Given a nearest-pixel inpainted image (left) and its corresponding prompt, we can inpaint the image via noise optimization. Input Inpainted Output "A young man with short black hair styled upward, ...
Abstract: It has been proven that introducing multiple guidance sources boosts image inpainting performance. However, existing methods primarily focus on local relationships and neglect the holistic ...
Token Painter: Training-Free Text-Guided Image Inpainting via Mask Autoregressive Models (AAAI 2026)
Token Painter is a training-free text-guided image inpainting model built upon the Mask AutoRegressive (MAR) paradigm. Unlike diffusion-based methods that model the entire image in latent space and ...
Abstract: Video inpainting aims to reconstruct missing or corrupted regions in video frames, with applications in video editing, restoration, and special effects. Current deep video inpainting methods ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results