3 papers
cs.CV2021
PREMA: Part-based REcurrent Multi-view Aggregation Network for 3D Shape Retrieval
Jiongchao Jin, Huanqiang Xu, Pengliang Ji +2
We propose the Part-based Recurrent Multi-view Aggregation network(PREMA) to eliminate the detrimental effects of the practical view defects, such as insufficient view numbers, occ…
cs.CV2021
RaidaR: A Rich Annotated Image Dataset of Rainy Street Scenes
Jiongchao Jin, Arezou Fatemi, Wallace Lira +5
We introduce RaidaR, a rich annotated image dataset of rainy street scenes, to support autonomous driving research. The new dataset contains the largest number of rainy images (58,…
cs.GR2019
DR-KFS: A Differentiable Visual Similarity Metric for 3D Shape Reconstruction
Jiongchao Jin, Akshay Gadi Patil, Zhang Xiong +1
We introduce a differential visual similarity metric to train deep neural networks for 3D reconstruction, aimed at improving reconstruction quality. The metric compares two 3D shap…