Computer Vision: From Surfaces to 3D Objects (Hardcover)

The typical computational approach to object understanding derives shape information from the 2D outline of the objects. For complex object structures, however, such a planar approach cannot determine object shape; the structural edges have to be encoded in terms of their full 3D spatial configuration. Computer Vision: From Surfaces to 3D Objects is the first book to take a full approach to the challenging issue of veridical 3D object representation. It introduces mathematical and conceptual advances that offer an unprecedented framework for analyzing the complex scene structure of the world.

An Unprecedented Framework for Complex Object Representation
Presenting the material from both computational and neural implementation perspectives, the book covers novel analytic techniques for all levels of the surface representation problem. The cutting-edge contributions in this work run the gamut from the basic issue of the ground plane for surface estimation through mid-level analyses of surface segmentation processes to complex Riemannian space methods for representing and evaluating surfaces.

State-of-the-Art 3D Surface and Object Representation
This well-illustrated book takes a fresh look at the issue of 3D object representation. It provides a comprehensive survey of current approaches to the computational reconstruction of surface structure in the visual scene.

傳統的物體理解計算方法是從物體的二維輪廓中獲取形狀信息。然而，對於複雜的物體結構，這種平面方法無法確定物體的形狀；結構邊緣必須以完整的三維空間配置編碼。《從表面到三維物體的計算機視覺》是第一本全面探討真實三維物體表示問題的書籍。它介紹了數學和概念上的創新，為分析複雜場景結構提供了前所未有的框架。

以計算和神經實現的角度呈現材料，本書涵蓋了表面表示問題各個層次的新穎分析技術。這項工作的尖端貢獻從表面估計的基本問題，到表面分割過程的中級分析，再到用於表示和評估表面的複雜黎曼空間方法，涵蓋了各個方面。

這本圖文並茂的書對三維物體表示問題提出了新的觀點。它全面調查了當前在視覺場景中計算重建表面結構的方法。