Reflecting Reality: Enabling Diffusion Models to Produce Faithful Mirror Reflections

Ankit Dhiman, Manan Shah, Rishubh Parihar, Yash Sanjay Bhalgat, LOKESH R BOREGOWDA, Venkatesh Babu Radhakrishnan

Keywords: Diffusion-Models, Reflections

TL;DR: Introducting MirrorFusion, a diffusion-based method for generating realistic mirror reflections using the proposed SynMirror dataset, enabling precise control to generate faithful mirror reflections..

Abstract: We tackle the problem of generating highly realistic and plausible mirror reflections using diffusion-based generative models. We formulate this problem as an image inpainting task, allowing for more user control over the placement of mirrors during the generation process. To enable this, we create SynMirror, a large-scale dataset of diverse synthetic scenes with objects placed in front of mirrors. SynMirror contains around 198k samples rendered from 66k unique 3D objects, along with their associated depth maps, normal maps and instance-wise segmentation masks, to capture relevant geometric properties of the scene. Using this dataset, we propose a novel depth-conditioned inpainting method called MirrorFusion, which generates high-quality, realistic, shape and appearance-aware reflections of real-world objects. MirrorFusion outperforms state-of-the-art methods on SynMirror, as demonstrated by extensive quantitative and qualitative analysis. To the best of our knowledge, we are the first to successfully tackle the challenging problem of generating controlled and faithful mirror reflections of an object in a scene using diffusion-based models. SynMirror and MirrorFusion open up new avenues for image editing and augmented reality applications for practitioners and researchers alike. The project page is available at: https://val.cds.iisc.ac.in/reflecting-reality.github.io/.

Submission Number: 250