MirrorWorld: Taming Video Diffusion Models for Mirror Reflection Generation

• URL: http://arxiv.org/abs/2608.07463v1
• Date: Fri, 07 Aug 2026 17:58:10 GMT
• Title: MirrorWorld: Taming Video Diffusion Models for Mirror Reflection Generation
• Abstract summary: 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.
• Score: 46.878264012748694
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advances in video diffusion models (VDMs) have enabled high-fidelity video synthesis. However, generating mirror reflections remains challenging because the content within a mirror must remain consistent with the surrounding scene. Existing VDMs are not specifically designed to model scene-to-mirror relationships, which can lead to reflections with incorrect content or inconsistent spatial arrangements. We observe that mirror reflection generation involves two complementary challenges: determining what scene content should be reflected and how the reflected content should be spatially arranged within the mirror region. Motivated by this observation, we propose MirrorWorld, a reflection-aware video inpainting framework that models scene-to-mirror relationships during generation. Specifically, we introduce Semantic Relation Distillation (SRD), which transfers relational information from a frozen visual foundation model to encourage semantic associations between visible scene content and mirror regions. We further propose Geometric Transformation Alignment (GTA), which learns a transformation that guides the spatial arrangement of reflected content. The two components play complementary roles, with SRD modeling what should be reflected and GTA modeling how it should be arranged. To facilitate research on this problem, we construct a benchmark for video mirror reflection generation by repurposing four existing video mirror datasets into a unified reflection reconstruction task. Experimental results show that MirrorWorld achieves improved reflection reconstruction quality over representative image-based reflection generation methods and strong video inpainting baselines.

Related papers

• Reflection-aware Generative Novel View Synthesis [29.38808167444839]
  Ref-GeNVS is a training-free, reflection-aware method for generative novel view synthesis (NVS) in mirror scenes.<n>On synthetic and real scenes including mirrors, Ref-GeNVS outperforms recent generative NVS methods.
  arXiv  Detail & Related papers  (2026-09-04T17:33:45Z)
• Fill My Mirror: Geometry-Constrained Mirror Inpainting [14.396466872686494]
  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.
  arXiv  Detail & Related papers  (2026-09-03T12:11:02Z)
• RT-GS: Gaussian Splatting with Reflection and Transmittance Primitives [52.10688811929143]
  We propose a unified framework that integrates a microfacet material model and ray tracing to jointly model specular reflection and transmittance in Gaussian Splatting.<n>Our experiments demonstrate that our method successfully produces reflections and recovers objects behind transparent surfaces in complex environments.
  arXiv  Detail & Related papers  (2026-04-01T05:50:03Z)
• 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)
• Seeing Through Reflections: Advancing 3D Scene Reconstruction in Mirror-Containing Environments with Gaussian Splatting [3.0501972844045273]
  We present MirrorScene3D, a dataset featuring diverse indoor scenes, 1256 high-quality images, and annotated mirror masks.<n>We propose ReflectiveGS, an extension of 3D Gaussian Splatting that utilizes mirror reflections as complementary viewpoints.<n>Experiments on MirrorScene3D show that ReflectiveGaussian outperforms existing methods in SSIM, PSNR, LPIPS, and training speed.
  arXiv  Detail & Related papers  (2025-09-23T13:06:00Z)
• MirrorSAM2: Segment Mirror in Videos with Depth Perception [48.40774412545921]
  This paper presents MirrorSAM2, the first framework that adapts Segment Anything Model 2 (SAM2) to the task of RGB-D video mirror segmentation.<n>MirrorSAM2 addresses key challenges in mirror detection, such as ambiguity reflection and texture confusion.<n>Experiments on the VMD and DVMD benchmark demonstrate that MirrorSAM2 achieves SOTA performance, even under challenging conditions such as small mirrors, weak boundaries, and strong reflections.
  arXiv  Detail & Related papers  (2025-09-21T20:00:33Z)
• NeRFs are Mirror Detectors: Using Structural Similarity for Multi-View Mirror Scene Reconstruction with 3D Surface Primitives [7.116175288307167]
  We present NeRF-MD, a method which shows that NeRFs can be considered as mirror detectors.<n>We first compute an initial estimate of the scene geometry by training a standard NeRF.<n>We then jointly optimize the radiance field and mirror geometry in a second training stage to refine their quality.
  arXiv  Detail & Related papers  (2025-01-07T18:59:53Z)
• 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)
• 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)
• Revisiting Single Image Reflection Removal In the Wild [83.42368937164473]
  This research focuses on the issue of single-image reflection removal (SIRR) in real-world conditions. We devise an advanced reflection collection pipeline that is highly adaptable to a wide range of real-world reflection scenarios. We develop a large-scale, high-quality reflection dataset named Reflection Removal in the Wild (RRW)
  arXiv  Detail & Related papers  (2023-11-29T02:31:10Z)
• 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)
• Symmetry-Aware Transformer-based Mirror Detection [85.47570468668955]
  We propose a dual-path Symmetry-Aware Transformer-based mirror detection Network (SATNet) SATNet includes two novel modules: Symmetry-Aware Attention Module (SAAM) and Contrast and Fusion Decoder Module (CFDM) Experimental results show that SATNet outperforms both RGB and RGB-D mirror detection methods on all available mirror detection datasets.
  arXiv  Detail & Related papers  (2022-07-13T16:40:01Z)

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.