|
Robust Fusion of Dynamic Shape and Normal Capture for High-quality Reconstruction of Time-varying Geometry We present a new passive approach to capture time-varying scene geometry in large acquisition volumes from multi-view video. It can be applied to reconstruct complete moving models of human actors that feature even slightest dynamic geometry detail, such as wrinkles and folds in clothing, and that can be viewed from 360 degrees. Starting from multi-view video streams recorded under calibrated lighting, we first perform marker-less human motion capture based on a smooth template with no high-frequency surface detail. Subsequently, surface reflectance and time-varying normal fields are estimated based on the coarse template shape. The main contribution of this work is a new statistical approach to solve the non-trivial problem of transforming the captured normal field that is defined over the smooth non-planar 3D template into true 3D displacements. Our spatio-temporal reconstruction method outputs displaced geometry that is accurate at each time step of video and temporally smooth, even if the input data are affected by noise.
|
|
|
Dense Correspondence Finding for Parametrization-free Animation Reconstruction from Video We present a dense 3D correspondence finding method that enables spatio-temporally coherent reconstruction of surface animations from multi-view video data. Given as input a sequence of shape-from-silhouette volumes of a moving subject that were reconstructed for each time frame individually, our method establishes dense surface correspondences between subsequent shapes independently of surface discretization. This is achieved in two steps: first, we obtain sparse correspondences from robust optical features between adjacent frames. Second, we generate dense correspondences which serve as map between respective surfaces. By applying this procedure subsequently to all pairs of time steps we can trivially align one shape with all others. Thus, the original input can be reconstructed as a sequence of meshes with constant connectivity and small tangential distortion.
|
|
|
Performance Capture from Sparse Multi-view Video We propose a new marker-less approach to capturing human performances from multi-view video. Our algorithm can jointly reconstruct spatio-temporally coherent geometry, motion and textural surface appearance of actors that perform complex and rapid moves. Furthermore, since our algorithm is purely meshbased and makes as few as possible prior assumptions about the type of subject being tracked, it can even capture performances of people wearing wide apparel, such as a dancer wearing a skirt. To serve this purpose our method efficiently and effectively combines the power of surface- and volume-based shape deformation techniques with a new mesh-based analysis-through-synthesis framework that extracts motion constraints from video in order to make a laser-scan of the tracked subject mimic the recorded performance. Also small-scale time-varying shape detail is recovered by applying model-guided multi-view stereo to refine the model surface. Our method delivers captured performance data at an unprecedented level of detail, is highly versatile, and is applicable to many complex types of scenes that could not be handled by alternative marker-based or marker-free recording techniques.
|
|
|
Spatio-temporal Reflectance Sharing for Relightable 3D Video Extending our work on Relightable Free-Viewpoint Video, we propose a novel algorithm that exploits spatio-temporal coherence in our reflectance samples and reduces the bias in BRDF estimates of a single surface point. We demonstrate the improvements achieved with this spatio-temporal reflectance sharing approach both visually and quantitatively.
|
|
|
Relightable Free-Viewpoint Video By means of passive optical motion capture real people can be authentically animated and photo-realistically textured. To import real-world characters into virtual environments, however, also surface reflectance properties must be known. We describe a video-based modeling approach that captures human shape and motion as well as reflectance characteristics from a handful of synchronized video recordings. The presented method is able to recover spatially varying surface reflectance properties of clothes from multi-view video footage. The resulting model description enables us to realistically reproduce the appearance of animated virtual actors under different lighting conditions, as well as to interchange surface attributes among different people, e.g. for virtual dressing. Our contribution can be used to create 3D renditions of real-world people under arbitrary novel lighting conditions on standard graphics hardware.
|
|
|
Automatic Generation of Human Avatars We present a novel easy-to-use and fully-automatic approach to create a personalized avatar from multi-view video data of a moving person. An adaptable generic human body model is scaled and deformed until its shape and skeletal dimensions match the real human shown in the video footage. A consistent surface texture for the model is generated using multi-view video frames from different camera views and different body poses. With our proposed method photo-realistic human avatars can be robustly generated.
|
|
|
BRDF Reconstruction from Video Streams of Multi-View Recordings This project is the implementation of my Master's thesis. We propose a novel method for estimating surface reflectance properties of dynamic objects from multi-view video recordings.
|
|
|
Through the Looking Glass On the right is the final output from a ray-tracer that I implemented in the Computer Graphics course. Main features were photon mapping, cook-torrance shading model, area light sources and the depth of field effect.
|
|
![High Resolution [1280x1024]](Looking_Glass.jpg){kind=link}