GeezerVison

I am a postdoc at Stanford University, where I work on computer graphics and vision. I did my PhD at UC San Diego with Ravi Ramamoorthi and Manmohan Chandraker. Before that, I was at IIIT Hyderabad studying computer vision and computational photography. I have spent time at Microsoft Research, Adobe Research, Meta Reality Labs and Google.

Email: [email protected]

Video Numerical Continuation for Differentiable Inverse Rendering
Haolin Lu, Ishit Mehta, Haodong Li, Yu Fu, Tzu-Mao Li, Ravi Ramamoorthi
SIGGRAPH Asia 2026
[Project] [Paper] [Code]

Distance Marching for Generative Modeling
Zimo Wang, Ishit Mehta, Haolin Lu, Chung-En Sun, Ge Yan, Tsui-Wei Weng, Tzu-Mao Li
NeurIPS 2026
[Paper]

Material Apprentice: Reflecting Process Expertise in Procedural Material Generation
Kunal Gupta, Gaurav Joshi, Yen-Ru Chen, Seemandhar Jain, Ishit Mehta, Manmohan Chandraker
ECCV 2026
[Project] [Paper] [BibTex] [Code]

INTERIORAGENT: LLM Agent for Interior Design aware 3D Layout Generation
Kunal Gupta, Ishit Mehta, Kun Wang, Nicholas Chua, Abhimanyu Krishna, Yan Deng, Ravi Ramamoorthi, Manmohan Chandraker
3DV 2026
[Paper] [BibTex]

Automatic Sampling for Discontinuities in Differentiable Shaders
Yash Belhe, Ishit Mehta, Wesley Chang, Iliyan Georgiev, Michaël Gharbi, Ravi Ramamoorthi, Tzu-Mao Li
ACM Transactions on Graphics (SIGGRAPH Asia) 2025
[Project] [Paper] [BibTex] [Code]
[Best Paper]

Spectral Prefiltering of Neural Fields
Mustafa B. Yaldiz, Ishit Mehta, Nithin Raghavan, Andreas Meuleman, Tzu-Mao Li, Ravi Ramamoorthi
SIGGRAPH Asia 2025
[Project] [Paper] [BibTex]

Locally Orderless Images for Optimization in Differentiable Rendering
Ishit Mehta, Manmohan Chandraker, Ravi Ramamoorthi
CVPR 2025 (Highlight)
[Project] [Paper] [BibTex] [Code]

A Theory of Topological Derivatives for Inverse Rendering of Geometry
Ishit Mehta, Manmohan Chandraker, Ravi Ramamoorthi
ICCV 2023
[Project] [Paper] [BibTex]

A Level Set Theory for Neural Implicit Evolution under Explicit Flows
Ishit Mehta, Manmohan Chandraker, Ravi Ramamoorthi
ECCV 2022 (Oral)
[Project] [Paper] [BibTex] [Code]
[Best Paper Honorable Mention: Top 3 from ~6000 Papers]

Modulated Periodic Activations for Generalizable Local Functional Representations
Ishit Mehta, Michaël Gharbi, Connelly Barnes, Eli Shechtman, Ravi Ramamoorthi, Manmohan Chandraker
ICCV 2021
[Project] [Paper] [BibTex] [Code]

Smartphone-based Driver License testing: Demo Abstract
Anurag Ghosh, Vijay Lingam, Ishit Mehta, Akshay Uttama Nambi, Venkata N Padmanabhan, Satish Sangameswaran
SenSys 2019
[Paper]

ALT: Towards Automating Driver License Testing Using Smartphones
Akshay Uttama Nambi, Ishit Mehta, Anurag Ghosh, Vijay Lingam, Venkata N Padmanabhan
SenSys 2019
[Paper]

Defocus Magnification using Conditional Adversarial Networks
Parikshit Sakurikar, Ishit Mehta, PJ Narayanan
WACV 2019
[Paper]

Hams: Driver and Driving Monitoring using a Smartphone
Akshay Uttama Nambi, Shruthi Bannur, Ishit Mehta, Harshvardhan Kalra, Aditya Virmani, Venkata N Padmanabhan, Ravi Bhandari, Bhaskaran Raman
MobiCom 2018
[Paper]

Structured Adversarial Training for Unsupervised Monocular Depth Estimation
Ishit Mehta, Parikshit Sakurikar, PJ Narayanan
3DV 2018
[Paper]

RefocusGAN: Scene Refocusing using a Single Image
Parikshit Sakurikar, Ishit Mehta, Vineeth N Balasubramanian, PJ Narayanan
ECCV 2018
[Paper]

Beyond Ocrs for Document Blur Estimation
Pranjal Kumar Rai, Sajal Maheshwari, Ishit Mehta, Parikshit Sakurikar, Vineet Gandhi
ICDAR 2017
[Paper]

SynCam: Capturing Sub-Frame Synchronous Media using Smartphones
Ishit Mehta, Parikshit Sakurikar, Rajvi Shah, PJ Narayanan
ICME (Oral) 2017
[Paper]