AnchoredDream: Zero-Shot 360deg Indoor Scene Generation from a Single View via Geometric Grounding
Not on the map. Why?
Abstract (arXiv)
Single-view indoor scene generation plays a crucial role in a range of real-world applications. However, generating a complete 360deg scene from a single image remains a highly ill-posed and challenging problem. Recent approaches have made progress by leveraging diffusion models and depth estimation networks, yet they still struggle to maintain appearance consistency and geometric plausibility under large viewpoint changes, limiting their effectiveness in full-scene generation. To address this, we propose AnchoredDream, a novel zero-shot pipeline that anchors 360deg scene generation on high-fidelity geometry via an appearance-geometry mutual boosting mechanism. Given a single-view image, our method first performs appearance-guided geometry generation to construct a reliable 3D scene layout. Then, we progressively generate the complete scene through a series of modules: warp-and-inpaint, warp-and-refine, post-optimization, and a novel Grouting Block, which ensures seamless transitions between the input view and generated regions. Extensive experiments demonstrate that AnchoredDream outperforms existing methods by a large margin in both appearance consistency and geometric plausibility--all in a zero-shot manner. Our results highlight the potential of geometric grounding for high-quality, zero-shot single-view scene generation.
Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 58 of its 63 references that are in the map. First posted on arXiv 23 Jan 2026.
Builds on
58 of 63 references.
References · 58
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
- 2020Denoising Diffusion Probabilistic Modelscited by 20,851
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
- 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
- 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
- 2023Visual Instruction Tuningcited by 7,792
- 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
- 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
- 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
- 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
- 2024GPT-4o System Cardcited by 4,467
- 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,310
38 more
- 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,848
- 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
- 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,522
- 2024Depth Anything V2cited by 1,385
- 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,354
- 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,346
- 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,207
- 2024CAT3D: Create Anything in 3D with Multi-View Diffusion Modelscited by 425
- 2024Depth Pro: Sharp Monocular Metric Depth in Less Than a Secondcited by 395
- 2024ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesiscited by 392
- 2023LayoutGPT: Compositional Visual Planning and Generation with Large Language Modelscited by 337
- 2023Common Diffusion Noise Schedules and Sample Steps are Flawedcited by 308
- 2023Holodeck: Language Guided Generation of 3D Embodied AI Environmentscited by 257
- 2023GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Modelscited by 255
- 2023Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Modelscited by 245
- 2023Text2Tex: Text-driven Texture Synthesis via Diffusion Modelscited by 234
- 2023LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenescited by 228
- 2020Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contextscited by 210
- 2023MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusioncited by 210
- 2023NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusioncited by 179
- 2019LayoutGAN: Generating Graphic Layouts with Wireframe Discriminatorscited by 130
- 2020LayoutTransformer: Layout Generation and Completion with Self-attentioncited by 122
- 2023Text2NeRF: Text-Driven 3D Scene Generation with Neural Radiance Fieldscited by 122
- 2019LayoutVAE: Stochastic Scene Layout Generation From a Label Setcited by 119
- 2024InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Priorcited by 110
- 2024RealmDreamer: Text-Driven 3D Scene Generation with Inpainting and Depth Diffusioncited by 109
- 2018LayoutNet: Reconstructing the 3D Room Layout from a Single RGB Imagecited by 94
- 2024LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Modelscited by 94
- 2023AnyHome: Open-Vocabulary Generation of Structured and Textured 3D Homescited by 81
- 2024DreamScene360: Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splattingcited by 81
- 2023SceneDreamer: Unbounded 3D Scene Generation from 2D Image Collectionscited by 72
- 2024GenWarp: Single Image to Novel Views with Semantic-Preserving Generative Warpingcited by 72
- 2021BLT: Bidirectional Layout Transformer for Controllable Layout Generationcited by 69
- 2024LayerPano3D: Layered 3D Panorama for Hyper-Immersive Scene Generationcited by 53
- 2022RGBD2: Generative Scene Synthesis via Incremental View Inpainting using RGBD Diffusion Modelscited by 45
- 2024VistaDream: Sampling multiview consistent images for single-view scene reconstructioncited by 38
- 2024Architect: Generating Vivid and Interactive 3D Scenes with Hierarchical 2D Inpaintingcited by 37
- 2025FlexWorld: Progressively Expanding 3D Scenes for Flexiable-View Synthesiscited by 37
50 most cited of 58 All 58 (JSON)
Built on by
Citing papers per year: 2026: 5.
5 papers.
- 2026MoRe: Motion-aware Feed-forward 4D Reconstruction Transformercited by 8
- 2026PhysX-Omni: Unified Simulation-Ready Physical 3D Generation for Rigid, Deformable, and Articulated Objectscited by 7
- 2026CFG-Ctrl: Control-Based Classifier-Free Diffusion Guidancecited by 3
- 2026Pano2World: End-to-End 3D Generation via Unified Multi-View Sequencescited by 2
- 2026Apple-π: Benchmarking Thinking with Video Towards Law-Grounded Physical Intelligencecited by 1
- 2026Apple-π: Benchmarking Thinking with Video Towards Law-Grounded Physical Intelligence17 Jul 2026
- 2026Pano2World: End-to-End 3D Generation via Unified Multi-View Sequences1 Jul 2026
- 2026PhysX-Omni: Unified Simulation-Ready Physical 3D Generation for Rigid, Deformable, and Articulated Objects20 May 2026
- 2026MoRe: Motion-aware Feed-forward 4D Reconstruction Transformer5 Mar 2026
- 2026CFG-Ctrl: Control-Based Classifier-Free Diffusion Guidance3 Mar 2026
Similar, not cited
Close in wording, no citation either way
- 2026InSpace: Structure-Aware 3D Indoor Scene Generation from a Single 360deg Image
- 2026Scene Generation at Absolute Scale: Utilizing Semantic and Geometric Guidance From Text for Accurate and Interpretable 3D Indoor Scene Generation
- 2024SceneCraft: Layout-Guided 3D Scene Generation
- 2023DiffInDScene: Diffusion-based High-Quality 3D Indoor Scene Generation
- 2024Invisible Stitch: Generating Smooth 3D Scenes with Depth Inpainting
- 2023ZeroNVS: Zero-Shot 360-Degree View Synthesis from a Single Image
- 2025MVRoom: Controllable 3D Indoor Scene Generation with Multi-View Diffusion Models
- 2023RoomDreamer: Text-Driven 3D Indoor Scene Synthesis with Coherent Geometry and Texture