Robust Near-Isometric Matching via Structured Learning of Graphical Models
نویسندگان
چکیده
Models for near-rigid shape matching are typically based on distance-related features, in order to infer matches that are consistent with the isometric assumption. However, real shapes from image datasets, even when expected to be related by “almost isometric” transformations, are actually subject not only to noise but also, to some limited degree, to variations in appearance and scale. In this paper, we introduce a graphical model that parameterises appearance, distance, and angle features and we learn all of the involved parameters via structured prediction. The outcome is a model for near-rigid shape matching which is robust in the sense that it is able to capture the possibly limited but still important scale and appearance variations. Our experimental results reveal substantial improvements upon recent successful models, while maintaining similar running times.
منابع مشابه
Learning Near-Isometric Matching Models
Shape matching problems are typically described in terms of structural properties, encoding (for example) the ‘elasticity’ of certain joints in a rigid object. Unfortunately, encoding such constraints often results in a hard optimization problem (such as quadratic assignment), meaning that approximate solutions are typically employed; this presents a problem for many learning approaches that re...
متن کاملA Low-Dimensional Representation for Robust Partial Isometric Correspondences Computation
Intrinsic shape matching has become the standard approach for pose invariant correspondence estimation among deformable shapes. Most existing approaches assume global consistency. While global isometric matching is well understood, only a few heuristic solutions are known for partial matching. Partial matching is particularly important for robustness to topological noise, which is a common prob...
متن کاملFast matching of large point sets under occlusions
The problem of isometric point-pattern matching can be modeled as inference in small tree-width graphical models whose embeddings in the plane are said to be ‘globally rigid’. Although such graphical models lead to efficient and exact solutions, they cannot generally handle occlusions, as even a single missing point may ‘break’ the rigidity of the graph in question. In addition, such models can...
متن کاملBethe Learning of Graphical Models via MAP Decoding
Many machine learning tasks require fitting probabilistic models over structured objects, such as pixel grids, matchings, and graph edges. Maximum likelihood estimation (MLE) for such domains is challenging due to the intractability of computing partition functions. One can resort to approximate marginal inference in conjunction with gradient descent, but such algorithms require careful tuning....
متن کاملGraphical Models for Inference and Learning in Computer Vision
Graphical models are indispensable as tools for inference in computer vision, where highly structured and interdependent output spaces can be described in terms of low-order, local relationships. One such problem is that of graph matching, where the goal is to localise various parts of an object within an image: although the number of joint configurations of these parts may be very large, the r...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2008