Showing papers by "Neil Birkbeck published in 2006"

Variational shape and reflectance estimation under changing light and viewpoints

Abstract: Fitting parameterized 3D shape and general reflectance models to 2D image data is challenging due to the high dimensionality of the problem. The proposed method combines the capabilities of classical and photometric stereo, allowing for accurate reconstruction of both textured and non-textured surfaces. In particular, we present a variational method implemented as a PDE-driven surface evolution interleaved with reflectance estimation. The surface is represented on an adaptive mesh allowing topological change. To provide the input data, we have designed a capture setup that simultaneously acquires both viewpoint and light variation while minimizing self-shadowing. Our capture method is feasible for real-world application as it requires a moderate amount of input data and processing time. In experiments, models of people and everyday objects were captured from a few dozen images taken with a consumer digital camera. The capture process recovers a photo-consistent model of spatially varying Lambertian and specular reflectance and a highly accurate geometry.

Variational Shape and Reflectance Estimation Under Changing Light and Viewpoints

Abstract: Fitting parameterized 3D shape and general reflectance models to 2D image data is challenging due to the high dimensionality of the problem. The proposed method combines the capabilities of classical and photometric stereo, allowing for accurate reconstruction of both textured and non-textured surfaces. In particular, we present a variational method implemented as a PDE-driven surface evolution interleaved with reflectance estimation. The surface is represented on an adaptive mesh allowing topological change. To provide the input data, we have designed a capture setup that simultaneously acquires both viewpoint and light variation while minimizing self-shadowing. Our capture method is feasible for real-world application as it requires a moderate amount of input data and processing time. In experiments, models of people and everyday objects were captured from a few dozen images taken with a consumer digital camera. The capture process recovers a photo-consistent model of spatially varying Lambertian and specular reflectance and a highly accurate geometry.

Object Centered Stereo: Displacement Map Estimation Using Texture and Shading

Abstract: We consider the problem of recovering 3D surface displacements using both shading and multi-view stereo cues. In contrast to traditional disparity or depth map representations, the object centered displacement map representation enables the recovery of complete 3D objects while also ensuring the reconstruction is not biased towards a particular image. Although displacement mapping requires a base surface, this base mesh is easily obtained using traditional computer vision techniques (e.g., shape-from-silhouette or structure-from-motion). Our method exploits shading variation due to object rotation relative to the light source, allowing the recovery of displacements in both textured and textureless regions in a common framework. In particular, shading cues are integrated into a multi-view stereo photo-consistency function through the surface normals that are implied by the displacement map. The analytic gradient of this photo-consistency function is used to drive a multi-resolution conjugate gradient optimization. We demonstrate the geometric quality of the reconstructed displacements on several example objects including a human face.

Video augmented reality with robust tracking

Abstract: The goal of our research is to augment a 3D scene with video for a variety of applications, including entertainment and advertisement. In an entertainment application we could add video on to a 3D games environment to both add realism and allow players to pick up clues from video clips. For advertisement, we could add videos of popular soft drinks into a movie; for example, a video advertisement could be added on the side of a building as a helicopter flies by. To make video augmented reality possible, and robust, we need to address several issues; camera registration and rendering, tracking of certain feature planes (e.g., the side of a building or the top of a roof), integrating video into a 3D scene, and invariance to illumination variations, being some important ones.