Sharath Golluri is currently a Software Engineer at Amazon, based in Seattle.

He was a Master’s student in Robotics with the SAIR Lab at the University at Buffalo (UB). His interests lie in the intersection of 3D computer vision, robot perception, and SLAM. His research work includes developing multi-modal fusion models based on ViTs and transformers.

Experience

Software Engineer, Amazon
- Nov 2024 - Present
Master of Science in Robotics
- University at Buffalo (UB), USA
- Aug 2022 - Nov 2024
Senior Software Engineer
- Groww, India
- 2020 - 2022
Software Engineer
- InMobi, India
- 2019 - 2020
Bachelor of Engineering
- Birla Institute of Technology and Science, Pilani, India
- 2015 - 2019

Other Information

Email: sgolluri@buffalo.edu

Publications

SuperPC: A Single Diffusion Model for Point Cloud Completion, Upsampling, Denoising, and Colorization.
Yi Du, Zhipeng Zhao, Shaoshu Su, Sharath Golluri, Haoze Zheng, Runmao Yao, Chen Wang.
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16953–16964, 2025.

Unifying point cloud processing via a single diffusion model
```
@inproceedings{du2025superpc,
  title = {{SuperPC}: A Single Diffusion Model for Point Cloud Completion, Upsampling, Denoising, and Colorization},
  author = {Du, Yi and Zhao, Zhipeng and Su, Shaoshu and Golluri, Sharath and Zheng, Haoze and Yao, Runmao and Wang, Chen},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  url = {https://arxiv.org/abs/2503.14558},
  year = {2025},
  pages = {16953--16964},
  code = {https://github.com/sair-lab/superpc},
  website = {https://sairlab.org/superpc/},
  cover = {/img/posts/2025-02-28-superpc/superpc_cover.mp4},
  addendum = {Unifying point cloud processing via a single diffusion model}
}
```
```
Du, Yi and Zhao, Zhipeng and Su, Shaoshu and Golluri, Sharath and Zheng, Haoze and Yao, Runmao and Wang, Chen, "SuperPC: A Single Diffusion Model for Point Cloud Completion, Upsampling, Denoising, and Colorization," IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025.
```