← ArchivePaper2008
Articulated Mesh Animation from Multi-view Silhouettes
Reconstructs articulated character mesh animation from multi-view silhouette sequences enabling markerless performance capture.
Abstract
Details in mesh animations are difficult to generate but they have great impact on visual quality. In this work, we demonstrate a practical software system for capturing such details from multi-view video recordings. Given a stream of synchronized video images that record a human performance from multiple viewpoints and an articulated template of the performer, our system captures the motion of both the skeleton and the shape. The output mesh animation is enhanced with the details observed in the image silhouettes. For example, a performance in casual loose-fitting clothes will generate mesh animations with flowing garment motions. We accomplish this with a fast pose tracking method followed by nonrigid deformation of the template to fit the silhouettes. The entire process takes less than sixteen seconds per frame and requires no markers or texture cues. Captured meshes are in full correspondence making them readily usable for editing operations including texturing, deformation transfer, and deformation model learning.
How to read this
- Category
- Capture system: markerless articulated performance capture
- Contributions
- Reconstructs both skeleton motion and detailed surface shape from multi-view silhouette video using an articulated template
- A fast pose-tracking step followed by nonrigid template deformation to fit observed silhouettes, capturing details like flowing clothing
- Produces meshes in full correspondence, ready for texturing, deformation transfer, and deformation-model learning
- Context
- Fits in the markerless multi-view performance-capture line of work, using an articulated template plus silhouette fitting rather than markers or texture cues.
- Correctness
- Demonstrated on human performances including loose clothing with a stated per-frame processing time and no markers needed; a reader should note silhouette-only cues can be ambiguous for concavities and surface detail away from the contour, and quality depends on the template and camera coverage.
- Clarity
- Reads as a practical system paper; a first pass conveys the pipeline, a second pass clarifies the pose-tracking and nonrigid-fitting stages.
- How to read it
- Read it as a pipeline: focus on how pose tracking feeds the nonrigid silhouette fit, and what correspondence buys you downstream; one careful pass usually suffices unless you plan to reimplement the fitting.
Related work
Keywords
This page summarises the entry and links to its original source. The archive never hosts or redistributes the publication itself.Show it in the full archive list →