Amodal Completion via Progressive Mixed Context Diffusion
This addresses the problem of recognizing partially hidden objects for computer vision applications, representing an incremental improvement over existing two-step approaches.
The paper tackles the challenge of amodal completion in generative AI by proposing a method that uses context outside object bounding boxes to guide a pre-trained diffusion inpainting model, progressively growing occluded objects and trimming background, resulting in improved photorealistic completion without requiring special training or fine-tuning.
Our brain can effortlessly recognize objects even when partially hidden from view. Seeing the visible of the hidden is called amodal completion; however, this task remains a challenge for generative AI despite rapid progress. We propose to sidestep many of the difficulties of existing approaches, which typically involve a two-step process of predicting amodal masks and then generating pixels. Our method involves thinking outside the box, literally! We go outside the object bounding box to use its context to guide a pre-trained diffusion inpainting model, and then progressively grow the occluded object and trim the extra background. We overcome two technical challenges: 1) how to be free of unwanted co-occurrence bias, which tends to regenerate similar occluders, and 2) how to judge if an amodal completion has succeeded. Our amodal completion method exhibits improved photorealistic completion results compared to existing approaches in numerous successful completion cases. And the best part? It doesn't require any special training or fine-tuning of models.