Published in IEEE TVCG (CVM 2025), 2024
This paper reconstructs 3D objects albedo with unknown illumination, in hand-object interaction scenes.
Aggarwal, A., Wang, N. & Guo, X. (2024). TexHOI: Reconstructing Textures of 3D Unknown Objects in Monocular Hand-Object Interaction Scenes.
Published in 16th Asian Conference on Computer Vision (ACCV2022), 2022
This paper reconstructs multiple implicit layers of intersection-free garments on an implicit human body
Aggarwal, A., Wang, J., Hogue, S., Ni, S., Budagavi, M., & Guo, X. (2022). Layered-Garment Net: Generating Multiple Implicit Garment Layers from a Single Image. In Proceedings of the Asian Conference on Computer Vision (pp. 3000-3017).
Published in 2020 IEEE International IOT, Electronics and Mechatronics Conference (IEMTRONICS), 2020
This paper introduces a GAN-based architecture to de-identify the faces from public dataset for privacy protection, without the loss of other non-biometric information.
Aggarwal, A., Rathore, R., Chattopadhyay, P., & Wang, L. (2020, September). EPD-Net: A GAN-based Architecture for Face De-identification from Images. In 2020 IEEE International IOT, Electronics and Mechatronics Conference (IEMTRONICS) (pp. 1-7). IEEE.
Published in Proceedings of the International Conference on Emerging Technologies in Graphics IEMGraph 2018 in AICS, vol 937 Series of Springer, Singapore, 2019
This paper discusses about an improvement in Broad Neural Network’s architecture, and its performace in highly imbalanced data formed by introducing changes in satellite or aerial images of landscapes.
Shrivastava S., Aggarwal A., Chattopadhyay P. (2020) Broad Neural Network for Change Detection in Aerial Images. In: Mandal J., Bhattacharya D. (eds) Emerging Technology in Modelling and Graphics. Advances in Intelligent Systems and Computing, vol 937. Springer, Singapore
Published in Proceeding of the National Conference on Computer Vision, Pattern Recognition, Image Processing, and Graphics NCVPRIPG 2017 in CCIS, vol 841 Series of Springer, Singapore, 2018
This paper discusses our approach of transferring the learned object detection features trained entirely on Synthetic Images and tested on Real Images, which show significant performance improvements, along with easily generatable huge data for Deep Neural Networks.
Rajpura P. et al. (2018) Transfer Learning by Finetuning Pretrained CNNs Entirely with Synthetic Images. In: Rameshan R., Arora C., Dutta Roy S. (eds) Computer Vision, Pattern Recognition, Image Processing, and Graphics. NCVPRIPG 2017. Communications in Computer and Information Science, vol 841. Springer, Singapore