This article was accepted into the corpus but its outbound wikilinks were never NER-processed — typical at the deepest BFS hop or when the run's entity cap was reached. No expansion funnel to show.
| Pratul Srinivasan | |
|---|---|
| Name | Pratul Srinivasan |
| Occupation | Computer scientist, researcher, educator |
| Known for | Machine perception, computer graphics, robotics |
| Alma mater | Massachusetts Institute of Technology, Stanford University |
| Employer | Google Research, MIT CSAIL |
Pratul Srinivasan is a researcher in computer vision, computer graphics, and robotics whose work has influenced neural rendering, 3D reconstruction, and perception for autonomous systems. He has contributed to academic projects and industrial research initiatives that bridge algorithms for visual sensing with scalable systems at technology companies and research laboratories. Srinivasan's work is noted for combining techniques from photogrammetry, deep learning, and graphics to advance novel view synthesis and scene understanding.
Srinivasan was born and raised in India and completed undergraduate studies before pursuing graduate education in the United States, studying at institutions linked to major research communities. He earned advanced degrees at Massachusetts Institute of Technology and Stanford University, where he trained with advisors active in computer vision and computer graphics research groups. During graduate study he collaborated with members of research labs associated with MIT CSAIL and the SAIL, participating in seminars and workshops alongside researchers from University of California, Berkeley, Carnegie Mellon University, and University of Washington. His doctoral work connected topics from the SIGGRAPH community, the CVPR, and interdisciplinary teams that included researchers affiliated with Google Research and Microsoft Research.
Srinivasan held postdoctoral and research scientist positions in settings that combined academic publishing and product-oriented research, affiliating with labs that have produced influential papers at venues such as NeurIPS, ICCV, ECCV, and SIGGRAPH. He collaborated with faculty and researchers from institutions including Princeton University, Harvard University, and Yale University, contributing to projects on neural scene representations and light transport. His industrial roles included appointments at research groups within Google Research and partnerships with teams connected to NVIDIA Research, which placed his work at the intersection of large-scale compute infrastructure and algorithm development. Srinivasan's collaborations extended to researchers from MIT Media Lab, ETH Zurich, and University College London on cross-disciplinary problems involving perception for robotics, human-computer interaction, and graphics.
He supervised and mentored students and interns who later joined research groups at OpenAI, DeepMind, and academic departments across California Institute of Technology and University of Toronto. Srinivasan participated in grant-funded projects supported by agencies and foundations that sponsor computing research, working with investigators linked to DARPA programs, collaborative efforts with NSF centers, and partnerships involving Amazon Research initiatives.
Srinivasan's research portfolio emphasizes neural rendering techniques for novel view synthesis, neural radiance fields, and multi-view stereo, producing work that influenced both the theoretical framing and practical implementations adopted by industrial pipelines. He co-authored papers that appeared in proceedings of SIGGRAPH, NeurIPS, CVPR, and ICLR, addressing topics such as differentiable rendering, volumetric scene representations, and real-time reconstruction. His contributions include methods for improving geometry quality and view-dependent appearance modeling, integrating insights from the Rendering Equation literature and recent advances in implicit function modeling explored by groups at FAIR and Google Brain.
Srinivasan's publications often advanced techniques for compressing and accelerating neural scene representations for deployment on hardware platforms produced by NVIDIA, Intel, and Qualcomm, enabling applications in virtual production, augmented reality, and autonomous navigation. He collaborated on datasets and benchmarks that have been adopted by research teams at Stanford University, UC Berkeley, and ETH Zurich for assessing reconstruction fidelity, contributing to reproducible evaluation protocols used in follow-up work from University of Cambridge and Imperial College London researchers. His co-authored work on view synthesis and scene capture drew citations from subsequent studies at Columbia University and University of Michigan that extended neural implicit modeling to dynamic scenes and lighting variation.
Srinivasan received recognition from professional organizations and research communities for impactful publications and contributions to open-source toolkits used by practitioners. His papers received best-paper nominations and awards at conferences such as SIGGRAPH Asia and he was invited to present at workshops organized by NeurIPS and CVPR program committees. Industry accolades included internal research awards at Google and competitive fellowships associated with centers at MIT and Stanford. He was listed among early-career researcher highlights by institutions like ACM and was selected for competitive mentoring programs run by collaborations between NSF and leading laboratories.
Outside research, Srinivasan engaged with communities at academic conferences and workshops linked to SIGGRAPH, NeurIPS, and CVPR, serving on program committees and organizing tutorials that connected junior researchers from IIT Madras and IISc Bangalore with international labs. He advocated for reproducibility and data sharing practices promoted by initiatives at OpenAI, Linux Foundation, and academic consortia across Europe and North America. Srinivasan's legacy includes a body of work that influenced practices in neural rendering, scene capture, and perception systems used by teams at Pixar, Industrial Light & Magic, and consumer-product groups within Apple and Meta Platforms. His students and collaborators continue to advance topics in 3D vision at academic and industrial research centers worldwide.
Category:Computer scientists Category:Computer vision researchers Category:Machine learning researchers