mlsanityData to 14 Oct 2026

DepR: Depth Guided Single-view Scene Reconstruction with Instance-level Diffusion

arXiv 2507.22825 ↗First posted 30 Jul 2025cs.CVcited by 23

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

Abstract (arXiv)

We propose DepR, a depth-guided single-view scene reconstruction framework that integrates instance-level diffusion within a compositional paradigm. Instead of reconstructing the entire scene holistically, DepR generates individual objects and subsequently composes them into a coherent 3D layout. Unlike previous methods that use depth solely for object layout estimation during inference and therefore fail to fully exploit its rich geometric information, DepR leverages depth throughout both training and inference. Specifically, we introduce depth-guided conditioning to effectively encode shape priors into diffusion models. During inference, depth further guides DDIM sampling and layout optimization, enhancing alignment between the reconstruction and the input image. Despite being trained on limited synthetic data, DepR achieves state-of-the-art performance and demonstrates strong generalization in single-view scene reconstruction, as shown through evaluations on both synthetic and real-world datasets.

Key facts. Cited by 23 papers in the map (data through 14 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 66 of its 69 references that are in the map. First posted on arXiv 30 Jul 2025.

Builds on

66 of 69 references.

Closest ancestors · 12

Same direction, newest first

  1. 2024CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets30 May
  2. 2024Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image30 May
  3. 2024Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformer23 May
  4. 2024SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusion18 Mar
  5. 2024Bayesian Diffusion Models for 3D Shape Reconstruction11 Mar
  6. 2023EpiDiff: Enhancing Multi-View Synthesis via Localized Epipolar-Constrained Diffusion11 Dec
  7. 2023One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion14 Nov
  8. 2023Wonder3D: Single Image to 3D using Cross-Domain Diffusion23 Oct
  9. 2023SyncDreamer: Generating Multiview-consistent Images from a Single-view Image7 Sep
  10. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization29 Jun
  11. 2023Zero-1-to-3: Zero-shot One Image to 3D Object20 Mar
  12. 20223D Neural Field Generation using Triplane Diffusion30 Nov

Other references · 54

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2020Denoising Diffusion Implicit Modelscited by 9,781
  4. 2023Segment Anythingcited by 8,234
  5. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  6. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  7. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  8. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  9. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  10. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,614
  11. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
  12. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,581
38 more
  1. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,540
  2. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,274
  3. 2024Grounded SAM: Assembling Open-World Models for Diverse Visual Taskscited by 929
  4. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 849
  5. 2023Objaverse-XL: A Universe of 10M+ 3D Objectscited by 774
  6. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 739
  7. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 470
  8. 2024InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Modelscited by 433
  9. 2024Depth Pro: Sharp Monocular Metric Depth in Less Than a Secondcited by 404
  10. 2023Shap-E: Generating Conditional 3D Implicit Functionscited by 385
  11. 20203D-FRONT: 3D Furnished Rooms with layOuts and semaNTicscited by 380
  12. 2021Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scanscited by 336
  13. 20203D-FUTURE: 3D Furniture shape with TextUREcited by 311
  14. 2024GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generationcited by 301
  15. 2023Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with Transformerscited by 258
  16. 2023Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representationcited by 228
  17. 2018Pix3D: Dataset and Methods for Single-Image 3D Shape Modelingcited by 218
  18. 2024CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Modelcited by 215
  19. 2020Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Imagecited by 172
  20. 2018Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps with Accurate Object Boundariescited by 145
  21. 2021Holistic 3D Scene Understanding from a Single Image with Implicit Representationcited by 94
  22. 2024BlockFusion: Expandable 3D Scene Generation using Latent Tri-plane Extrapolationcited by 83
  23. 2016IM2CADcited by 78
  24. 2021Panoptic 3D Scene Reconstruction From a Single RGB Imagecited by 70
  25. 2018Holistic 3D Scene Parsing and Reconstruction from a Single RGB Imagecited by 69
  26. 2021ROCA: Robust CAD Model Retrieval and Alignment from a Single Imagecited by 67
  27. 2020Mask2CAD: 3D Shape Prediction by Learning to Segment and Retrievecited by 65
  28. 2024Gen3DSR: Generalizable 3D Scene Reconstruction via Divide and Conquer from a Single Viewcited by 61
  29. 2024ComboVerse: Compositional 3D Assets Creation Using Spatially-Aware Diffusion Guidancecited by 59
  30. 2023DiffCAD: Weakly-Supervised Probabilistic CAD Model Retrieval and Alignment from an RGB Imagecited by 48
  31. 2024REPARO: Compositional 3D Assets Generation with Differentiable 3D Layout Alignmentcited by 45
  32. 2022Towards High-Fidelity Single-view Holistic Reconstruction of Indoor Scenescited by 44
  33. 2021Patch2CAD: Patchwise Embedding Learning for In-the-Wild Shape Retrieval from a Single Imagecited by 39
  34. 2023Single-view 3D Scene Reconstruction with High-fidelity Shape and Texturecited by 37
  35. 2022CASA: Category-agnostic Skeletal Animal Reconstructioncited by 35
  36. 2024Zero-Shot Scene Reconstruction from Single Images with Deep Prior Assemblycited by 35
  37. 2024Frankenstein: Generating Semantic-Compositional 3D Scenes in One Tri-Planecited by 26
  38. 2023PSDR-Room: Single Photo to Scene using Differentiable Renderingcited by 23

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 8; 2026: 15.

23 papers.

Sort:

By area:

  1. 2025SceneGen: Single-Image 3D Scene Generation in One Feedforward Passcited by 54
  2. 2025VertexRegen: Mesh Generation with Continuous Level of Detailcited by 16
  3. 2025OverLayBench: A Benchmark for Layout-to-Image Generation with Dense Overlapscited by 10
  4. 20253D-RE-GEN: 3D Reconstruction of Indoor Scenes with a Generative Frameworkcited by 10
  5. 2026REST3D: Reconstructing Physically Stable 3D Scenes from a Single Imagecited by 6
  6. 2026One Video, One World: Turning Monocular Video into Physical 4D Scenescited by 6
  7. 2025C3Editor: Achieving Controllable Consistency in 2D Model for 3D Editingcited by 5
  8. 2025CVP: Central-Peripheral Vision-Inspired Multimodal Model for Spatial Reasoningcited by 5
  9. 2026PixARMesh: Autoregressive Mesh-Native Single-View Scene Reconstructioncited by 3
  10. 2026AdaSFormer: Adaptive Serialized Transformers for Monocular Semantic Scene Completion from Indoor Environmentscited by 3
  11. 2026φ-Scene: Physically Grounded Image-to-3D Scene Reconstructioncited by 3
  12. 2026JRM: Joint Reconstruction Model for Multiple Objects without Alignmentcited by 2
11 more
  1. 2026PhyMix: Towards Physically Consistent Single-Image 3D Indoor Scene Generation with Implicit--Explicit Optimizationcited by 2
  2. 20263D Generation for Embodied AI and Robotic Simulation: A Surveycited by 1
  3. 2026Pose-Aware Diffusion for 3D Generationcited by 1
  4. 2026OCH3R: Object-Centric Holistic 3D Reconstructioncited by 1
  5. 2026InfiniSplat: Implicit Gaussian Decoding for Large-Baseline Monocular View Synthesiscited by 1
  6. 2025CC-FMO: Camera-Conditioned Zero-Shot Single Image to 3D Scene Generation with Foundation Model Orchestrationcited by 0
  7. 2025Gaussian Swaying: Surface-Based Framework for Aerodynamic Simulation with 3D Gaussianscited by 0
  8. 2026FurnSet: Exploiting Repeats for 3D Scene Reconstructioncited by 0
  9. 2026Can Single-View Mesh Reconstruction Generalize to Robot Camera Rotation?cited by 0
  10. 2026ORCA: Occlusion-Aware Refinement and Completion for Novel View Synthesiscited by 0
  11. 2026Fysiverse-3D-Vision Technical Report: Generating Executable 3D Worlds from Images through Unified Spatial Reasoningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Dream-to-Recon: Monocular 3D Reconstruction with Diffusion-Depth Distillation from Single Images
  2. 2024Coherent 3D Scene Diffusion From a Single RGB Image
  3. 2024Diffusion Models for Monocular Depth Estimation: Overcoming Challenging Conditions
  4. 2025Lightweight and Accurate Multi-View Stereo with Confidence-Aware Diffusion Model
  5. 2026ARDepth: Auto-regressive Monocular Depth Estimation with Progressive Visual Conditioning
  6. 2024MVDiffusion++: A Dense High-resolution Multi-view Diffusion Model for Single or Sparse-view 3D Object Reconstruction
  7. 2025Decompositional Neural Scene Reconstruction with Generative Diffusion Prior
  8. 2024VistaDream: Sampling multiview consistent images for single-view scene reconstruction