Asim Unmesh

Asim Unmesh

Asim Unmesh is a PhD student in the School of Electrical and Computer Engineering. He completed his Bachelor's and Master's in Computer Science and Engineering from Indian Institute of Technology Kanpur.  He works in the area of Computer Vision and Machine Learning. Currently he is working in the area of Activity Recognition and other related tasks.
PowVRtool: a handheld haptic device for realistic power tool feedback in VR-based manufacturing training

PowVRtool: a handheld haptic device for realistic power tool feedback in VR-based manufacturing training

Mayank Patel, Asim Unmesh, Ananya Ipsita, Levi Erickson, Priyam Maheshwari, Rahul Jain, Jingyu Shi, Laura H Blumenschein, Karthik Ramani
Virtual Reality 30, 16 (2026)

In VR-based manufacturing training employing Oculus controllers for power tool operation, users consistently encounter a glaring impediment: the conspicuous absence of haptic feedback. This critical shortfall significantly hinders the seamless...

AnnotateXR: An Extended Reality Workflow for Automating Data Annotation to Support Computer Vision Applications

AnnotateXR: An Extended Reality Workflow for Automating Data Annotation to Support Computer Vision Applications

Subramanian Chidambaram*, Rahul Jain*, Sai Swarup Reddy, Asim Unmesh, Karthik Ramani
J. Comput. Inf. Sci. Eng. Dec 2024, 24(12): 121001 (13 pages)

Computer vision (CV) algorithms require large annotated datasets that are often labor-intensive and expensive to create. We propose AnnotateXR, an extended reality (XR) workflow to collect various high-fidelity data and auto-annotate it in a single...

Interacting Objects: A dataset of object-object interactions for richer dynamic scene representations

Interacting Objects: A dataset of object-object interactions for richer dynamic scene representations

Asim Unmesh, Rahul Jain, Jingyu Shi, VK Chaitanya, Hyung-Gun Chi, Subramanian Chidambaram, Alexander Quinn, Karthik Ramani
IEEE Robotics and Automation Letters, vol. 9, no. 1, pp. 451-458, Jan. 2024

Interacting Objects: A dataset of object-object interactions for richer dynamic scene representations Asim Unmesh, Rahul Jain, Jingyu Shi, V. K. Chaithanya Manam, Hyung-Gun Chi, Subramanian Chidambaram, Alexander J. Quinn, Karthik Ramani IEEE...

SurfNet: Generating 3D shape surfaces using deep residual networks

SurfNet: Generating 3D shape surfaces using deep residual networks

Sinha, A., Unmesh, A., Huang, Q., and Ramani, K
Proceedings of the IEEE conference on computer vision and pattern recognition. 2017.

  3D shape models are naturally parameterized using vertices and faces, i.e., composed of polygons forming a surface. However, current 3D learning paradigms for predictive and generative tasks using convolutional neural networks focus on a...