Inferring the deformation of unfamiliar objects
نویسندگان
چکیده
منابع مشابه
Inferring 2D Object Structure from the Deformation of Apparent Contours
We present a new integrated approach to the two-dimensional part segmentation, shape and motion estimation of moving multi-part objects. Our technique exploits the relationship between the geometry and the observed deformations of the apparent contour of a moving multi-part object and its structure. The novelty of the technique is that no prior model of the object or of its parts is employed. W...
متن کاملConfigural and analytical processing of familiar and unfamiliar objects.
Configural processing could develop for non-face visual objects as one becomes familiar with those objects through repeated exposure. To explore the role of familiarity in object recognition, we studied the effect of adaptation to a visual object (adapting stimulus) on the identification performance of other objects (test stimulus) while adapting and test stimuli were exactly the same, shared p...
متن کاملFirst Contact: Segmenting Unfamiliar Objects by Poking Them
How a robot should grasp an object depends on its size and shape. Such parameters can be estimated visually, but this is fallible, particularly for unrecognized, unfamiliar objects. Failure will result in a clumsy grasp or glancing blow against the object. If the robot does not learn something from the encounter, then it will be apt to repeat the same mistake again and again. This paper shows h...
متن کاملAdaptive Deformation Simulation of Inhomogeneous Elastic Objects
ゼリーのような柔らかいもの(もしくは弾性体)の物理 ベースな変形シミュレーションは, 動画やテレビゲームなど の分野において重要である. これまで, コンピューターグラ フィックスの分野において, 弾性体の変形に関する非常に多 くの研究がなされてきた. 質量バネモデルや粒子ベースモ デル [19, 11, 1]は, テレビゲームのようなインタラクティブ なアプリケーションに用いられ, より正確な, すなわち連続 体力学に基づいた FEM(Finite Element Method, 有限要素 法)ベースのシミュレーション手法は, 主に正確さが要求さ れる動画に用いられている. FEM ベースのモデルは, 計算 コストが高いことが知られており, アダプティブ分割法など の多重解像度手法が提案されている [4, 8]. 一般的に多重解像度のアプローチを用いる FEM ベース の手法では,...
متن کاملDynamic Network: Graphical Deformation of Penetrated Objects
In a computer-based virtual environment, objects may collide with each other. Therefore, different algorithms are needed to detect the collision and perform a correct action in order to avoid penetration. Based on the application and objects physical characteristics, a correct action can include separating or deforming the penetrated objects. In this article, by using the concepts of dynamic ne...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Journal of Vision
سال: 2017
ISSN: 1534-7362
DOI: 10.1167/17.10.315