Sparsh Garg

I am currently pursuing a Master’s degree at Carnegie Mellon University, specializing in computer vision and robotics. Under the mentorship of Dr. George A. Kantor at the Robotics Institute's Kantor Lab, I am engaged in advancing automation technologies for agriculture and physical sciences. My work focuses on developing advanced perception and manipulation pipelines for various downstream appliactions including agriculture.

I worked as a Research Intern at Bosch Center for Artificial Intelligence (BCAI), Sunnyvale. At Bosch, I co-developed a state-of-the-art model for monocular metric depth estimation from any camera.

Prior to my current pursuit, I earned my undergraduate degree from Punjab Engineering College, India. Subsequently, I gained valuable professional experience working at ExxonMobil in Bangalore. Following this, I served as a Design & Development Engineer in the RnD team of Cybernetics Laboratory (CynLr), Bangalore. At CynLr, I played a key role in developing a stereo vision system from the ground up, contributing to both the hardware and software layers of the first version of the product.

My overarching goal is to contribute to the realization of truly autonomous systems. Recognizing the pivotal role of vision in achieving this objective, I have dedicated my master's program to in-depth study and research in the field of computer vision. My research interests span computer vision, deep learning, and robotics.

I am enthusiastic about leveraging my skills and knowledge to advance the frontier of autonomous technologies and make a meaningful impact on the field.

I am actively looking for full-time opportunities in the field of robotics and computer vision. If you think I can be a good fit for your team, please feel free to reach out.

    email: sparshg@andrew.cmu.edu
    Office: CIC Robotics Institute (near Lab 2)

Publications

Depth Any Camera (DAC): A Framework for Zero-Shot Metric Depth Estimation Across Diverse Camera Types
Yuliang Guo*, Sparsh Garg*, S. Mahdi H. Miangoleh, Xinyu Huang, Liu Ren
(Accepted to CVPR 2025)
pdf project page abstract bibtex

            @inproceedings{guo2025depthanycamera,
              title={Depth Any Camera: Zero-Shot Metric Depth Estimation from Any Camera},
              author={Yuliang Guo and Sparsh Garg and S. Mahdi H. Miangoleh and Xinyu Huang and Liu Ren},
              booktitle={arXiv},
              year={2025}
            }

SplatSim: Zero-Shot Sim2Real Transfer of RGB Manipulation Policies Using Gaussian Splatting
Mohammad Nomaan Qureshi, Sparsh Garg, Francisco Yandun, David Held, George Kantor, Abhisesh Silwal
(Accepted to ICRA 2025) (Spotlight Presentation at CoRL MRM-D Workshop)
pdf project page abstract bibtex

Sim2Real transfer, particularly for manipulation policies relying on RGB images, remains a critical challenge in robotics due to the significant domain shift between syn- thetic and real-world visual data. In this paper, we propose SplatSim, a novel framework that leverages Gaussian Splatting as the primary rendering primitive to reduce the Sim2Real gap for RGB-based manipulation policies. By replacing tradi- tional mesh representations with Gaussian Splats in simulators, SplatSim produces highly photorealistic synthetic data while maintaining the scalability and cost-efficiency of simulation. We demonstrate the effectiveness of our framework by training manipulation policies within SplatSim and deploying them in the real world in a zero-shot manner, achieving an average success rate of 86.25%, compared to 97.5% for policies trained on real-world data.

@misc{qureshi2024splatsimzeroshotsim2realtransfer,
      title={SplatSim: Zero-Shot Sim2Real Transfer of RGB Manipulation Policies Using Gaussian Splatting}, 
      author={Mohammad Nomaan Qureshi and Sparsh Garg and Francisco Yandun and David Held and George Kantor and Abhisesh Silwal},
      year={2024},
      eprint={2409.10161},
      archivePrefix={arXiv},
      primaryClass={cs.RO},
      url={https://arxiv.org/abs/2409.10161}, 
}