Fill My Mirror: Geometry-Constrained Mirror Inpainting

• URL: http://arxiv.org/abs/2609.03740v1
• Date: Thu, 03 Sep 2026 12:11:02 GMT
• Title: Fill My Mirror: Geometry-Constrained Mirror Inpainting
• Abstract summary: Mirror appearance depends on scene geometry and viewpoint, making it hard to synthesize using learned appearance priors alone.<n>We address this in the mirror inpainting setting, where the scene is fixed and only the mirror region is generated.<n>A generative model then completes the mirror region via a two-mask diffusion strategy balancing geometric constraints with the model's learned priors.
• Score: 14.396466872686494
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Mirrors are common in real-world images, yet producing geometrically consistent reflections with generative models remains challenging. Unlike most objects, mirror appearance depends on scene geometry and viewpoint, making it hard to synthesize using learned appearance priors alone. We address this in the mirror inpainting setting, where the scene is fixed and only the mirror region is generated. Our key insight is that much mirror content is geometrically constrained by the visible scene and need not be hallucinated. We estimate scene geometry and project visible content into the mirror to recover reflection regions determined by geometry. A generative model then completes the mirror region via a two-mask diffusion strategy balancing geometric constraints with the model's learned priors, reducing projection artifacts and improving reflection consistency. The method is training-free and applicable to complex real-world scenes. We evaluate on MirrorBench-V2 (synthetic) and real images. Using standard and geometry-aware metrics, we show that explicitly using scene geometry improves consistency.

Related papers

• MirrorWorld: Taming Video Diffusion Models for Mirror Reflection Generation [46.878264012748694]
  We propose a reflection-aware video inpainting framework that models scene-to-mirror relationships during generation.<n>MirrorWorld achieves improved reflection reconstruction quality over representative image-based reflection generation methods.
  arXiv  Detail & Related papers  (2026-08-07T17:58:10Z)
• Reflect3r: Single-View 3D Stereo Reconstruction Aided by Mirror Reflections [55.248092751290834]
  Mirror reflections are common in everyday environments and can provide stereo information within a single capture.<n>We exploit this property by treating the reflection as an auxiliary view and designing a transformation that constructs a physically valid virtual camera.<n>This enables a multi-view stereo setup from a single image, simplifying the imaging process.
  arXiv  Detail & Related papers  (2025-09-24T23:00:22Z)
• Reflections Unlock: Geometry-Aware Reflection Disentanglement in 3D Gaussian Splatting for Photorealistic Scenes Rendering [51.223347330075576]
  Ref-Unlock is a novel geometry-aware reflection modeling framework based on 3D Gaussian Splatting.<n>Our approach employs a dual-branch representation with high-order spherical harmonics to capture high-frequency reflective details.<n>Our method thus offers an efficient and generalizable solution for realistic rendering of reflective scenes.
  arXiv  Detail & Related papers  (2025-07-08T15:45:08Z)
• Gaussian Splatting in Mirrors: Reflection-Aware Rendering via Virtual Camera Optimization [14.324573496923792]
  3D-GS often misinterprets reflections as virtual spaces, resulting in blurred and inconsistent multi-view rendering within mirrors. Our paper presents a novel method aimed at obtaining high-quality multi-view consistent reflection rendering by modelling reflections as physically-based virtual cameras.
  arXiv  Detail & Related papers  (2024-10-02T14:53:24Z)
• Reflecting Reality: Enabling Diffusion Models to Produce Faithful Mirror Reflections [26.02117310176884]
  We tackle the problem of generating highly realistic and plausible mirror reflections using diffusion-based generative models.<n>We propose a novel depth-conditioned inpainting method called MirrorFusion, which generates high-quality, realistic, shape and appearance-aware reflections of real-world objects.<n>MirrorFusion outperforms state-of-the-art methods on SynMirror, as demonstrated by extensive quantitative and qualitative analysis.
  arXiv  Detail & Related papers  (2024-09-23T02:59:07Z)
• MirrorGaussian: Reflecting 3D Gaussians for Reconstructing Mirror Reflections [58.003014868772254]
  MirrorGaussian is the first method for mirror scene reconstruction with real-time rendering based on 3D Gaussian Splatting. We introduce an intuitive dual-rendering strategy that enables differentiableization of both the real-world 3D Gaussians and the mirrored counterpart. Our approach significantly outperforms existing methods, achieving state-of-the-art results.
  arXiv  Detail & Related papers  (2024-05-20T09:58:03Z)
• Mirror-3DGS: Incorporating Mirror Reflections into 3D Gaussian Splatting [27.361324194709155]
  Mirror-3DGS is a novel framework designed to accurately handle mirror geometries and reflections.<n>By incorporating mirror attributes into 3DGS, Mirror-3DGS simulates a mirrored viewpoint from behind the mirror, enhancing the realism of scene renderings.
  arXiv  Detail & Related papers  (2024-04-01T15:16:33Z)
• Mirror-NeRF: Learning Neural Radiance Fields for Mirrors with Whitted-Style Ray Tracing [33.852910220413655]
  We present a novel neural rendering framework, named Mirror-NeRF, which is able to learn accurate geometry and reflection of the mirror. Mirror-NeRF supports various scene manipulation applications with mirrors, such as adding new objects or mirrors into the scene and synthesizing the reflections of these new objects in mirrors.
  arXiv  Detail & Related papers  (2023-08-07T03:48:07Z)
• Lighting, Reflectance and Geometry Estimation from 360$^{\circ}$ Panoramic Stereo [88.14090671267907]
  We propose a method for estimating high-definition spatially-varying lighting, reflectance, and geometry of a scene from 360$circ$ stereo images. Our model takes advantage of the 360$circ$ input to observe the entire scene with geometric detail, then jointly estimates the scene's properties with physical constraints.
  arXiv  Detail & Related papers  (2021-04-20T10:41:50Z)
• Visual Chirality [51.685596116645776]
  We investigate how statistics of visual data are changed by reflection. Our work has implications for data augmentation, self-supervised learning, and image forensics.
  arXiv  Detail & Related papers  (2020-06-16T20:48:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.