Nikhila Ravi

Papers

Total Citations

111

H-Index

About

Nikhila Ravi is a computer vision researcher whose work centers on 3D scene understanding, object detection, and the development of large-scale benchmarks that push the boundaries of what machines can perceive from a single image. Her most impactful contribution, **Omni3D**, introduced a large-scale benchmark and unified model for 3D object detection "in the wild" — addressing a critical gap in the field where existing datasets were small and methods struggled to generalize across diverse environments. This work has garnered 89 citations since its 2023 publication, reflecting its immediate significance to the robotics and AR/VR communities. Ravi also advances unsupervised 3D learning, as demonstrated in her work on inferring 3D object shape and spatial layout from 2D images without requiring 3D supervision — a practically important capability given how difficult 3D ground-truth data is to collect. Together, her research tackles fundamental scalability challenges in 3D perception, bridging the gap between richly resourced 2D recognition systems and the comparatively underdeveloped 3D domain. Her contributions make her a notable voice in efforts to bring robust, generalizable 3D understanding to real-world computer vision applications.