Richard P. Tucker

Google (United States), Google DeepMind (United Kingdom)

Papers

Total Citations

H-Index

About

Richard P. Tucker is a rising researcher in computer vision and 3D scene understanding, with a focus on synthesizing immersive indoor environments and modeling dynamic motion. His most cited work, "Simple and Effective Synthesis of Indoor 3D Scenes" (2023, 19 citations), introduces a method for generating high-resolution, 3D-consistent images and videos from just one or a few input images, enabling novel viewpoint extrapolation far beyond the original view. This contribution addresses a critical challenge in virtual reality and scene reconstruction. Building on this, his 2025 paper "Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos" (6 citations) tackles the difficult problem of recovering 3D motion from dynamic scenes, leveraging large-scale internet video data to train models without direct supervision. This work has implications for robotics and autonomous systems. Tucker’s research consistently pushes the boundaries of 3D synthesis and motion estimation, and his growing citation record reflects the community’s interest in scalable, practical solutions for immersive 3D content creation.