mlsanityData to 7 Oct 2026

Reflection Generation for Composite Image Using Diffusion Model

arXiv 2604.02168 ↗First posted 2 Apr 2026cs.CVcited by 0

On the map: Diffusion models → 3D, point cloud and scene generation

Abstract (arXiv)

Image composition involves inserting a foreground object into the background while synthesizing environment-consistent effects such as shadows and reflections. Although shadow generation has been extensively studied, reflection generation remains largely underexplored. In this work, we focus on reflection generation. We inject the prior information of reflection placement and reflection appearance into foundation diffusion model. We also divide reflections into two types and adopt type-aware model design. To support training, we construct the first large-scale object reflection dataset DEROBA. Experiments demonstrate that our method generates reflections that are physically coherent and visually realistic, establishing a new benchmark for reflection generation.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 34 of its 37 references that are in the map. First posted on arXiv 2 Apr 2026.

Builds on

34 of 37 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025MirrorVerse: Pushing Diffusion Models to Realistically Reflect the World21 Apr
  2. 2025OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpainting11 Mar
  3. 2024Reflecting Reality: Enabling Diffusion Models to Produce Faithful Mirror Reflections23 Sep
  4. 2024Shadow Generation for Composite Image Using Diffusion model22 Mar

Other references · 30

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2023Segment Anythingcited by 8,158
  5. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,069
  6. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  7. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,274
  8. 2023IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Modelscited by 1,439
  9. 2025Qwen-Image Technical Reportcited by 973
  10. 2025FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Spacecited by 960
  11. 2022Paint by Example: Exemplar-based Image Editing with Diffusion Modelscited by 489
  12. 2025In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformercited by 199
18 more
  1. 2023A Task is Worth One Word: Learning with Task Prompts for High-Quality Versatile Image Inpaintingcited by 168
  2. 2019DoveNet: Deep Image Harmonization via Domain Verificationcited by 134
  3. 2025EasyControl: Adding Efficient and Flexible Control for Diffusion Transformercited by 118
  4. 2022The KFIoU Loss for Rotated Object Detectioncited by 73
  5. 2024IMPRINT: Generative Object Compositing by Learning Identity-Preserving Representationcited by 64
  6. 2021Making Images Real Again: A Comprehensive Survey on Deep Image Compositioncited by 63
  7. 2025Insert Anything: Image Insertion via In-Context Editing in DiTcited by 61
  8. 2021High-Resolution Image Harmonization via Collaborative Dual Transformationscited by 55
  9. 2023ControlCom: Controllable Image Composition using Diffusion Modelcited by 43
  10. 2023DreamEdit: Subject-driven Image Editingcited by 37
  11. 2023CustomNet: Zero-shot Object Customization with Variable-Viewpoints in Text-to-Image Diffusion Modelscited by 25
  12. 2025UniCombine: Unified Multi-Conditional Combination with Diffusion Transformercited by 25
  13. 2024PrimeComposer: Faster Progressively Combined Diffusion for Image Composition with Attention Steeringcited by 20
  14. 2024Thinking Outside the BBox: Unconstrained Generative Object Compositingcited by 19
  15. 2024ObjectMate: A Recurrence Prior for Object Insertion and Subject-Driven Generationcited by 16
  16. 2025ORIDa: Object-centric Real-world Image Composition Datasetcited by 11
  17. 2025CareCom: Generative Image Composition with Calibrated Reference Featurescited by 2
  18. 2024Diverse Image Harmonizationcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Reflection Separation from a Single Image via Joint Latent Diffusion
  2. 2026Reflection-aware Generative Novel View Synthesis
  3. 2026MirrorWorld: Taming Video Diffusion Models for Mirror Reflection Generation
  4. 2025Reflection Removal through Efficient Adaptation of Diffusion Transformers
  5. 2026MultiShadow: Multi-Object Shadow Generation for Image Compositing via Diffusion Model
  6. 2024Controllable Shadow Generation with Single-Step Diffusion Models from Synthetic Data
  7. 2026PhysReflect: Geometry and Perception Guided Diffusion for Physically-Plausible Mirror Reflections
  8. 2026From Synthesis to Removal: Physics-Grounded Reflection Simulation and Diffusion-Based Video Dereflection