First-person Hyperlapse Videos Johannes Kopf 2014-08-10 | We present a method for converting first-person videos, for example, captured with a helmet camera during activities such as rock climbing or bicycling, into hyperlapse videos: time-lapse videos with a smoothly moving camera.For a more technical explanation of our system watch this video:http://www.youtube.com/watch?v=sA4Za3Hv6ngDownload Hyperlapse for Android, Windows Phone and Windows Desktop here:http://aka.ms/hyperlapse
Space-Time Neural Irradiance Fields for Free-Viewpoint Video Johannes Kopf 2020-11-26 | Fresh off arxiv, our latest paper on *free-viewpoint video* from a single cell phone input video.Paper: arxiv.org/abs/2011.12950Project page: video-nerf.github.io
[SIGGRAPH Talk] One Shot 3D Photography Johannes Kopf 2020-09-01 | This is the presentation I gave at the virtual SIGGRAPH 2020 about our paper "One Shot 3D Photography".Video: youtube.com/watch?v=dR_NGkHS7rUProject page: facebookresearch.github.io/one_shot_3d_photographyDepth estimation code: github.com/facebookresearch/one_shot_3d_photography
One Shot 3D Photography (SIGGRAPH 2020) Johannes Kopf 2020-08-27 | This SIGGRAPH 2020 paper describes the tech behind the Facebook 3D Photos feature.Project page: facebookresearch.github.io/one_shot_3d_photographyCode: github.com/facebookresearch/one_shot_3d_photography
Consistent Video Depth Estimation Johannes Kopf 2020-05-01 | Our SIGGRAPH 2020 paper about reconstructing dense, geometrically consistent depth for all pixels in a monocular video. The input is just a hand-held captured cell phone video.Paper and more results available at our project page:roxanneluo.github.io/Consistent-Video-Depth-EstimationCode:github.com/facebookresearch/consistent_depth
Casual 3D Photography Johannes Kopf 2017-09-22 | Home-made VR just with a camera. Check out youtube.com/watch?v=wGBistgOsyQ&t=3s for all the details. Even more stuff on our project page http://visual.cs.ucl.ac.uk/pubs/casual3d
Interview about Digital Reconstruction of Classic Comics Johannes Kopf 2015-08-28 | While cleaning my hard drive I found this old interview about a fun paper I wrote a couple years ago with my friend Dani. It is about digitizing scanned comic books, removing half-toning, and creating some cool parallax-layered zoom animations. You can check out all the details on our project page:http://tinyurl.com/q4nl6na
First-person Hyperlapse Videos (Technical) Johannes Kopf 2014-08-10 | We present a method for converting first-person videos, for example, captured with a helmet camera during activities such as rock climbing or bicycling, into hyperlapse videos: time-lapse videos with a smoothly moving camera.This video accompanies our SIGGRAPH paper and provides a technical explanation of our system.Download Hyperlapse apps for Android, Windows Phone, and Windows Desktop here:http://aka.ms/hyperlapse
Image-Based Rendering in the Gradient Domain Johannes Kopf 2013-09-04 | This is the accompanying video to our SIGGRAPH Asia 2013 paper "Image-Based Rendering in the Gradient Domain".The music track is courtesy of Nadjana Gaffron, soundcloud.com/nadjana/sycamore.
Image-Based Rendering for Scenes with Reflections Johannes Kopf 2012-05-15 | The supplementary video to our SIGGRAPH 2012 paper. Enjoy!Abstract:We present a system for image-based modeling and rendering of real-world scenes containing reflective and glossy surfaces. Previous approaches to image-based rendering assume that the scene can be approximated by 3D proxies that enable view interpolation using traditional back-to-front or z-buffer compositing. In this work, we show how these can be generalized to multiple layers that are combined in an additive fashion to model the reflection and transmission of light that occurs at specular surfaces such as glass and glossy materials. To simplify the analysis and rendering stages, we model the world using piecewise-planar layers combined using both additive and opaque mixing of light. We also introduce novel techniques for estimating multiple depths in the scene and separating the reflection and transmission components into different layers. We then use our system to model and render a variety of real-world scenes with reflections.
Street Slide: Browsing Street Level Imagery Johannes Kopf 2010-07-24 | This is the accompanying video to our SIGGRAPH 2010 paper. Enjoy! Visit http://tinyurl.com/28myc32 for more info about the project. Abstract: Systems such as Google Street View and Bing Maps Streetside enable users to virtually visit cities by navigating between immersive 360panoramas, or bubbles. The discrete moves from bubble to bubble enabled in these systems do not provide a good visual sense of a larger aggregate such as a whole city block. Multi-perspective "strip" panoramas can provide a visual summary of a city street but lack the full realism of immersive panoramas. We present Street Slide, which combines the best aspects of the immersive nature of bubbles with the overview provided by multi-perspective strip panoramas. We demonstrate a seamless transition between bubbles and multi-perspective panoramas. We also present a dynamic construction of the panoramas which overcomes many of the limitations of previous systems. As the user slides sideways, the multi-perspective panorama is constructed and rendered dynamically to simulate either a perspective or hyper-perspective view. This provides a strong sense of parallax, which adds to the immersion. We call this form of sliding sideways while looking at a street facade a street slide. Finally we integrate annotations and a mini-map within the user interface to provide geographic information as well additional affordances for navigation. We demonstrate our Street Slide system on a series of intersecting streets in an urban setting. We report the results of a user study, which shows that visual searching is greatly enhanced with the Street Slide interface over existing systems from Google and Bing.
Solid Texture Synthesis from 2D Exemplars Johannes Kopf 2009-06-02 | Feast your eyes on this:*** This is the accompanying video for our SIGGRAPH 2007 paper ***Enjoy!Title:Solid Texture Synthesis from 2D ExemplarsAbstract:We present a novel method for synthesizing solid textures from 2D texture exemplars. First, we extend optimization-based 2D texture synthesis to synthesize 3D texture solids. Next, the non-parametric texture optimization approach is integrated with histogram matching, which forces the global statistics of the synthesized solid to match those of the exemplar. This improves the convergence of the synthesis process and enables using smaller neighborhoods. In addition to producing compelling texture mapped surfaces, our method also effectively models the material in the interior of solid objects. We also demonstrate that our method is well-suited for synthesizing textures with a large number of channels per texel.
Recursive Wang Tiles for Real-Time Blue Noise Johannes Kopf 2009-06-02 | This is the accompanying video for our SIGGRAPH 2006 paper."Recursive Wang Tiles for Real-Time Blue Noise"Enjoy!Abstract:Well distributed point sets play an important role in a variety of computer graphics contexts, such as anti-aliasing, global illumination, halftoning, non-photorealistic rendering, point-based modeling and rendering, and geometry processing. In this paper, we introduce a novel technique for rapidly generating large point sets possessing a blue noise Fourier spectrum and a high visual quality. Our technique generates non-periodic point sets, distributed over arbitrarily large areas. The local density of a point set may be prescribed by an arbitrary target density function, without any preset bound on the maximum density. Our technique is deterministic and tile-based; thus, any local portion of a potentially infinite point set may be consistently regenerated as needed. The memory footprint of the technique is constant, and the cost to generate any local portion of the point set is proportional to the integral over the target density in that area. These properties make our technique highly suitable for a variety of real-time interactive applications, some of which are demonstrated in the paper.Our technique utilizes a set of carefully constructed progressive and recursive blue noise Wang tiles. The use of Wang tiles enables the generation of infinite non-periodic tilings. The progressive point sets inside each tile are able to produce spatially varying point densities. Recursion allows our technique to adaptively subdivide tiles only where high density is required, and makes it possible to zoom into point sets by an arbitrary amount, while maintaining a constant apparent density.
Deep Photo: Model-Based Photograph Enhancement and Viewing Johannes Kopf 2009-06-02 | Fasten your seat belts and light off your cigarettes:*** This is the supplementary video to our SIGGRAPH Asia 2008 paper ***Enjoy!Visit http://johanneskopf.de/publications/deep_photoTitle:Deep Photo: Model-Based Photograph Enhancement and ViewingAbstract:In this paper, we introduce a novel system for browsing, enhancing, and manipulating casual outdoor photographs by combining them with already existing georeferenced digital terrain and urban models. A simple interactive registration process is used to align a photograph with such a model. Once the photograph and the model have been registered, an abundance of information, such as depth, texture, and GIS data, becomes immediately available to our system. This information, in turn, enables a variety of operations, ranging from dehazing and relighting the photograph, to novel view synthesis, and overlaying with geographic information. We describe the implementation of a number of these applications and discuss possible extensions. Our results show that augmenting photographs with already available 3D models of the world supports a wide variety of new ways for us to experience and interact with our everyday snapshots.
Locally Adapted Projections to Reduce Panorama Distortions Johannes Kopf 2009-06-02 | This is the supplementary video for our EGSR 2009 paper.See http://johanneskopf.de/publications/projection for more info.Enjoy!Title:Locally Adapted Projections to Reduce Panorama DistortionsAbstract:Displaying panoramic and wide angle views on a flat 2D display surface is necessarily prone to distortions. Perspective projections are limited to fairly narrow view angles. Cylindrical and spherical projections can show full 360° panoramas, but at the cost of curving straight lines, interfering with the perception of salient shapes in the scene. In this paper, we introduce locally-adapted projections. Such projections are defined by a continuous projection surface consisting of both near-planar and curved parts. A simple and intuitive user interface allows the specification of regions of interest to be mapped to the near-planar parts, thereby reducing bending artifacts. We demonstrate the effectiveness of our approach on a variety of panoramic and wide angle images, including both indoor and outdoor scenes.
Capturing and Viewing Gigapixel Images Johannes Kopf 2007-05-14 | This is the accompanying video to our SIGGRAPH 2007 paper. We present a system to capture and view "Gigapixel images": very high resolution, high dynamic range, and wide angle imagery consisting of several billion pixels each. A specialized camera mount, in combination with an automated pipeline for alignment, exposure compensation, and stitching, provide the means to acquire Gigapixel images with a standard camera and lens. More importantly, our novel viewer enables exploration of such images at interactive rates over a network, while dynamically and smoothly interpolating the projection between perspective and curved projections, and simultaneously modifying the tone-mapping to ensure an optimal view of the portion of the scene being viewed. The authors are: Johannes Kopf University of Konstanz Matt Uyttendaele Microsoft Research Oliver Deussen University of Konstanz Michael Cohen Microsoft Research
