Finish Hardware Accelerated Voxel Coloring Anselmo A. Montenegro †, Luiz Velho †, Paulo Carvalho † and Marcelo Gattass ‡ †

Slides:



Advertisements
Similar presentations
A Robust Super Resolution Method for Images of 3D Scenes Pablo L. Sala Department of Computer Science University of Toronto.
Advertisements

Stereo matching Class 7 Read Chapter 7 of tutorial Tsukuba dataset.
Visibility Culling. Back face culling View-frustrum culling Detail culling Occlusion culling.
Tracking Multiple Occluding People by Localizing on Multiple Scene Planes Professor :王聖智 教授 Student :周節.
MultiView Stereo Steve Seitz CSE590SS: Vision for Graphics.
Multiview Reconstruction. Why More Than 2 Views? BaselineBaseline – Too short – low accuracy – Too long – matching becomes hard.
Shape from Contours and Multiple Stereo A Hierarchical, Mesh-Based Approach Hendrik Kück, Wolfgang Heidrich, Christian Vogelgsang.
Broadcast Court-Net Sports Video Analysis Using Fast 3-D Camera Modeling Jungong Han Dirk Farin Peter H. N. IEEE CSVT 2008.
Rasterization and Ray Tracing in Real-Time Applications (Games) Andrew Graff.
Last Time Pinhole camera model, projection
1 Learning to Detect Objects in Images via a Sparse, Part-Based Representation S. Agarwal, A. Awan and D. Roth IEEE Transactions on Pattern Analysis and.
Computational Photography: Image-based Modeling Jinxiang Chai.
Introduction to Volume Rendering Presented by Zvi Devir.
CSCE 641 Computer Graphics: Image-based Modeling Jinxiang Chai.
Contents Description of the big picture Theoretical background on this work The Algorithm Examples.
Probabilistic video stabilization using Kalman filtering and mosaicking.
Direct Methods for Visual Scene Reconstruction Paper by Richard Szeliski & Sing Bing Kang Presented by Kristin Branson November 7, 2002.
1 Image-Based Visual Hulls Paper by Wojciech Matusik, Chris Buehler, Ramesh Raskar, Steven J. Gortler and Leonard McMillan [
Multiview stereo. Volumetric stereo Scene Volume V Input Images (Calibrated) Goal: Determine occupancy, “color” of points in V.
Multiple Human Objects Tracking in Crowded Scenes Yao-Te Tsai, Huang-Chia Shih, and Chung-Lin Huang Dept. of EE, NTHU International Conference on Pattern.
Vision-based Registration for AR Presented by Diem Vu Nov 20, 2003.
Multi-view stereo Many slides adapted from S. Seitz.
The plan for today Camera matrix
Automatic Camera Calibration for Image Sequences of a Football Match Flávio Szenberg (PUC-Rio) Paulo Cezar P. Carvalho (IMPA) Marcelo Gattass (PUC-Rio)
Project 1 grades out Announcements. Multiview stereo Readings S. M. Seitz and C. R. Dyer, Photorealistic Scene Reconstruction by Voxel Coloring, International.
Accurate, Dense and Robust Multi-View Stereopsis Yasutaka Furukawa and Jean Ponce Presented by Rahul Garg and Ryan Kaminsky.
Review: Binocular stereo If necessary, rectify the two stereo images to transform epipolar lines into scanlines For each pixel x in the first image Find.
Hidden Surface Removal
Research & Innovation 1 An Industry Perspective on VVG Research Oliver Grau BBC Research & Innovation VVG SUMMER SCHOOL '07.
Image-Based Visual Hulls Wojciech Matusik Chris Buehler Ramesh Raskar Steven Gortler Leonard McMillan Presentation by: Kenton McHenry.
What Does the Scene Look Like From a Scene Point? Donald Tanguay August 7, 2002 M. Irani, T. Hassner, and P. Anandan ECCV 2002.
Finish Adaptive Space Carving Anselmo A. Montenegro †, Marcelo Gattass ‡, Paulo Carvalho † and Luiz Velho † †
Prakash Chockalingam Clemson University Non-Rigid Multi-Modal Object Tracking Using Gaussian Mixture Models Committee Members Dr Stan Birchfield (chair)
Lecture 12 Stereo Reconstruction II Lecture 12 Stereo Reconstruction II Mata kuliah: T Computer Vision Tahun: 2010.
Shape-Based Human Detection and Segmentation via Hierarchical Part- Template Matching Zhe Lin, Member, IEEE Larry S. Davis, Fellow, IEEE IEEE TRANSACTIONS.
Automatic Registration of Color Images to 3D Geometry Computer Graphics International 2009 Yunzhen Li and Kok-Lim Low School of Computing National University.
Real-time object tracking using Kalman filter Siddharth Verma P.hD. Candidate Mechanical Engineering.
KinectFusion : Real-Time Dense Surface Mapping and Tracking IEEE International Symposium on Mixed and Augmented Reality 2011 Science and Technology Proceedings.
Multiscale Moment-Based Painterly Rendering Diego Nehab and Luiz Velho
Adaptive Registration of Very Large Images Brian Jackson & Ardy Goshtasby Wright State University.
High-Resolution Interactive Panoramas with MPEG-4 발표자 : 김영백 임베디드시스템연구실.
Person detection, tracking and human body analysis in multi-camera scenarios Montse Pardàs (UPC) ACV, Bilkent University, MTA-SZTAKI, Technion-ML, University.
September 5, 2013Computer Vision Lecture 2: Digital Images 1 Computer Vision A simple two-stage model of computer vision: Image processing Scene analysis.
Introduction to Computer Vision Sebastian van Delden USC Upstate
Global Parametrization of Range Image Sets Nico Pietroni, Marco Tarini, Olga Sorkine, Denis Zorin.
Towards real-time camera based logos detection Mathieu Delalandre Laboratory of Computer Science, RFAI group, Tours city, France Osaka Prefecture Partnership.
Computational Framework for Performance Characterization of 3-D Reconstruction Techniques from Sequence of Images Ahmed Eid and Aly Farag Computer Vision.
A General-Purpose Platform for 3-D Reconstruction from Sequence of Images Ahmed Eid, Sherif Rashad, and Aly Farag Computer Vision and Image Processing.
Vision-based human motion analysis: An overview Computer Vision and Image Understanding(2007)
Interactive Point-based Modeling of Complex Objects from Images Pierre Poulin (a,b) Marc Stamminger (a,c) François Duranleau (b) Marie-Claude Frasson (a)
875 Dynamic Scene Reconstruction
High Resolution Surface Reconstruction from Overlapping Multiple-Views
Robotics Chapter 6 – Machine Vision Dr. Amit Goradia.
Motion tracking TEAM D, Project 11: Laura Gui - Timisoara Calin Garboni - Timisoara Peter Horvath - Szeged Peter Kovacs - Debrecen.
Robot Vision SS 2011 Matthias Rüther / Matthias Straka 1 ROBOT VISION Lesson 7: Volumetric Object Reconstruction Matthias Straka.
Visual Information Processing. Human Perception V.S. Machine Perception  Human perception: pictorial information improvement for human interpretation.
Bounding Volume Hierarchies and Spatial Partitioning
Real-Time Soft Shadows with Adaptive Light Source Sampling
CS4670 / 5670: Computer Vision Kavita Bala Lec 27: Stereo.
Bounding Volume Hierarchies and Spatial Partitioning
SoC and FPGA Oriented High-quality Stereo Vision System
Fast and Robust Object Tracking with Adaptive Detection
A Distributed System for Real-time Volume Reconstruction
Brief Review of Recognition + Context
Parking Spot Recognition from Video Footage
Announcements Midterm due now Project 2 artifacts: vote today!
Chapter V Vertex Processing
--- Range Image Registration
Announcements Project 3 out today (help session at end of class)
Presentation transcript:

Finish Hardware Accelerated Voxel Coloring Anselmo A. Montenegro †, Luiz Velho †, Paulo Carvalho † and Marcelo Gattass ‡ † ‡ 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. Problems with photometric approaches: Registration and evaluation of thousands of individual elements. Solution: Registration based on projective texture mapping. Photo-consitency evaluation done by GPU programming. 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 real- time reconstructions. This is not the case when we consider photometric approaches. Still some problems: Too much elements Memory waste Solution: Hierarchical representation of scene space Refinement approach Adaptive Carving Background estimation Camera calibration Image capture Object segmentation Reconstruction by Adaptive Space Carving Fixed pre-calibrated cameras setup Calibration by model recongnition Adaptive space carving: Works on an octree representation of the scene space.Works on an octree representation of the scene space. The reconstruction is obtained by a refinement process based on photo-consistency tests.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.Uses photometric and silhouette information in multiresolution to detect coarse empty regions as soon as possible. Classification of the cells: CONSISTENT, INCONSISTENT and UNDEFINED.Classification of the cells: CONSISTENT, INCONSISTENT and UNDEFINED. Undefined cells are subdivided and classified in later stages.Undefined cells are subdivided and classified in later stages. Level 5 Segmentation based on intervals of confidence Adaptive Space Carving Space Carving No cell subdivided ? Last registration plane of the level? Subdivide undefined cells and colorize photo-consistent cells. Update visibility maps. Test the consistency of the non- classified cells intersected by the current registration plane Project images on the current registration plane with resolution compatible to the octree level Algorithm Levels of refinement Level 6 Level7 Level 8 Zoom Fixed cameras reconstruction results Occlusion tolerant Calibration Background estimation and segmentation K 1 Rtm 1 K 2 Rtm 2 Homography H =K 1 Rtm 1 (Rtm 2 ) -1 (K 2 ) -1 Final considerations Hand-held camera setup Problems: Calibration Background estimation Solution: Insert model in the scene Background estimation by warping images of the scene without the object Hand-held camera reconstruction results 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. =0 YES NO YES NO Process next registration plane Process next octree refinement level Determine the registration planes at the current level Initialize the octree root cell with the bounding box of the scene Segmentation problem at the pattern lines due to alignement errors (a). Solution: Solution: the interval of confidence for a pixel p(i,j) in the target image is calculated by sampling the pixels from the registered images at a neighborhood of (i,j) whose color is the closest to p(i,j) (b). wrong (a) correct(a) Registered backgrounds Input image Background image Images and segmentation Visibility and noise maps H Z=0