Pioneer Centre for Artificial Intelligence Colloquium
Sagie Benaim on "Semantic Manipulation of Visual Content"
Oplysninger om arrangementet
Tidspunkt
Sted
Ada 333 or online (see Zoom link below)
Pris
Abstract:
Methods for visual content manipulation, such as texture and style transfer, are a subject of long-term interest in computer vision, but often lack the ability to manipulate content semantically. In this talk, I will discuss approaches for the semantic manipulation of images, videos, and 3D objects.
In the image domain, I will discuss a method for generating a 'structural analogy' between two images A and B: that is, an image that keeps the appearance and style of B, but has a structural arrangement that corresponds to A.
Moving the videos, I will discuss a method that learns to automatically predict the 'speediness' of moving objects in videos in a self-supervised manner. This can be used for semantic adaptive video speedup as well as for self-supervised action recognition and video retrieval.
Lastly, I will discuss a method for the semantic stylization of 3D meshes conforming to a target text prompt. The method can handle low-quality meshes (non-manifold, boundaries, etc.) with arbitrary genus, and does not require parameterization. It can be used to synthesize a myriad of semantic styles over a wide variety of 3D meshes in-the-wild.
Join Zoom Meeting
https://aarhusuniversity.zoom.us/j/66373029363
Meeting ID: 663 7302 9363
Join by SIP
Join by H.323
109.105.112.236
109.105.112.235
Meeting ID: 663 7302 9363