Hardware Acelerated Voxel Coloring

Download Report

Transcript Hardware Acelerated Voxel Coloring

Adaptive Space Carving
Anselmo A. Montenegro†, Marcelo Gattass‡ , Paulo Carvalho† and Luiz Velho†
†[anselmo,lvelho,pcezar]@visgraf.impa.br, ‡ [email protected]
Space Carving
3D object reconstruction is one of the most investigated topics
in computer graphics and vision. Among different techniques,
image based reconstruction is considered one of the most
promising as high quality digital cameras are becoming a
commodity hardware.
Adaptive Space Carving
Fixed pre-calibrated cameras setup
Adaptive space carving:
•Works on an octree representation of the scene space.
•The reconstruction is obtained by a refinement process based
on photo-consistency tests.
•Uses photometric and silhouette information in multiresolution to
detect coarse empty regions as soon as possible.
•Classification of the cells: CONSISTENT, INCONSISTENT and UNDEFINED.
•Undefined cells are subdivided and classified in later stages.
Background
estimation
Camera
calibration
Calibration by model
recongnition
Volumetric carving is a very
common technique use for
image based reconstruction. It
may use silhouette and/or
photometric
information.
Silhouette based methods
were successfully used in realtime reconstructions. This is
not the case when we consider
photometric approaches.
Algorithm
Visibility and noise maps
Still some problems:
Too much elements
Memory waste
Solution:
Hierarchical representation
of scene space
Refinement approach
Adaptive Carving
Subdivide undefined cells and
colorize photo-consistent cells.
Update visibility maps.
Last registration
plane of the level?
Process next octree refinement level
Registration based on projective texture mapping.
Photo-consitency evaluation done by GPU programming.
Process next registration plane
Solution:
Project images on the current
registration plane with resolution
compatible to the octree level
Test the consistency of the nonclassified cells intersected by
the current registration plane
Level 5
Level 6
Level7
Level 8
NO
NO
YES
Finish
Segmentation based on
intervals of confidence
Final considerations
YES
No cell
subdivided ?
Reconstruction
by Adaptive
Space Carving
Fixed cameras reconstruction results
Determine the registration
planes at the current level
Registration and evaluation of thousands of individual
elements.
Object
segmentation
Levels of refinement
Initialize the octree root cell with
the bounding box of the scene
Problems with photometric approaches:
Images and
segmentation
Image
capture
Zoom
In this work we only explored convencional GPU hardware
accelerated operations, as in the registration step by projective
texture mapping . The mechanism of copying framebuffer
information to main memory introduces significant overhead to the
overall processing time. We believe that by combining our adaptive
approach with photo-consistency test done by GPU programming
we can obtain considerable gains in efficiency.