Every9D-22M: Large-Scale Real-World 9D Canonicalization of Everyday Objects
cs.CV
Submitted: 2026-05-27
Updated: 2026-11-02
License: http://creativecommons.org/licenses/by/4.0/
The gist: Estimating the 9D pose of everyday objects from a single real-world image remains challenging.
Terminology
Abstract
Estimating the 9D pose of everyday objects from a single real-world image remains challenging. This is largely due to the lack of large-scale supervision. Most existing datasets either rely heavily on synthetic renderings or provide limited coverage of real-world objects. We address this gap with Every9D-22M, a dataset of 9D pose annotations for 22.8M real-world images from 114K object-centric videos spanning 630 everyday object categories, making it nearly two orders of magnitude larger than any prior real-world 9D pose dataset in at least one of category, object, or image count. To achieve this scale, we leverage object-centric videos by reconstructing object-level point clouds via multi-view geometry and aligning similar instances into a shared canonical coordinate frame. Canonical poses are manually annotated for only a small set of reference objects (fewer than 0.01% of all images) and propagated to the remaining instances via cross-instance alignment. All propagated canonical poses are then verified from multiple viewpoints. We further introduce cross-category orientation rules that induce category-level symmetries, enabling symmetry-aware evaluation. Beyond establishing dedicated training and evaluation splits as a benchmark for 9D pose foundation models, we show that training on Every9D-22M generalizes better to other datasets than training on existing datasets, and outperforms prior foundation models in rotation accuracy on all benchmarks except the viewpoint-biased ImageNet3D, where joint training with ImageNet3D surpasses them as well. Data and code are available at https://github.com/GenIntel/Every9D.
Sources
- WildDet3D: Scaling Promptable 3D Detection in the Wild
- Depth Anything 3: Recovering the Visual Space from Any Views
- Decoupled Weight Decay Regularization
- Orientation Matters: Making 3D Generative Models Orientation-Aligned
- DINOv2: Learning Robust Visual Features without Supervision
- DINOv3
- Orient Anything: Learning Robust Object Orientation Estimation from Rendering 3D Models
- Orient Anything V2: Unifying Orientation and Rotation Understanding
- LitePT: Lighter Yet Stronger Point Transformer
- Beyond 'Templates': Category-Agnostic Object Pose, Size, and Shape Estimation from a Single View
- TexVerse: A Universe of 3D Objects with High-Resolution Textures
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs