mlsanityData to 14 Oct 2026

Orientation Matters: Making 3D Generative Models Orientation-Aligned

arXiv 2506.08640 ↗First posted 10 Jun 2025cs.CVcited by 13

Not on the map. Why?

Abstract (arXiv)

Humans intuitively perceive object shape and orientation from a single image, guided by strong priors about canonical poses. However, existing 3D generative models often produce misaligned results due to inconsistent training data, limiting their usability in downstream tasks. To address this gap, we introduce the task of orientation-aligned 3D object generation: producing 3D objects from single images with consistent orientations across categories. To facilitate this, we construct Objaverse-OA, a dataset of 14,832 orientation-aligned 3D models spanning 1,008 categories. Leveraging Objaverse-OA, we fine-tune two representative 3D generative models based on multi-view diffusion and 3D variational autoencoder frameworks to produce aligned objects that generalize well to unseen objects across various categories. Experimental results demonstrate the superiority of our method over post-hoc alignment approaches. Furthermore, we showcase downstream applications enabled by our aligned object generation, including zero-shot object orientation estimation via analysis-by-synthesis and efficient arrow-based object rotation manipulation.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 59 of its 64 references that are in the map. First posted on arXiv 10 Jun 2025.

Builds on

59 of 64 references.

References · 59

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  5. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  6. 2023Segment Anythingcited by 8,234
  7. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  8. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,025
  9. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  10. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
  11. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,540
  12. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,290
38 more
  1. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,219
  2. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,205
  3. 2022Diffusion Models in Vision: A Surveycited by 1,015
  4. 2023MVDream: Multi-view Diffusion for 3D Generationcited by 938
  5. 2023DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creationcited by 843
  6. 2023Objaverse-XL: A Universe of 10M+ 3D Objectscited by 774
  7. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 770
  8. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 739
  9. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 689
  10. 2023Wonder3D: Single Image to 3D using Cross-Domain Diffusioncited by 689
  11. 2023SyncDreamer: Generating Multiview-consistent Images from a Single-view Imagecited by 645
  12. 2022Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Itemscited by 612
  13. 2022Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generationcited by 597
  14. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  15. 2023Zero123++: a Single Image to Consistent Multi-view Diffusion Base Modelcited by 521
  16. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 495
  17. 2024CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assetscited by 455
  18. 2023FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objectscited by 429
  19. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
  20. 2024UniDepth: Universal Monocular Metric Depth Estimationcited by 382
  21. 2025Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generationcited by 356
  22. 2023Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Priorcited by 343
  23. 2024GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generationcited by 301
  24. 2023LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matchingcited by 290
  25. 2023ImageDream: Image-Prompt Multi-view Diffusion for 3D Generationcited by 257
  26. 2023DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Modelcited by 214
  27. 2020Shape Prior Deformation for Categorical 6D Object Pose and Size Estimationcited by 161
  28. 2022OnePose: One-Shot Object Pose Estimation without CAD Modelscited by 157
  29. 2020Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wildcited by 142
  30. 2021Using Shape to Categorize: Low-Shot Learning with an Explicit Shape Biascited by 118
  31. 2023Viewset Diffusion: (0-)Image-Conditioned 3D Generative Models from 2D Datacited by 113
  32. 2020Category Level Object Pose Estimation via Neural Analysis-by-Synthesiscited by 100
  33. 2022Category-Level 6D Object Pose and Size Estimation using Self-Supervised Deep Prior Deformation Networkscited by 74
  34. 2023DiffusionLight: Light Probes for Free by Painting a Chrome Ballcited by 64
  35. 2024LT3SD: Latent Trees for 3D Scene Diffusioncited by 55
  36. 2025Amodal3R: Amodal 3D Reconstruction from Occluded 2D Imagescited by 54
  37. 2025Any6D: Model-free 6D Pose Estimation of Novel Objectscited by 49
  38. 2024Orient Anything: Learning Robust Object Orientation Estimation from Rendering 3D Modelscited by 45

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 10.

13 papers.

Sort:

By area:

  1. 2026HY3D-Bench: Generation of 3D Assetscited by 11
  2. 2025CUPID: Generative 3D Reconstruction via Joint Object and Pose Modelingcited by 8
  3. 2026One Video, One World: Turning Monocular Video into Physical 4D Scenescited by 6
  4. 2025Droplet3D: Commonsense Priors from Videos Facilitate 3D Generationcited by 1
  5. 2026VIAFormer: Voxel-Image Alignment Transformer for High-Fidelity Voxel Refinementcited by 1
  6. 2026CanoVerse: 3D Object Scalable Canonicalization and Dataset for Generation and Posecited by 1
  7. 2026FlowObject: Flow Steering for Bridging Generative Priors and Reconstruction Fidelitycited by 1
  8. 2026EditVerse3D: High-Quality 3D Object Editing with Region-Aware Learningcited by 1
  9. 2025Twist and Compute: The Cost of Pose in 3D Generative Diffusioncited by 0
  10. 2026Every9D-21M: Large-Scale Real-World 9D Canonicalization of Everyday Objectscited by 0
  11. 2026Emergence of a Shared Canonical Object Frame from In-the-Wild Videoscited by 0
  12. 2026Global Pose Control for Generative View Synthesis in Normalized Object Coordinate Spacecited by 0
1 more
  1. 2026CANIS: Generation-Assisted 3D Canonicalization via an Image-Semantic Bridgecited by 0