Direct Methods for Visual Scene Reconstruction

نویسندگان

  • Richard Szeliski
  • Sing Bing Kang
چکیده

There has been a lot of activity recently surrounding the reconstruction of photorealistic 3-D scenes and high-resolution images from video sequences. In this paper, we present some of our recent work in this area, which is based on the registration of multiple images (views) in a projective framework. Unlike most other techniques, we do not rely on special features to form a projective basis. Instead, we directly solve a least-squares estimation problem in the unknown structure and motion parameters, which leads to statistically optimal estimates. We discuss algorithms for both constructing planar and panoramic mosaics, and for projective depth recovery. We also speculate about the ultimate usefulness of projective approaches to visual scene reconstruction.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Reconstruction from image correspondences

A single picture provides a largely incomplete representation of the scene one is looking at. Usually it reproduces only a limited spatial portion of the scene according to the standpoint and the viewing angle, besides it contains only instantaneous information. Thus very little can be understood on the geometrical structure of the scene, the position and orientation of the observer with respec...

متن کامل

Incremental Visual Hull Reconstruction

Visual hull reconstruction is the process of generating three dimensional scene geometry from silhouette images captured from different views of a scene. The visual hull is the shape maximally consistent with its silhouette projection [4]. It has been popular due to its good approximating qualities for many objects and its ease and speed of implementation. It is commonly used as a starting poin...

متن کامل

R4-B.4: Integrated Reconstruction/Recognition

In CT-based security screening, a challenging problem is to correctly identify and label objects in a scene from X-ray projection data. The presence of artifacts in the reconstructed image confounds traditional segmentation and labeling methods. In this work, we focus on integrating machine learning, physical modeling and Bayesian inference in a framework for direct material identifi cation and...

متن کامل

Optimizing Ray Tracing with Visual Coherence

We present a method that directs sampling and reconstruction for image generation. This method reduces the cost of the sampling stage, allows a reconstruction of the scene to be progressively reened during the sampling process, and produces a representation of the scene that permits exibility in the generation of images. The method employs a set of region estimators to model and evaluate the sa...

متن کامل

Silhouette Extraction for Visual Hull Reconstruction

Most of volumetric 3D reconstruction methods need accurate silhouette information of foreground objects for the reliable 3D scene reconstruction of the objects. We present an approach to silhouette extraction based on our change detection method [1] using a statistical model and graph cuts based optimization. We describe some requirements for visual hull reconstruction. We show that our change ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1995