Richard Newcombe

9

Papers

59

Total Citations

Papers (9)

Sonata: Self-Supervised Learning of Reliable Point Representations

EgoLM: Multi-Modal Language Model of Egocentric Motions

LIRM: Large Inverse Rendering Model for Progressive Reconstruction of Shape, Materials and View-dependent Radiance Fields

Segment This Thing: Foveated Tokenization for Efficient Point-Prompted Segmentation

Digital Twin Catalog: A Large-Scale Photorealistic 3D Object Digital Twin Dataset

HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videos

Human-in-the-Loop Local Corrections of 3D Scene Layouts via Infilling

Benchmarking Egocentric Visual-Inertial SLAM at City Scale

Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives