Max Robotics — Global Service Robot Directory + US Certification

About

Ayush Tewari is a leading researcher in computer vision and graphics, whose work bridges the gap between 2D perception and persistent 3D scene understanding. His key contributions lie in neural scene representations, novel view synthesis, and open-set 3D mapping for robotics. In his highly influential paper "Neural Groundplans" (2022, 8 citations), Tewari introduced a method to map a single 2D image to a persistent 3D scene representation, enabling disentangled modeling of movable and immovable scene components—a breakthrough for dynamic environment understanding. He further advanced the field with "ConceptFusion" (2023, 4 citations), which pioneered open-set multimodal 3D mapping, allowing robots to reason about an unbounded set of semantic concepts rather than being limited to a predefined closed set. This work has significant implications for autonomous navigation and human-robot interaction. Tewari's research is characterized by its practical impact on robotics and graphics, combining theoretical elegance with real-world applicability. His ability to create persistent, semantically rich 3D representations from limited visual input marks him as a rising star in the intersection of computer vision and embodied AI.