Generative AI

Video and image synthesis with diffusion models, GANs, and generative video prediction.

(Mitra & Rawat, 2026) (Mitra & Rawat, 2025) (Lim et al., 2024) (Biyani et al., 2021) (Li et al., 2021) (Schatz et al., 2020) (Shiraz et al., 2021) (Vyas et al., 2020)

References

2026

ProDiG: Progressive Diffusion-Guided Gaussian Splatting for Aerial to Ground Reconstruction

Sirshapan Mitra and Yogesh S. Rawat

In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Findings, 2026

CVPR Findings arXiv Bib Video

@inproceedings{mitra2026prodig,
  title = {ProDiG: Progressive Diffusion-Guided Gaussian Splatting for Aerial to Ground Reconstruction},
  author = {Mitra, Sirshapan and Rawat, Yogesh S.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Findings},
  year = {2026},
}

2025

GaitCrafter: Diffusion Model for Biometric Preserving Gait Synthesis

Sirshapan Mitra and Yogesh Singh Rawat

In IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), 2025

ICCVW arXiv Bib Code Website

@inproceedings{mitra2025gaitcrafter,
  title = {GaitCrafter: Diffusion Model for Biometric Preserving Gait Synthesis},
  author = {Mitra, Sirshapan and Rawat, Yogesh Singh},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)},
  pages = {3726--3735},
  year = {2025},
}

2024

AirSketch: Generative Motion to Sketch

Hui Xian Grace Lim, Xuanming Cui, Ser-Nam Lim, and Yogesh S Rawat

In The Thirty-eighth Annual Conference on Neural Information Processing Systems, 2024

NeurIPS Bib

@inproceedings{lim2024airsketch,
  title = {AirSketch: Generative Motion to Sketch},
  author = {Lim, Hui Xian Grace and Cui, Xuanming and Lim, Ser-Nam and Rawat, Yogesh S},
  booktitle = {The Thirty-eighth Annual Conference on Neural Information Processing Systems},
  year = {2024},
}

2021

LARNet: Latent Action Representation for Human Action Synthesis

Naman Biyani, Aayush J Rana, Shruti Vyas, and Yogesh S Rawat

In The British Machine Vision Conference (BMVC), 2021

BMVC Bib PDF Code Slides Website

@inproceedings{biyani2021larnet,
  title = {LARNet: Latent Action Representation for Human Action Synthesis},
  author = {Biyani, Naman and Rana, Aayush J and Vyas, Shruti and Rawat, Yogesh S},
  booktitle = {The British Machine Vision Conference (BMVC)},
  year = {2021},
}

Pose-guided Generative Adversarial Net for Novel View Action Synthesis

Xianhang Li, Junhao Zhang, Kunchang Li, Shruti Vyas, and Yogesh S Rawat

In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2021

Bib PDF Code Website

@inproceedings{li2021pose,
  title = {Pose-guided Generative Adversarial Net for Novel View Action Synthesis},
  author = {Li, Xianhang and Zhang, Junhao and Li, Kunchang and Vyas, Shruti and Rawat, Yogesh S},
  booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision},
  year = {2021},
}

Novel View Video Prediction Using a Dual Representation

Sarah Shiraz, Krishna Regmi, Shruti Vyas, Yogesh S Rawat, and Mubarak Shah

In IEEE International Conference on Image Processing, 2021

ICIP Bib

@inproceedings{shiraz2021novel,
  title = {Novel View Video Prediction Using a Dual Representation},
  author = {Shiraz, Sarah and Regmi, Krishna and Vyas, Shruti and Rawat, Yogesh S and Shah, Mubarak},
  booktitle = {IEEE International Conference on Image Processing},
  year = {2021},
}

2020

A Recurrent Transformer Network for Novel View Action Synthesis

Kara Marie Schatz, Erik Quintanilla, Shruti Vyas, and Yogesh S Rawat

In Proceedings of the European Conference on Computer Vision (ECCV), 2020

ECCV Bib

@inproceedings{schatz2020recurrent,
  title = {A Recurrent Transformer Network for Novel View Action Synthesis},
  author = {Schatz, Kara Marie and Quintanilla, Erik and Vyas, Shruti and Rawat, Yogesh S},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  year = {2020},
}

Multi-view Action Recognition using Cross-view Video Prediction

Shruti Vyas, Yogesh S Rawat, and Mubarak Shah

In European Conference on Computer Vision (ECCV), 2020

ECCV Bib Code

@inproceedings{vyas2020multi,
  title = {Multi-view Action Recognition using Cross-view Video Prediction},
  author = {Vyas, Shruti and Rawat, Yogesh S and Shah, Mubarak},
  booktitle = {European Conference on Computer Vision (ECCV)},
  year = {2020},
}