Text2LIVE: Text-Driven Layered Image and Video Editing

5 Apr 2022  ·  Omer Bar-Tal, Dolev Ofri-Amar, Rafail Fridman, Yoni Kasten, Tali Dekel ·

We present a method for zero-shot, text-driven appearance manipulation in natural images and videos. Given an input image or video and a target text prompt, our goal is to edit the appearance of existing objects (e.g., object's texture) or augment the scene with visual effects (e.g., smoke, fire) in a semantically meaningful manner. We train a generator using an internal dataset of training examples, extracted from a single input (image or video and target text prompt), while leveraging an external pre-trained CLIP model to establish our losses. Rather than directly generating the edited output, our key idea is to generate an edit layer (color+opacity) that is composited over the original input. This allows us to constrain the generation process and maintain high fidelity to the original input via novel text-driven losses that are applied directly to the edit layer. Our method neither relies on a pre-trained generator nor requires user-provided edit masks. We demonstrate localized, semantic edits on high-resolution natural images and videos across a variety of objects and scenes.

PDF Abstract


  Add Datasets introduced or used in this paper

Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.