mlsanityData to 14 Oct 2026

CanoVerse: 3D Object Scalable Canonicalization and Dataset for Generation and Pose

arXiv 2603.07144 ↗First posted 7 Mar 2026cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

3D learning systems implicitly assume that objects occupy a coherent reference frame. Nonetheless, in practice, every asset arrives with an arbitrary global rotation, and models are left to resolve directional ambiguity on their own. This persistent misalignment suppresses pose-consistent generation, and blocks the emergence of stable directional semantics. To address this issue, we construct methodName, a massive canonical 3D dataset of 320K objects over 1,156 categories -- an order-of-magnitude increase over prior work. At this scale, directional semantics become statistically learnable: Canoverse improves 3D generation stability, enables precise cross-modal 3D shape retrieval, and unlocks zero-shot point-cloud orientation estimation even for out-of-distribution data. This is achieved by a new canonicalization framework that reduces alignment from minutes to seconds per object via compact hypothesis generation and lightweight human discrimination, transforming canonicalization from manual curation into a high-throughput data generation pipeline. The Canoverse dataset will be publicly released upon acceptance. Project page: https://github.com/123321456-gif/Canoverse

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 36 of its 42 references that are in the map. First posted on arXiv 7 Mar 2026.

Builds on

36 of 42 references.

References · 36

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  4. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  5. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 770
  6. 2022Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Itemscited by 612
  7. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 495
  8. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Modelscited by 458
  9. 2024CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assetscited by 455
  10. 2023FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objectscited by 429
  11. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
  12. 2025Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generationcited by 356
24 more
  1. 2023OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generationcited by 326
  2. 2023Uni3D: Exploring Unified 3D Representation at Scalecited by 237
  3. 2024Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformercited by 210
  4. 2023ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understandingcited by 202
  5. 2023XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchiescited by 189
  6. 2025Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Materialcited by 165
  7. 2022OnePose: One-Shot Object Pose Estimation without CAD Modelscited by 157
  8. 2021Using Shape to Categorize: Low-Shot Learning with an Explicit Shape Biascited by 118
  9. 2025Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attentioncited by 110
  10. 2020Category Level Object Pose Estimation via Neural Analysis-by-Synthesiscited by 100
  11. 2024Dora: Sampling and Benchmarking for 3D Shape Variational Auto-Encoderscited by 98
  12. 2022Category-Level 6D Object Pose and Size Estimation using Self-Supervised Deep Prior Deformation Networkscited by 74
  13. 2023SecondPose: SE(3)-Consistent Dual-Stream Feature Fusion for Category-Level Pose Estimationcited by 53
  14. 2022Domain Randomization-Enhanced Depth Simulation and Restoration for Perceiving and Grasping Specular and Transparent Objectscited by 50
  15. 2024Omni6DPose: A Benchmark and Model for Universal 6D Object Pose Estimation and Trackingcited by 50
  16. 2025Any6D: Model-free 6D Pose Estimation of Novel Objectscited by 49
  17. 2024Orient Anything: Learning Robust Object Orientation Estimation from Rendering 3D Modelscited by 45
  18. 2024Instance-Adaptive and Geometric-Aware Keypoint Learning for Category-Level 6D Object Pose Estimationcited by 43
  19. 2023VI-Net: Boosting Category-level 6D Object Pose Estimation via Learning Decoupled Rotations on the Spherical Representationscited by 41
  20. 2022ConDor: Self-Supervised Canonicalization of 3D Pose for Partial Shapescited by 31
  21. 2022Object Level Depth Reconstruction for Category Level 6D Object Pose Estimation From Monocular RGB Imagecited by 30
  22. 2025Orientation Matters: Making 3D Generative Models Orientation-Alignedcited by 13
  23. 2025CleanPose: Category-Level Object Pose Estimation via Causal Learning and Knowledge Distillationcited by 10
  24. 2023ShapeMatcher: Self-Supervised Joint Shape Canonicalization, Segmentation, Retrieval and Deformationcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026CANIS: Generation-Assisted 3D Canonicalization via an Image-Semantic Bridgecited by 0