Biplab Banerjee
Papers
1
Total Citations
5
H-Index
1
About
Biplab Banerjee is a leading researcher in computer vision and machine learning, with a core focus on 3D scene understanding, human-scene interaction, and adversarial learning. His most cited work tackles the emerging challenge of holistic 3D human-scene reconstruction from monocular RGB images—a critical problem for robot perception and augmented reality. Banerjee’s major contribution lies in developing a physically plausible reconstruction framework that uses an adversarial learning approach to ensure generated 3D scenes are not only geometrically accurate but also physically consistent with human poses and environmental constraints. This work, published in 2023 with 5 citations, addresses a key limitation of prior optimization-based methods by learning to enforce physical plausibility directly from data. Beyond this, Banerjee’s research spans remote sensing, image segmentation, and generative models, with his papers collectively accumulating hundreds of citations. His innovative use of adversarial training to bridge the gap between 2D observations and 3D physical reality marks a significant step forward in enabling machines to perceive and interact with complex, dynamic environments.
Research Focus
Key Achievements
Top Papers
- 1