Early art: events. Baroque art: portraits. Renaissance art: events. Being There: Capturing and Experiencing a Sense of Place

Similar documents
High Performance Imaging Using Large Camera Arrays

Computational Photography

Introduction to Virtual Reality (based on a talk by Bill Mark)

360 HDR photography time is money! talk by Urs Krebs

Video Registration: Key Challenges. Richard Szeliski Microsoft Research

Supplementary Material of

Capturing Light. The Light Field. Grayscale Snapshot 12/1/16. P(q, f)

High Dynamic Range Photography

The Basic SLR

The Application of Virtual Reality Technology to Digital Tourism Systems

10 Tips for Shooting Autumn Foliage

Form = a solid, three-dimensional area. It s boundaries are measured using height, width, and depth.

High dynamic range imaging and tonemapping


Tonemapping and bilateral filtering

High-Resolution Interactive Panoramas with MPEG-4

Light-Field Database Creation and Depth Estimation

AP Summer Work DeLong 1. Direct Observation Object Triptych-

Fake Impressionist Paintings for Images and Video

CHAPTER 7 - HISTOGRAMS

Continuous Flash. October 1, Technical Report MSR-TR Microsoft Research Microsoft Corporation One Microsoft Way Redmond, WA 98052

Computational Photography Introduction

CS354 Computer Graphics Computational Photography. Qixing Huang April 23 th 2018

COPYRIGHTED MATERIAL

History of projection. Perspective. History of projection. Plane projection in drawing

Quad Cities Photography Club

Black and White (Monochrome) Photography

How to combine images in Photoshop

A Gentle Introduction to Bilateral Filtering and its Applications 08/10: Applications: Advanced uses of Bilateral Filters

2017 SUMMER CAMP PLAN

Why learn about photography in this course?

Travel & Landscapes. Introduction

Multi Viewpoint Panoramas

lecture 24 image capture - photography: model of image formation - image blur - camera settings (f-number, shutter speed) - exposure - camera response

Dynamically Reparameterized Light Fields & Fourier Slice Photography. Oliver Barth, 2009 Max Planck Institute Saarbrücken

SEPTEMBER 2015/SKILLS SHEET

Chapter 1 Virtual World Fundamentals

Applications of Flash and No-Flash Image Pairs in Mobile Phone Photography

High Renaissance Art Gallery. Student Name Columbia Southern University 9/20/2015

Physical Presence in Virtual Worlds using PhysX

Seniors Photography Workshop

A Gentle Introduction to Bilateral Filtering and its Applications 08/10: Applications: Advanced uses of Bilateral Filters

Achieving High Quality Mobile VR Games

CREATION AND SCENE COMPOSITION FOR HIGH-RESOLUTION PANORAMAS

Essential Elements of a Good Photograph

Light field sensing. Marc Levoy. Computer Science Department Stanford University

CSE 190: Virtual Reality Technologies LECTURE #7: VR DISPLAYS

U nde rw ater Pho to

Class 1 Children State Fair Photography Judging. Place the four photos here & size for short dimension to 2

History of projection

A collection of example photos SB-910

PHOTOGRAPHY CAMERA SETUP PAGE 1 CAMERA SETUP MODE

Autumn. Get Ready For Autumn. Technique eguide. Get Ready For

Dappled Photography: Mask Enhanced Cameras for Heterodyned Light Fields and Coded Aperture Refocusing

Focusing and Metering

The ultimate camera. Computational Photography. Creating the ultimate camera. The ultimate camera. What does it do?

Photographing Long Scenes with Multiviewpoint

Coded Exposure HDR Light-Field Video Recording

The Mixed Reality Book: A New Multimedia Reading Experience

AUGMENTED REALITY, FEATURE DETECTION Applications on camera phones. Prof. Charles Woodward, Digital Systems VTT TECHNICAL RESEARCH CENTRE OF FINLAND

Cameras. Steve Rotenberg CSE168: Rendering Algorithms UCSD, Spring 2017

Presented to you today by the Fort Collins Digital Camera Club

Intro to Digital Compositions: Week One Physical Design

Technical Specifications: tog VR

On the data compression and transmission aspects of panoramic video

History of Cartographic Landscape Representation

Real World / Virtual Presentations: Comparing Different Web-based 4D Presentation Techniques of the Built Environment

Jeff Morgan Tel: Through My Lens. ~ Available as 1 hour, 2 hour or 3 hour talk/discussion ~

Virtual Reality I. Visual Imaging in the Electronic Age. Donald P. Greenberg November 9, 2017 Lecture #21

Image stitching. Image stitching. Video summarization. Applications of image stitching. Stitching = alignment + blending. geometrical registration

Limitations of the Medium, compensation or accentuation: Contrast & Palette

Active Stereo Vision. COMP 4102A Winter 2014 Gerhard Roth Version 1

Panoramic imaging. Ixyzϕθλt. 45 degrees FOV (normal view)

Figure 1 HDR image fusion example

23270: AUGMENTED REALITY FOR NAVIGATION AND INFORMATIONAL ADAS. Sergii Bykov Technical Lead Machine Learning 12 Oct 2017

Visual Imaging in the Electronic Age An Interdisciplinary Course Bridging Art, Architecture, Computer Science, and Engineering Offered in Fall 2016

Art Journal 3 (SL) Joseph Sullivan

mastering manual week one

COURSES. Summary and Outlook. James Tompkin

Visual Art. Forms of Art - Watercolor 187 words. Forms of Art - African Sculpture 201 words. Forms of Art - Abstract Art 233 words

Capturing Realistic HDR Images. Dave Curtin Nassau County Camera Club February 24 th, 2016

Multi-perspective Panoramas. Slides from a talk by Lihi Zelnik-Manor at ICCV 07 3DRR workshop

8.2 IMAGE PROCESSING VERSUS IMAGE ANALYSIS Image processing: The collection of routines and

Computational Photography and Video. Prof. Marc Pollefeys

CSC Stereography Course I. What is Stereoscopic Photography?... 3 A. Binocular Vision Depth perception due to stereopsis

Virtual Environments. Ruth Aylett

Antialiasing and Related Issues

Perspective in Art. Yuchen Wu 07/20/17. Mathematics in the universe. Professor Hubert Bray. Duke University

Multi-perspective Panoramas. Slides from a talk by Lihi Zelnik-Manor at ICCV 07 3DRR workshop

Coded photography , , Computational Photography Fall 2018, Lecture 14

WHY YOU MUST NOT CALL YOURSELF A PHOTOGRAPHER

AP Studio Art 2-D Design Drawing Summer Preparation

Greenwich Visual Arts Objectives The History of Art (Shapers) High School

Perspective. Cornell CS4620/5620 Fall 2012 Lecture Kavita Bala 1 (with previous instructors James/Marschner)

Course: Grade One Year: 2019 Teacher: D. Remetta

Limitations of the Medium, compensation or accentuation

Limitations of the Medium, compensation or accentuation

La photographie numérique. Frank NIELSEN Lundi 7 Juin 2010

"Beasts of the Sea" Lesson: Henri Matisse Created by Art in Action

VIRTUAL REALITY FOR NONDESTRUCTIVE EVALUATION APPLICATIONS

Transcription:

Being There: Capturing and Experiencing a Sense of Place Early art: events Richard Szeliski Microsoft Research Symposium on Computational Photography and Video Lascaux Early art: events Early art: events Bayeux Tapestries Renaissance art: events Baroque art: portraits Da Vinci Rembrandt 1

Baroque art: landscapes Classical art: landscapes Rembrandt Corot Impressionism: landscapes Modern art: multi-perspective Monet Picasso Impressionism: landscapes Photography: events Monet Henri Cartier-Bresson 2

Photography: landscapes Photography: landscapes Ansel Adams Galen Rowell Photography: landscapes Interactive Visual Media Branching Games: storytelling problem solving, skill acquisition Art Wolfe sense of place, navigation Real-world immersive media Recapturing the sense of place QTVR: the first real breakthrough in modeling from reality? Fairly universal for high-end home and car sales, virtual tourism Limitations: mostly static, discrete jumps Increasing realism Better: field of view and resolution Demo: Space Needle dynamic range Additional cues/modalities: motion / movement Demo: Deception Falls sound 3

Fully automated stitch discovery VR Tools Demo Image stitching open issues HDR: merging exposures Fully automated assembly (no ordering) Full 2D stitching (multiple rows) Double image fix-up (de-ghosting) Merging different exposures Automated grouping/clustering (detection) Inputs Tonemapped output: no motion compensation or consistency check HDR: merging exposures Video Textures How can we turn a short video clip into continuous video? Enhance sense of liveness Inputs Tonemapped output: global+local motion compensation Use in games and presentations 4

Video Textures 1. Find cyclic structure in the video Animating Stills What if we only have a single beautiful photo (or painting)? 2. Play frames with random shuffle 3. Optional region-based analysis 4. Smooth over discontinuities (morph) Can we add so liveness to a photo/still? Animating Stills Increasing immersion Add continuous movement Demo Bellevue Botanical Garden Demo HDR Home Walkthrough 5

Video-based walkthroughs Add continuous movement How did we do this? Is this 3D? 2D? Graphics? Video? Limits of Video-Based Walkthroughs Video-based walkthroughs are rail experiences of a space-time slice How do we break the bounds? Can t move from side to side If there is motion in the scene, don t see it Capturing all points of view everywhere in space at all times is impractical Dimensionality and storage? A Practical 3D Video Camera 3D video Working volume? Walls of a room: Virtualized Reality 2D window : LightField Array 1D rail : Virtual Viewpoint Video Virtual Viewpoint Video Key to view interpolation: Geometry Capture multiple synchronized video streams Stereo Image 1 Image 2 Camera 1 Camera 2 Virtual Camera 6

Don t match pixels match segments Segments contain more information, so they re easier to match. Iteratively update depths Depth through time: Matting Some pixels get influence for multiple surfaces. Background Surface Foreground Surface Close up of real image: Image Camera Multiple colors and depths at boundary pixels Find matting information: Why matting is important 1. Find boundary strips using depth. 2. Within boundary strips compute the colors and depths of the foreground and background object. No Matting Matting Background Strip Width Foreground 7

Representation Rendering pipeline (GPU) Composite Render Boundary Layer Render Boundary Layer Color MAIN LAYER Depth Color Depth Render Main Layer Render Main Layer BOUNDARY LAYER Matting information Real-time viewpoint control Matrix -like effects on demand! Wrapping up (With much, much less hardware.) Light Field Rendering Sample and synthesize (capture and render) from a 4D ray space [Lightfield, Levoy & Hanrahan; Lumigraph, Gortler et al., SIGGRAPH 96] Slow Glass What if we could capture all the photons and play them all back at a later time? Light of Other Days Bob Shaw, 1969 http://www.scifi.com/scifiction/classics/classics_archive/shaw/shaw1.htm 8

Slow Glass One could stand the glass beside, say, a woodland lake until the scene emerged, perhaps a year later. If the glass was then removed and installed in a dismal city flat, the flat would for that year appear to overlook the woodland lake. During the year it wouldn't be merely a very realistic but still picture the water would ripple in sunlight, silent animals would come to drink, birds would cross the sky, night would follow day, season would follow season. Apart from its stupendous novelty value, the commercial success of slow glass was founded on the fact that having a scenedow was the exact emotional equivalent of owning land. The meanest cave dweller could look out on misty parks and who was to say they weren't his? A man who really owns tailored gardens and estates doesn't spend his time proving his ownership by crawling on his ground, feeling, smelling, tasting it. All he receives from the land are light patterns Being There Artists (and all of us) have always wanted to capture a sense of being there. Computational photography and video bring us a lot closer: realism (field of view, resolution, contrast) movement and sound immersion and exploration What does the future hold? 9