Xiaoguang Han Department of Computer Science Probation talk – 2015.05.27 3D Human Reconstruction from Sparse Uncalibrated Views.

Slides:



Advertisements
Similar presentations
Coherent Laplacian 3D protrusion segmentation Oxford Brookes Vision Group Queen Mary, University of London, 11/12/2009 Fabio Cuzzolin.
Advertisements

1 Photometric Stereo Reconstruction Dr. Maria E. Angelopoulou.
Active Shape Models Suppose we have a statistical shape model –Trained from sets of examples How do we use it to interpret new images? Use an “Active Shape.
The fundamental matrix F
L1 sparse reconstruction of sharp point set surfaces
For Internal Use Only. © CT T IN EM. All rights reserved. 3D Reconstruction Using Aerial Images A Dense Structure from Motion pipeline Ramakrishna Vedantam.
Face Alignment with Part-Based Modeling
MASKS © 2004 Invitation to 3D vision Lecture 7 Step-by-Step Model Buidling.
Temporally Coherent Completion of Dynamic Shapes Hao Li, Linjie Luo, Daniel Vlasic, Pieter Peers, Jovan Popović, Mark Pauly, Szymon Rusinkiewicz ACM Transactions.
Proportion Priors for Image Sequence Segmentation Claudia Nieuwenhuis, etc. ICCV 2013 Oral.
Shape-from-X Class 11 Some slides from Shree Nayar. others.
PARAMETRIC RESHAPING OF HUMAN BODIES IN IMAGES SIGGRAPH 2010 Shizhe Zhou Hongbo Fu Ligang Liu Daniel Cohen-Or Xiaoguang Han.
Camera calibration and epipolar geometry
Shape from Contours and Multiple Stereo A Hierarchical, Mesh-Based Approach Hendrik Kück, Wolfgang Heidrich, Christian Vogelgsang.
Silhouettes in Multiview Stereo Ian Simon. Multiview Stereo Problem Input: – a collection of images of a rigid object (or scene) – camera parameters for.
Human Body Shape Estimation from Single Image Moin Nabi Computer Vision Lab. ©IPM - Dec
GATE D Object Representations (GATE-540) Dr.Çağatay ÜNDEĞER Instructor Middle East Technical University, GameTechnologies & General Manager SimBT.
Copyright  Philipp Slusallek Cs fall IBR: Model-based Methods Philipp Slusallek.
Real-time Embedded Face Recognition for Smart Home Fei Zuo, Student Member, IEEE, Peter H. N. de With, Senior Member, IEEE.
A Study of Approaches for Object Recognition
Direct Methods for Visual Scene Reconstruction Paper by Richard Szeliski & Sing Bing Kang Presented by Kristin Branson November 7, 2002.
Multi-view stereo Many slides adapted from S. Seitz.
High-Quality Video View Interpolation
Lecture 11: Structure from motion CS6670: Computer Vision Noah Snavely.
Lecture 22: Structure from motion CS6670: Computer Vision Noah Snavely.
Image-Based Rendering using Hardware Accelerated Dynamic Textures Keith Yerex Dana Cobzas Martin Jagersand.
Multi-camera Tracking of Articulated Human Motion using Motion and Shape Cues Aravind Sundaresan and Rama Chellappa Center for Automation Research University.
Quan Yu State Key Lab of CAD&CG Zhejiang University
Convergence of vision and graphics Jitendra Malik University of California at Berkeley Jitendra Malik University of California at Berkeley.
CSCE 641 Computer Graphics: Image-based Modeling (Cont.) Jinxiang Chai.
Accurate, Dense and Robust Multi-View Stereopsis Yasutaka Furukawa and Jean Ponce Presented by Rahul Garg and Ryan Kaminsky.
David Luebke Modeling and Rendering Architecture from Photographs A hybrid geometry- and image-based approach Debevec, Taylor, and Malik SIGGRAPH.
Multi-view geometry. Multi-view geometry problems Structure: Given projections of the same 3D point in two or more images, compute the 3D coordinates.
Computer Vision Spring ,-685 Instructor: S. Narasimhan WH 5409 T-R 10:30am – 11:50am Lecture #15.
My Research Experience Cheng Qian. Outline 3D Reconstruction Based on Range Images Color Engineering Thermal Image Restoration.
DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING Automatic Posing of a Meshed Human Model Using Point Clouds Lei Wang Joint work with Tamal K. Dey, Huamin.
Structure from images. Calibration Review: Pinhole Camera.
Online Tracking of Outdoor Lighting Variations for Augmented Reality with Moving Cameras Yanli Liu 1,2 and Xavier Granier 2,3,4 1: College of Computer.
Automatic Registration of Color Images to 3D Geometry Computer Graphics International 2009 Yunzhen Li and Kok-Lim Low School of Computing National University.
Lighting-up geometry: accurate 3D modelling with a torch and a camera George Vogiatzis, Carlos Hernández, Roberto Cipolla University of Cambridge, Toshiba.
COLLEGE OF ENGINEERING UNIVERSITY OF PORTO COMPUTER GRAPHICS AND INTERFACES / GRAPHICS SYSTEMS JGB / AAS 1 Shading (Shading) & Smooth Shading Graphics.
ALIGNMENT OF 3D ARTICULATE SHAPES. Articulated registration Input: Two or more 3d point clouds (possibly with connectivity information) of an articulated.
Image-based Plant Modeling Zeng Lanling Mar 19, 2008.
Geometric Modeling using Polygonal Meshes Lecture 1: Introduction Hamid Laga Office: South.
Y. Moses 11 Combining Photometric and Geometric Constraints Yael Moses IDC, Herzliya Joint work with Ilan Shimshoni and Michael Lindenbaum, the Technion.
A Non-local Cost Aggregation Method for Stereo Matching
CSCE 643 Computer Vision: Structure from Motion
Presented by Matthew Cook INFO410 & INFO350 S INFORMATION SCIENCE Paper Discussion: Dynamic 3D Avatar Creation from Hand-held Video Input Paper Discussion:
Vision-based human motion analysis: An overview Computer Vision and Image Understanding(2007)
Andrew Nealen / Olga Sorkine / Mark Alexa / Daniel Cohen-Or SoHyeon Jeong 2007/03/02.
Peter Henry1, Michael Krainin1, Evan Herbst1,
Temporally Coherent Completion of Dynamic Shapes AUTHORS:HAO LI,LINJIE LUO,DANIEL VLASIC PIETER PEERS,JOVAN POPOVIC,MARK PAULY,SZYMON RUSINKIEWICZ Presenter:Zoomin(Zhuming)
COS429 Computer Vision =++ Assignment 4 Cloning Yourself.
1Ellen L. Walker 3D Vision Why? The world is 3D Not all useful information is readily available in 2D Why so hard? “Inverse problem”: one image = many.
Affine Registration in R m 5. The matching function allows to define tentative correspondences and a RANSAC-like algorithm can be used to estimate the.
DISCRIMINATIVELY TRAINED DENSE SURFACE NORMAL ESTIMATION ANDREW SHARP.
Announcements Final is Thursday, March 18, 10:30-12:20 –MGH 287 Sample final out today.
1 Review and Summary We have covered a LOT of material, spending more time and more detail on 2D image segmentation and analysis, but hopefully giving.
Presented by 翁丞世  View Interpolation  Layered Depth Images  Light Fields and Lumigraphs  Environment Mattes  Video-Based.
Intrinsic images and shape refinement
Real Time Dense 3D Reconstructions: KinectFusion (2011) and Fusion4D (2016) Eleanor Tursman.
Nonparametric Semantic Segmentation
Removing Highlight Spots in Visual Hull Rendering
Real-Time Human Pose Recognition in Parts from Single Depth Image
Merle Norman Cosmetics, Los Angeles
Mesh Parameterization: Theory and Practice
Image processing and computer vision
Filtering Things to take away from this lecture An image as a function
Filtering An image as a function Digital vs. continuous images
Artistic Rendering Final Project Initial Proposal
Presentation transcript:

Xiaoguang Han Department of Computer Science Probation talk – D Human Reconstruction from Sparse Uncalibrated Views

3D human reconstruction Create high-quality 3D human model from easy-captured data Applications: 3D self-portraits, computer games, virtual reality etc.

Existing methods – Kinect based Key problem – point cloud registration Weaknesses of the method - require complicated capturing steps - or generate low-quality results - limited to indoor environment [Siggraph Asia 2013] [TVCG 2012]

Existing methods – Multi-view stereo Weakness - require fully calibrated cameras

Existing methods – 123D catch Input uncalibrated images Calibrating cameras and then MVS - SFM from feature correspondences Weaknesses - around 40 images for half body - should have textured area - usually fails - low-quality results

The Goal in this paper Using sparse uncalibrated images to create high-quality mesh - around 15 casual images are enough - reconstruct geometric details: winkles

Approach overview Coarse model generation - dense feature correspondences - structure-from-motion : generate point cloud - template-based model fitting : point cloud and visual hull Model refinement - density-based pixel clustering - shading information extraction - geometry optimization using shading cues

Dense correspondences Traditional feature correspondences ( DOG, SIFT, ASIFT etc. ) - sparse views  sparse feature points  SFM failed Non-rigid dense correspondence ( Siggraph 2011 )

Point cloud reconstruction Match-Propagate-Filter - NRDC for each adjacent images - propagate image by image - consistency of correspondences Structure-from-motion - estimating cameras and rough point cloud - filtering the point cloud Edge-preserving resampling

Mesh initialization Labeling 2D skeletons 3D pose reconstruction - via structure-from-motion Skeleton-based mesh deformation - linear blending skinning

Template-based model fitting Objective: 2D silhouettes (visual hull) and point cloud Variable: Mesh and silhouettes (inaccurate camera estimation) Optimization: Laplacian mesh deformation

Shape from shading Rendering Inverse rendering - recover L and n from the observed image Geometry optimization ( CVPR 2011 ) - variable: the displacements of vertices along normal - formulate the Lighting as spherical harmonics - non-linear optimization

Our geometry refinement Input: coarse model and shading images Optimization - data term: shading constraint - smoothness term: preserve the smoothness of the mesh

Challenges for shading extraction Intrinsic image - image decomposition: reflectance (albedo) and shading Challenge - varying shading Clustering based methods - group pixels into several clusters - view each cluster with constant albedo

Density-based clustering

Density-based pixel clustering Construct nearly fully connected graph Extract minimum spanning tree (MST) Each point forms one cluster Visit the edge of MST in an increasing order - weight of edge is defined as distance - pseudo-merge/absorb/merge Obtain the most stable clustering

Shading extraction Clustering for all input images Global lighting estimation - pick the biggest cluster - using its mean color as the reflectance and obtain the shading - estimate the global lighting from shading and rough normal Calculate reflectance for other clusters - shading calculation with the lighting and rough geometry - using the average reflectance as the desired one for each cluster

Shading results K-meansOur

Experimental results “boy 1” – 15 images, “boy 2” – 16 images, “girl 1” – 16 images, “girl 2” – 13 images, “man” – 15 images

Comparison Our vs PMVS ( TPAMI2010 ) vs PCMVS ( TVCG2010 )

How many input images we need? Around 15 uniformly sampled views are recommended 8 images12 images16 images

How many labeled images we need? The number of labeled images will not influence results At least 3 labeled images are enough 3 labeled images6 labeled images