Curriculum Vitae

If you prefer a concise résumé, please see find it here.

Education

• PhD in Computer Vision, University of Cambridge, 2023 (expected). Funded by the ERC Grant Horizon 2020: Project Eyecode.
• B.Tech. in Information Technology, National Institute of Technology Karnataka, India, 2018.

Work experience

• Oct 2022 - Present: Research Associate at University of Cambridge
  • Supervisor: Dr Cengiz Öztireli
  • 3D generative modelling with pointclouds and/or implicit neural representations
  • Helped design and deliver L355: Machine Visual Perception
  • Supervising a year-long MPhil. and Part II project in generative modelling with diffusion methods
• Feb 2019 - Sept 2022: Research Assistant at University of Cambridge
  • Supervisor: Dr Rafał Mantiuk
  • Working to capture and render images on a novel multi-focalplane, stereoscopic, high dynamic range display. We aim to produce images that will successfully pass the Visual Turing Test.
  • Responsible for reconstructing HDR images and estimating per-view depth maps. MLE-based estimators obtained by assuming a statistical camera noise model produced the best HDR images. Preliminary results were presented at an ECCV workshop, with a more elaborate journal version currently under review.
  • Also worked on optical flow, differentiable rendering, neural view synthesis
• Sept 2020 - Feb 2021: Part-time project with Huawei Research, Munich
  • Exploring the effect of different tone-curves (encoding functions) on the performance of state-of-the-art Computer Vision methods.
  • Conducted an evaluation of state-of-the-art face and object detectors as well as optical flow with the help of a new adversarial illumination dataset. The dataset and preliminary study were accepted to be published in the Journal of Imaging Science and Technology (JIST).
• July 2018 - Jan 2019: Research Assistant at National University of Singapore
  • Supervisor: Prof. Gary Tan
  • Involved in the development of agent-based traffic simulator, at the Singapore-MIT Alliance for Research and Technology (SMART) Lab. Contributed to the first release of SimMobility.
  • Worked to improve the runtime performance of an on-demand vehicle controller that handles shared taxi requests. On average, the simulation time was reduced to a third of the original.

Publications

Perceptual Quality Assessment of NeRF and Neural View Synthesis Methods for Front-Facing Views

Hanxue Liang, Tianhao Wu, Param Hanji, Francesco Banterle, Hongyun Gao, Rafał K. Mantiuk and Cengiz Öztireli. "Perceptual Quality Assessment of NeRF and Neural View Synthesis Methods for Front-Facing Views." In Computer Graphics Forum. 2024.

Neural Fields with Hard Constraints of Arbitrary Differential Order

Fangcheng Zhong, Kyle Fogarty, Param Hanji, Tianhao Wu, Alejandro Sztrajman, Andrew Spielberg, Andrea Tagliasacchi, Petra Bosilj and Cengiz Öztireli. "Neural Fields with Hard Constraints of Arbitrary Differential Order." In Advances in Neural Information Processing Systems. 2023.

Robust estimation of exposure ratios in multi-exposure image stacks

Param Hanji and Rafał K. Mantiuk. "Robust estimation of exposure ratios in multi-exposure image stacks." In IEEE Transactions on Computational Imaging (TCI), 9, pp. 721-731, 2023.

Distilling Style from Image Pairs for Global Forward and Inverse Tone Mapping

Mustafa, Aamir, Param Hanji and Rafał K. Mantiuk. "Distilling Style from Image Pairs for Global Forward and Inverse Tone Mapping." In Proceedings of the 19th ACM SIGGRAPH European Conference on Visual Media Production (CVMP). 2022.

Comparison of single image HDR reconstruction methods — the caveats of quality assessment

Param Hanji, Rafał K. Mantiuk, Gabriel Eilertsen, Saghi Hajisharif and Jonas Unger "Comparison of single image HDR reconstruction methods — the caveats of quality assessment". In ACM SIGGRAPH 2022 Conference Proceedings (pp. 1-8). 2022.

Reproducing Reality with a High-Dynamic-Range Multi-Focal Stereo Display

Fangcheng Zhong, Akshay Jindal, Ali Özgür Yöntem, Param Hanji, Simon J. Watt and Rafał K. Mantiuk. "Reproducing Reality with a High-Dynamic-Range Multi-Focal Stereo Display". In ACM Transactions on Graphics, 40(6). 2021.

How to cheat with metrics in single-image HDR reconstruction

Gabriel Eilertsen, Saghi Hajisharif, Param Hanji , Apostolia Tsirikoglou, Rafał K. Mantiuk and Jonas Unger. "How to cheat with metrics in single-image HDR reconstruction". In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops. 2021.

HDR4CV: High dynamic range dataset with adversarial illumination for testing computer vision methods

Param Hanji, Muhammad Z. Alam, Nicola Giuliani, Hu Chen and Rafał K. Mantiuk. "HDR4CV: High dynamic range dataset with adversarial illumination for testing computer vision methods". In Journal of Imaging Science and Technology. 2021.

Noise-Aware Merging of High Dynamic Range Image Stacks without Camera Calibration

Param Hanji, Fangcheng Zhong and Rafał K. Mantiuk. "Noise-aware merging of high dynamic range image stacks without camera calibration". In Proceedings of the European Conference on Computer Vision (ECCV) Workshops, pages 376–391. Springer, 2020.

Parallel Computing for Iterative Hill Climbing Algorithm to solve TSP

Pramod Yelmewad, Param Hanji, Amogha Udupa, Parth shah and Basavaraj Talawar. "Parallel computing for iterative hill climbing algorithm to solve TSP". In Student Research Symposium (SRS), IEEE 24th High Performance Computing (HiPC). 2017.

Supervisions

Please see Teaching