Embedded Files
Spring School Goal
Spring School Goal
Humans have the astounding capability of visually identifying scenes and material despite complex illumination and vastness of the scene. For instance, one can tell which material an object is made of, just by looking at it (for instance metal, plastic, rubber, wood, glass or fabric). In addition, also based only on its visual appearance, we can often evaluate key properties of the material, such as its fragility or robustness, softness or hardness, smoothness or roughness, etc. One can identify the six-degree of freedom associated with the pose of an object. Navigating ("simultaneous localization and mapping") is another extraordinary ability we all possess. It's no wonder that close to 60% of the human activity is devoted to the visual cortex.
Humans have the astounding capability of visually identifying scenes and material despite complex illumination and vastness of the scene. For instance, one can tell which material an object is made of, just by looking at it (for instance metal, plastic, rubber, wood, glass or fabric). In addition, also based only on its visual appearance, we can often evaluate key properties of the material, such as its fragility or robustness, softness or hardness, smoothness or roughness, etc. One can identify the six-degree of freedom associated with the pose of an object. Navigating ("simultaneous localization and mapping") is another extraordinary ability we all possess. It's no wonder that close to 60% of the human activity is devoted to the visual cortex.
Beginning 2012, artificial neural networks with the so-called deep learning have seemingly become capable of mimicking this human ability. The goal of this workshop is to work from the basics of deep learning for computer vision and graphics, all the way up to the prevailing state of the art methods.
Beginning 2012, artificial neural networks with the so-called deep learning have seemingly become capable of mimicking this human ability. The goal of this workshop is to work from the basics of deep learning for computer vision and graphics, all the way up to the prevailing state of the art methods.
The mornings are devoted to talks and afternoons to laboratory sessions. The eventual goal is to gain new knowledge of how human beings perceive the visual appearance of materials, objects, and scenes, and to develop new methodologies for measuring and communicating visual appearance.
The mornings are devoted to talks and afternoons to laboratory sessions. The eventual goal is to gain new knowledge of how human beings perceive the visual appearance of materials, objects, and scenes, and to develop new methodologies for measuring and communicating visual appearance.
Page updated
Report abuse