Abstract
We tackle the task of stylizing video objects in an intuitive and semantic manner following a user-specified text prompt. This is a challenging task as the resulting video must satisfy multiple properties: (1) it has to be temporally consistent and avoid jittering or similar artifacts, (2) the resulting stylization must preserve both the global semantics of the object and its fine-grained details, and (3) it must adhere to the user-specified text prompt. To this end, our method stylizes an object in a video according to a global target text prompt that describes the global semantics and a local target text prompt that describes the local semantics. To modify the style of an object, we harness the representational power of CLIP to get a similarity score between (1) the local target text and a set of local stylized views, and (2) a global target text and a set of stylized global views. We use a pretrained atlas decomposition network to propagate the edits in a temporally consistent manner. We demonstrate that our method can generate consistent style changes in time for a variety of objects and videos, that adhere to the specification of the target texts. We also show how varying the specificity of the target texts, and augmenting the texts with a set of prefixes results in stylizations with different levels of detail. Full results are given on our project webpage: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2206.12396
