Apurva Swarnakar

Papers

Total Citations

217

H-Index

About

Apurva Swarnakar has established themselves as a notable researcher in the domain of underwater computer vision and image processing, with a particular focus on developing efficient deep learning solutions for challenging visual environments. Their most recognized contribution, "Shallow-UWnet," introduced a compressed neural network model designed specifically for underwater image enhancement — a critical challenge in fields such as underwater robotics and ocean engineering. By moving beyond computationally expensive deep CNNs and GANs, Swarnakar's work prioritized model efficiency without sacrificing enhancement quality, making it especially relevant for resource-constrained deployment scenarios. The paper, presented as a Student Abstract in 2021, has garnered an impressive 192 citations, reflecting its significant impact on the research community and its timely address of a practical bottleneck in the field. The accompanying full-length version further consolidates these contributions with 25 additional citations. What makes Swarnakar's work particularly noteworthy is achieving substantial research recognition at the student level, signaling a promising early-career trajectory. Their research bridges the gap between theoretical deep learning advances and practical, deployable solutions in marine and robotics applications, making them a compelling voice in lightweight computer vision research.