We also experiment on UBCFashion (Zablotskaia et al., 2019) and AIST (Tsuchida et al., 2019) for comparison with prior work. |
| Researcher Affiliation | Academia | S-Lab, Nanyang Technological University {fangzhou001, zhaoxi001, yushi001, liang.pan, ziwei.liu}@ntu.edu.sg |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks. |
| Open Source Code | Yes | Our code is publicly available at https://github.com/hongfz16/EVA3D. |
| Open Datasets | Yes | We conduct experiments on four datasets: Deep Fashion (Liu et al., 2016), SHHQ (Fu et al., 2022), UBCFashion (Zablotskaia et al., 2019) and AIST (Tsuchida et al., 2019). |
| Dataset Splits | No | The paper does not provide specific dataset split information (exact percentages, sample counts, or detailed splitting methodology) needed to reproduce the data partitioning into training, validation, and test sets. It mentions '50K samples... are used to compute FID and KID' and 'PCKh@0.5 and Depth are evaluated on 5K samples,' but these refer to the size of evaluation sets for metrics, not a general dataset split for model training and validation. |
| Hardware Specification | No | The paper does not provide specific hardware details (exact GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments. |
| Software Dependencies | No | The paper does not provide specific ancillary software details with version numbers. It mentions 'SIREN activation' but does not specify software library versions. |
| Experiment Setup | No | The paper does not contain specific experimental setup details such as concrete hyperparameter values (e.g., learning rate, batch size, number of epochs) or the specific values for the empirically defined loss weights (λoff, λeik). |