mlsanityData to 7 Oct 2026

Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridging

arXiv 2503.22236 ↗First posted 28 Mar 2025cs.GR cs.CVcited by 95

Not on the map. Why?

Abstract (arXiv)

With the growing demand for high-fidelity 3D models from 2D images, existing methods still face significant challenges in accurately reproducing fine-grained geometric details due to limitations in domain gaps and inherent ambiguities in RGB images. To address these issues, we propose Hi3DGen, a novel framework for generating high-fidelity 3D geometry from images via normal bridging. Hi3DGen consists of three key components: (1) an image-to-normal estimator that decouples the low-high frequency image pattern with noise injection and dual-stream training to achieve generalizable, stable, and sharp estimation; (2) a normal-to-geometry learning approach that uses normal-regularized latent diffusion learning to enhance 3D geometry generation fidelity; and (3) a 3D data synthesis pipeline that constructs a high-quality dataset to support training. Extensive experiments demonstrate the effectiveness and superiority of our framework in generating rich geometric details, outperforming state-of-the-art methods in terms of fidelity. Our work provides a new direction for high-fidelity 3D geometry generation from images by leveraging normal maps as an intermediate representation.

Key facts. Cited by 95 papers in the map (data through 7 Oct 2026). Builds on 71 of its 85 references that are in the map. First posted on arXiv 28 Mar 2025.

Builds on

71 of 85 references.

References · 71

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  4. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  5. 2022Scalable Diffusion Models with Transformerscited by 5,931
  6. 2022Classifier-Free Diffusion Guidancecited by 5,717
  7. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  8. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
  9. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  10. 2021Vision Transformers for Dense Predictioncited by 1,789
  11. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,522
  12. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,204
38 more
  1. 2023Objaverse-XL: A Universe of 10M+ 3D Objectscited by 767
  2. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 742
  3. 2023Wonder3D: Single Image to 3D using Cross-Domain Diffusioncited by 682
  4. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 646
  5. 2022Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Itemscited by 601
  6. 2022Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generationcited by 597
  7. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  8. 2020PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitizationcited by 521
  9. 2014Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecturecited by 483
  10. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 467
  11. 2024CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assetscited by 444
  12. 2020Modular Primitives for High-Performance Differentiable Renderingcited by 439
  13. 2024InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Modelscited by 421
  14. 2024Depth Pro: Sharp Monocular Metric Depth in Less Than a Secondcited by 395
  15. 2022DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Modelscited by 376
  16. 2021ABO: Dataset and Benchmarks for Real-World 3D Object Understandingcited by 360
  17. 2025Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generationcited by 342
  18. 2021Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scanscited by 336
  19. 2023OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generationcited by 324
  20. 20203D-FUTURE: 3D Furniture shape with TextUREcited by 306
  21. 2021ICON: Implicit Clothed humans Obtained from Normalscited by 283
  22. 2024GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Imagecited by 283
  23. 2023MVImgNet: A Large-scale Dataset of Multi-view Imagescited by 219
  24. 2024Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformercited by 210
  25. 2025TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Modelscited by 204
  26. 2022ECON: Explicit Clothed humans Optimized via Normal integrationcited by 199
  27. 2023RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3Dcited by 168
  28. 2024Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Predictioncited by 163
  29. 2023Habitat Synthetic Scenes Dataset (HSSD-200): An Analysis of 3D Scene Scale and Realism Tradeoffs for ObjectGoal Navigationcited by 162
  30. 2024StableNormal: Reducing Diffusion Variance for Stable and Sharp Normalcited by 153
  31. 2019Pattern-Affinitive Propagation across Depth, Surface Normal and Semantic Segmentationcited by 141
  32. 2024Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Imagecited by 132
  33. 2022NeuRIS: Neural Reconstruction of Indoor Scenes Using Normal Priorscited by 125
  34. 2024Rethinking Inductive Biases for Surface Normal Estimationcited by 122
  35. 2021Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimationcited by 116
  36. 2024Dora: Sampling and Benchmarking for 3D Shape Variational Auto-Encoderscited by 93
  37. 2023HumanNorm: Learning Normal Diffusion Model for High-quality and Realistic 3D Human Generationcited by 88
  38. 2024What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?cited by 74

50 most cited of 71 All 71 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 42; 2026: 53.

95 papers.

Sort:

By area:

  1. 2025SAM 3D: 3Dfy Anything in Imagescited by 230
  2. 2025Native and Compact Structured Latents for 3D Generationcited by 157
  3. 2025Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attentioncited by 103
  4. 2025PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformerscited by 78
  5. 2025Efficient Part-level 3D Object Generation via Dual Volume Packingcited by 47
  6. 2025Ultra3D: Efficient and High-Fidelity 3D Generation with Part Attentioncited by 43
  7. 2025LATTICE: Democratize High-Fidelity 3D Generation at Scalecited by 41
  8. 2025ShapeLLM-Omni: A Native Multimodal LLM for 3D Generation and Understandingcited by 34
  9. 2025AutoPartGen: Autogressive 3D Part Generation and Discoverycited by 33
  10. 2025ReconViaGen: Towards Accurate Multi-view 3D Object Reconstruction via Generationcited by 30
  11. 2025NANO3D: A Training-Free Approach for Efficient 3D Editing Without Maskscited by 29
  12. 2025DreamArt: Generating Interactable Articulated Objects from a Single Imagecited by 25
38 more
  1. 2026Orient Anything V2: Unifying Orientation and Rotation Understandingcited by 22
  2. 2025UniLat3D: Geometry-Appearance Unified Latents for Single-Stage 3D Generationcited by 20
  3. 2025ORV: 4D Occupancy-centric Robot Video Generationcited by 16
  4. 2025UltraShape 1.0: High-Fidelity 3D Shape Generation via Scalable Geometric Refinementcited by 16
  5. 2025QuadGPT: Native Quadrilateral Mesh Generation with Autoregressive Modelscited by 11
  6. 2025Light-X: Generative 4D Video Rendering with Camera and Illumination Controlcited by 11
  7. 2025CoRe3D: Collaborative Reasoning as a Foundation for 3D Intelligencecited by 9
  8. 2025Diffusion Knows Transparency: Repurposing Video Diffusion for Transparent Object Depth and Normal Estimationcited by 9
  9. 20253D Arena: An Open Platform for Generative 3D Evaluationcited by 8
  10. 2025CUPID: Generative 3D Reconstruction via Joint Object and Pose Modelingcited by 8
  11. 2025MeshRipple: Structured Autoregressive Generation of Artist-Meshescited by 8
  12. 2025MVPainter: Accurate and Detailed 3D Texture Generation via Multi-View Diffusion with Geometric Controlcited by 7
  13. 2026HVG-3D: Bridging Real and Simulation Domains for 3D-Conditional Hand-Object Interaction Video Synthesiscited by 7
  14. 2025DiMeR: Disentangled Mesh Reconstruction Modelcited by 6
  15. 2025Part-X-MLLM: Part-aware 3D Multimodal Large Language Modelcited by 6
  16. 2025ViewCraft3D: High-Fidelity and View-Consistent 3D Vector Graphics Synthesiscited by 5
  17. 2025PhysGen: Physically Grounded 3D Shape Generation for Industrial Designcited by 5
  18. 2025MoCA: Mixture-of-Components Attention for Scalable Compositional 3D Generationcited by 5
  19. 2026LottieGPT: Tokenizing Vector Animation for Autoregressive Generationcited by 5
  20. 2025ZeroScene: A Zero-Shot Framework for 3D Scene Generation from a Single Image and Controllable Texture Editingcited by 4
  21. 2025Faithful Contouring: Near-Lossless 3D Voxel Representation Free from Iso-surfacecited by 4
  22. 2025NeAR: Coupled Neural Asset-Renderer Stackcited by 4
  23. 2026MorphAny3D: Unleashing the Power of Structured Latent in 3D Morphingcited by 4
  24. 2025Fast3Dcache: Training-free 3D Geometry Synthesis Accelerationcited by 3
  25. 2026Mix3R: Mixing Feed-forward Reconstruction and Generative 3D Priors for Joint Multi-view Aligned 3D Reconstruction and Pose Estimationcited by 3
  26. 2025SAT-SKYLINES: 3D Building Generation from Satellite Imagery and Coarse Geometric Priorscited by 2
  27. 2025Few-step Flow for 3D Generation via Marginal-Data Transport Distillationcited by 2
  28. 2025FlexAvatar: Flexible Large Reconstruction Model for Animatable Gaussian Head Avatars with Detailed Deformationcited by 2
  29. 2026Monocular Normal Estimation via Shading Sequence Estimationcited by 2
  30. 2026Mesh-Pro: Asynchronous Advantage-guided Ranking Preference Optimization for Artist-style Quadrilateral Mesh Generationcited by 2
  31. 2026TopoMesh: High-Fidelity Mesh Autoencoding via Topological Unificationcited by 2
  32. 2026Hitem3D 2.0: Multi-View Guided Native 3D Texture Generationcited by 2
  33. 2026Grasp in Gaussians: Fast Monocular Reconstruction of Dynamic Hand-Object Interactionscited by 2
  34. 2026AnimateAnyMesh++: A Flexible Feed-Forward Framework for High-Fidelity Text-Driven Mesh Animationcited by 2
  35. 2026WorldAct: Activating Monolithic 3D Worlds into Interactive-Ready Object-Centric Scenescited by 2
  36. 2026EVA01: Unified Native 3D Understanding and Generation via Mixture-of-Transformerscited by 2
  37. 2026ROAR-3D: Routing Arbitrary Views for High-Fidelity 3D Generationcited by 2
  38. 2026TriFlow: Generating Artist-Like 3D Mesh Topology via Nearest-Vertex Vector Fieldscited by 2

50 most cited of 95 All 95 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Hi3D: Pursuing High-Resolution Image-to-3D Generation with Video Diffusion Models
  2. 20243D-Adapter: Geometry-Consistent Multi-View Diffusion for High-Quality 3D Generation
  3. 2024Gen-3Diffusion: Realistic Image-to-3D Generation via 2D & 3D Diffusion Synergy
  4. 2025HierOctFusion: Multi-scale Octree-based 3D Shape Generation via Part-Whole-Hierarchy Message Passing
  5. 2024Cycle3D: High-quality and Consistent Image-to-3D Generation via Generation-Reconstruction Cycle
  6. 2024Sculpt3D: Multi-View Consistent Text-to-3D Generation with Sparse 3D Prior
  7. 2023Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior
  8. 2024Ouroboros3D: Image-to-3D Generation via 3D-aware Recursive Diffusion