FaithFill: Faithful Inpainting for Object Completion Using a Single Reference Image

arXiv:2406.07865v1 Announce Type: new
Abstract: We present FaithFill, a diffusion-based inpainting object completion approach for realistic generation of missing object parts. Typically, multiple reference images are needed to achieve such realistic generation, otherwise the generation would not faithfully preserve shape, texture, color, and background. In this work, we propose a pipeline that utilizes only a single input reference image -having varying lighting, background, object pose, and/or viewpoint. The singular reference image is used to generate multiple views of the object …

abstract arxiv color cs.ai cs.cv cs.lg diffusion image images inpainting multiple object reference shape texture type work