Home | Spectrum Lab

Short CourseModule IV: Inverse Problems in Empirical ModelingJanuary 20, 2026

The Spectrum Lab is a research group led by Prof. Chandra Sekhar Seelamantula in the Department of Electrical Engineering at the Indian Institute of Science. The lab focuses on problems in the intersection of computational imaging and machine learning.

Spectrum Lab, 2024.

Lab Director

Chandra Sekhar Seelamantula is a Professor in the Department of Electrical Engineering at the Indian Institute of Science (IISc), Bangalore. He received his Bachelor of Engineering degree with Prof. K. K. Nair Gold Medal from Osmania University in 1999 and Ph.D. from IISc in 2005.

After completing postdoctoral research at EPFL, Switzerland (2006–2009), he joined IISc as faculty in 2009 and now leads the Spectrum Lab. His research interests include signal processing, machine learning, Generative AI, computational imaging, and AI for Healthcare.

He has served in various editorial roles including Senior Area Editor for IEEE Signal Processing Letters and Associate Editor for IEEE Transactions on Image Processing. He is a recipient of multiple awards including the Grand Challenges Exploration Award from Gates Foundation and the Qualcomm Innovation Fellowship.

Read Full Profile →

News

Jan 18, 2026 Paper Accepted

Our paper entitled “Event-driven Neuromorphic Near-Field Radar Imaging,” has been accepted for presentation at IEEE ICASSP 2026! See you in Barcelona!
Jan 18, 2026 Paper Accepted

Our paper entitled “Sparse recovery using tight frames and minimax concave penalty,” has been accepted for presentation at IEEE ICASSP 2026! See you in Barcelona!
Jan 13, 2026 Paper Accepted

Our paper titled “Visualization Guided Retinal Fluid Segmentation of Optical Coherence Tomography B-Scans” by Saptarshi Mandal, Oindrila Haldar, Chandra Sekhar Seelamantula, and Raghu Prasad has been accepted for presentation at the IEEE International Symposium on Biomedical Imaging (ISBI) 2026.

Recent Publications

SIGGRAPH Asia 25
SplineSplat: Representing Radiance Fields Using B-Splines

N. G. Thomas, and C. S. Seelamantula

In Proceedings of the SIGGRAPH Asia 2025 Technical Communications, , 2025

Abs DOI BIB URL

3D Gaussian Splatting (3DGS) has revolutionized novel view synthesis by offering excellent visual quality, real-time rendering and faster training. However, the infinite support and inherent smoothness of Gaussian kernels limit their ability to reconstruct fine geometric details and high-frequency texture, while also introducing domain-clipping artifacts near scene boundaries. We introduce SplineSplat, a novel approach that replaces Gaussian kernels with compactly supported and scalable polynomial B-spline bases, specifically, linear, quadratic, and cubic splines. B-Splines offer improved spatial localization, greater representational flexibility, and efficient evaluation through piecewise-polynomial definitions. We utilize fast spline computation strategies that enable significant training acceleration without sacrificing rendering quality or speed. Evaluations on the Mip-NeRF 360 static dataset and NVIDIA dynamic dataset demonstrate that SplineSplat matches the reconstruction fidelity of 3DGS while reducing training time by up to 18%, making it an effective kernel for high-performance radiance-field representations.
@inproceedings{10.1145/3757376.3771418, address = {New York, NY, USA}, articleno = {18}, author = {Thomas, N. G. and Seelamantula, C. S.}, booktitle = {Proceedings of the SIGGRAPH Asia 2025 Technical Communications}, doi = {10.1145/3757376.3771418}, isbn = {9798400721366}, location = { }, numpages = {4}, publisher = {Association for Computing Machinery}, series = {SA Technical Communications '25}, title = {{SplineSplat}: {R}epresenting Radiance Fields Using {B}-Splines}, url = {https://doi.org/10.1145/3757376.3771418}, year = {2025} }

SIIMS 25

LURE: An Unsupervised Denoising Framework for Multiplicative Lognormal Noise

M. Bakshi, G. Venkat, N. Bisen, C. S. Seelamantula, and T. Blu

SIAM Journal on Imaging Sciences, 2025

BIB URL

@article{bakshi2025lure,
  author = {Bakshi, M. and Venkat, G. and Bisen, N. and Seelamantula, C. S. and Blu, T.},
  journal = {SIAM Journal on Imaging Sciences},
  number = {4},
  pages = {2580--2604},
  publisher = {SIAM},
  title = {LURE: An Unsupervised Denoising Framework for Multiplicative Lognormal Noise},
  url = {https://epubs.siam.org/doi/full/10.1137/24M1700508},
  volume = {18},
  year = {2025}
}

IEEE ICIP 25

Deep Unsupervised Despeckling With Unbiased Risk Estimation

A. Gupta, C. S. Seelamantula, T. Blu, N. Dube, and S. Raman

In IEEE International Conference on Image Processing (ICIP), 2025

DOI BIB URL

@inproceedings{gupta2025deep,
  author = {Gupta, A. and Seelamantula, C. S. and Blu, T. and Dube, N. and Raman, S.},
  booktitle = {IEEE International Conference on Image Processing (ICIP)},
  doi = {10.1109/ICIP55913.2025.11084619},
  number = {},
  pages = {893-898},
  title = {Deep Unsupervised Despeckling With Unbiased Risk Estimation},
  url = {https://ieeexplore.ieee.org/document/11084619},
  volume = {},
  year = {2025}
}

ICASSP 25

Neuromorphic Unlimited Sampling for High-Dynamic-Range Video Acquisition

A. J. Kamath, and C. S. Seelamantula

In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025

Article BIB URL

@inproceedings{kamath2025neuromorphic,
  article_page = {/articles/neuromorphic-unlimited-sampling/},
  author = {Kamath, A. J. and Seelamantula, C. S.},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  title = {Neuromorphic Unlimited Sampling for High-Dynamic-Range Video Acquisition},
  url = {https://scholar.google.com/citations?view_op=view_citation&hl=en&user=1g1i1B4AAAAJ&cstart=200&pagesize=100&citation_for_view=1g1i1B4AAAAJ:BJbdYPG6LGMC},
  year = {2025}
}

ICASSP 25

Diffusion Model Based Image Reconstruction in Lensless Imaging

A. Verma, V. Boominathan, A. Veeraraghavan, and C. S. Seelamantula

In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025

BIB URL

@inproceedings{verma2025diffusion,
  author = {Verma, A. and Boominathan, V. and Veeraraghavan, A. and Seelamantula, C. S.},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  title = {Diffusion Model Based Image Reconstruction in Lensless Imaging},
  url = {https://scholar.google.com/citations?view_op=view_citation&hl=en&user=1g1i1B4AAAAJ&cstart=200&pagesize=100&citation_for_view=1g1i1B4AAAAJ:vDZJ-YLwNdEC},
  year = {2025}
}

ICASSP 25

Monte Carlo Score Matching for Image Generation

N. Shetty, and C. S. Seelamantula

In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025

BIB URL

@inproceedings{shetty2025monte,
  author = {Shetty, N. and Seelamantula, C. S.},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  title = {Monte Carlo Score Matching for Image Generation},
  url = {https://scholar.google.com/citations?view_op=view_citation&hl=en&user=1g1i1B4AAAAJ&cstart=200&pagesize=100&citation_for_view=1g1i1B4AAAAJ:tH6gc1N1XXoC},
  year = {2025}
}

Lab Director

Chandra Sekhar Seelamantula

News

Recent Publications

Funding