Hi...
I am a Ph.D. candidate at the University of Toronto with Prof. Roman Genov and Prof. Kyros Kutlakos.
I received my bachelor’s and master’s degrees from the Indian Institute of Technology Madras in 2017 with Prof. Nagendra Krishnapura.
At Toronto Computational Imaging Group, I work on designing coded-exposure image sensors and camera systems.
The coded-exposure cameras interrogate scene and enable machine-vision applications such as single-shot 3D imaging that would not be easily possible with conventional cameras.
During my research journey, I have had the opportunity to dive deep into various aspects of sensor and camera design, including mixed-signal integrated circuit design, pixel design, PCB firmware, and software development. With every new challenge, I discover new possibilities and am excited to see where my research will take me next.
Publications
Main Contributions
Rahul Gulve, Roberto Rangel, Ayandev Berman, Don Nguyen, Mian Wei, Motasem A Sakr, Xiaonong Sun, David B. Lindell, Kiriakos N Kutulakos and Roman Genov. “Dual-Port CMOS Image Sensor with Regression-Based HDR Flux-to-Digital Conversion and 80ns Rapid-Update Pixel-Wise Exposure Coding,” In 2023 IEEE International Solid-State Circuits Conference-(ISSCC).
Mian Wei*, Sotiris Nousias*, Rahul Gulve , David B. Lindell, Kiriakos N. Kutulakos
* Joint first authors.
ICCV 2023, Marr Prize (best paper award)
Rahul Gulve*, Navid Sarhangnejad*, Gairik Dutta, Motasem Sakr, Don Nguyen, Roberto Rangel, Wenzheng Chen, Zhengfan Xia, Mian Wei, Nikita Gusev, Esther Y. H. Lin, Xiaonong Sun, Leo Hanxu, Nikola Katic, Ameer Abdelhadi, Andreas Moshovos, Kiriakos N. Kutulakos and Roman Genov. “A 39,000 Subexposures/s CMOS Image Sensor with Dual-tap Coded-exposure Data-memory Pixel for Adaptive Single-shot Computational Imaging.” In 2022 IEEE Symposium on VLSI Technology and Circuits (VLSI Technology and Circuits), pp. 78-79. IEEE, 2022. https://doi.org/10.1109/VLSITechnologyandCir46769.2022.9830315
Roman Genov, Kiriakos Kutulakos, Navid Sarhangnejad, Rahul Gulve, and K. E. Hui. “Method and system for extending image dynamic range using per-pixel coding of pixel parameters.” U.S. Patent Application 17/606,969, filed July 28, 2022.
https://patents.google.com/patent/WO2020252592A1/en
R. Rangel, N. Sarhangnejad, M. Wei, R. Gulve, A. Barman, G. Dutta, Z. Xia, N. Gusev, N. Katic, H. Haim, K. N. Kutulakos, and R. Genov, “Flexible Spectrally-Scanning Snapshot Multispectral Imaging On Dual-Tap Coded-Exposure-Pixel CMOS Image Sensors,” in International Image Sensor Workshop, 2023.
Huifeng Ke, Navid Sarhangnejad, Rahul Gulve, Zhengfan Xia, Nikita Gusev, Nikola Katic, Kiriakos N. Kutulakos, and Roman Genov, “Extending Image Sensor Dynamic Range by Scene-aware Pixelwise-adaptive Coded Exposure,” In Proc. Int. Image Sensor Workshop. 2019.
https://www.imagesensors.org/Past%20Workshops/2019%20Workshop/2019%20Papers/P17.pdf
Wenzheng Chen*, Parsa Mirdehghan*, Rahul Gulve, Sanja Fidler, Roman Genov, and Kiriakos N. Kutulakos, “Auto-Tuning Structured Light for Coded Two-Bucket Cameras by Optical Stochastic Gradient Descent,” Poster and Demo at IEEE International Conference on Computational Photography, ICCP 2021
Others
Yuqi Li, Miao Qi, Rahul Gulve, Mian Wei, Roman Genov, Kiriakos N. Kutulakos, and Wolfgang Heidrich. “End-to-end video compressive sensing using anderson-accelerated unrolled networks,” In 2020 IEEE International Conference on Computational Photography (ICCP), pp. 1-12. IEEE, 2020.
https://doi.org/10.1109/ICCP48838.2020.9105237
[JSSC 19] Navid Sarhangnejad, Nikola Katic, Zhengfan Xia, Mian Wei, Nikita Gusev, Gairik Dutta, Rahul Gulve, Peter Li, Hui Ke, Harel Haim, Manuel Garcia, David Stoppa, Kiriakos Kutulakos and Roman Genov, “Dual-tap computational photography image sensor with per-pixel pipelined digital memory for intra-frame coded multi-exposure,” IEEE Journal of Solid-State Circuits 54, no. 11 (2019): 3191-3202. https://doi.org/10.1109/JSSC.2019.2932623
[ISSCC 19] Navid Sarhangnejad, Nikola Katic, Zhengfan Xia, Mian Wei, Nikita Gusev, Gairik Dutta, Rahul Gulve, Harel Haim, Manuel Garcia, David Stoppa, Kiriakos Kutulakos and Roman Genov. “5.5 dual-tap pipelined-code-memory coded-exposure-pixel cmos image sensor for multi-exposure single-frame computational imaging.” In 2019 IEEE International Solid-State Circuits Conference-(ISSCC), pp. 102-104. IEEE, 2019. https://doi.org/10.1109/ISSCC.2019.8662326
Published Projects
[Coming soon] RFDC: Regression Based Flux-to-Digital-Conversion
This work introduces new method to digitize the pixel value at wide dynamic range using regression-based approach.
39kHz Adaptive Coded-Exposure for HDR and 3D Imaging
This work showcases the fastest and adaptive per-pixel coded-exposure sensor with readout using two ADCs.
The HDR imaging uses the fast adaptive coding to boost the dynamic range of the sensor by 54 dB to image at maximum dynamic range of 101dB.
Burst Imaging from a Single-Shot Coded Exposure
The optimal exposure codes are designed to encode the high-speed temporal information of the scene in single exposure.
This work provides end-to-end solution to for compressive sensing applications
Inter-Frame Adaptive HDR
The first generation of coded-exposure cameras feature conventional readout with coded-exposure pixels.
This paper shows the method to capture HDR image with coded-exposure cameras and updating codes after every frame.