• Publications
  • Influence
Surface Capture for Performance-Based Animation
This work investigates studio capture technology with the objective of creating models of real people that accurately reflect the time-varying shape and appearance of the whole body with clothing and solves two key problems in performance capture: scene capture from a limited number of camera views and efficient scene representation for visualization.
Total Capture: 3D Human Pose Estimation Fusing Video and Inertial Sensors
An algorithm for fusing multi-viewpoint video (MVV) with inertial measurement unit (IMU) sensor data to accurately estimate 3D human pose is presented, yielding improved accuracy over prior methods.
The i3DPost Multi-View and 3D Human Action/Interaction Database
The database has been created using a convergent eight camera setup to produce high definition multi-view videos, where each video depicts one of eight persons performing one of twelve different human motions.
Visual Analysis of Humans - Looking at People
This unique text/reference provides a coherent and comprehensive overview of all aspects of video analysis of humans and reviews the historical origins of the different existing methods, and predicts future trends and challenges.
Marching triangles: range image fusion for complex object modelling
An efficient algorithm to reconstruct a triangulated model of a manifold implicit surface, a local 3D constraint is derived which defines the Delaunay surface triangulation of a set of points on a manifold surface in 3D space.
Shape Similarity for 3D Video Sequences of People
This evaluation demonstrates that shape-flow with a multi-frame alignment of motion sequences achieves the best performance, is stable for different people and motions, and overcome the ambiguity in static shape similarity.
A FACS valid 3D dynamic action unit database with applications to 3D dynamic morphable facial modeling
The first framework for building dynamic 3D morphable models and a novel Active Appearance Model (AAM) based 3D facial registration and mesh correspondence scheme is described, which overcomes limitations in existing methods that require facial markers or are prone to optical flow drift.
Virtual people: capturing human models to populate virtual worlds
A model based approach is presented for automatic reconstruction of recognisable avatars from a set of low cost colour images of a person taken from four orthogonal views to achieve automatic low cost modelling of people suitable for personalised avatars to populate virtual worlds.
Implicit Surface-Based Geometric Fusion
This paper introduces a general purpose algorithm for reliable integration of sets of surface measurements into a single 3D model. The new algorithm constructs a single continuous implicit surface