# Orient Anything V2: Unifying Orientation and Rotation Understanding

arXiv: https://arxiv.org/abs/2601.05573 · HTML: https://mlsanity.com/paper/2601.05573/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 59 references that are in the map.
- First posted on arXiv 9 Jan 2026.

## Builds on (most cited first, 30 of 42)

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Objaverse: A Universe of Annotated 3D Objects](https://mlsanity.com/paper/2212.08051/) (2022)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [Objaverse-XL: A Universe of 10M+ 3D Objects](https://mlsanity.com/paper/2307.05663/) (2023)
- [Structured 3D Latents for Scalable and Versatile 3D Generation](https://mlsanity.com/paper/2412.01506/) (2024)
- [ImageNet-21K Pretraining for the Masses](https://mlsanity.com/paper/2104.10972/) (2021)
- [Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation](https://mlsanity.com/paper/1901.02970/) (2019)
- [ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data](https://mlsanity.com/paper/2111.08897/) (2021)
- [FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects](https://mlsanity.com/paper/2312.08344/) (2023)
- [Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation](https://mlsanity.com/paper/2501.12202/) (2025)
- [Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlation](https://mlsanity.com/paper/2203.11483/) (2022)
- [COTR: Correspondence Transformer for Matching Across Images](https://mlsanity.com/paper/2103.14167/) (2021)
- [OnePose: One-Shot Object Pose Estimation without CAD Models](https://mlsanity.com/paper/2205.12257/) (2022)
- [Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild with Pose Annotations](https://mlsanity.com/paper/2012.09988/) (2020)
- [EPOS: Estimating 6D Pose of Objects with Symmetries](https://mlsanity.com/paper/2004.00605/) (2020)
- [Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild](https://mlsanity.com/paper/2007.12107/) (2020)
- [3DSRBench: A Comprehensive 3D Spatial Reasoning Benchmark](https://mlsanity.com/paper/2412.07825/) (2024)
- [Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Images](https://mlsanity.com/paper/2204.10776/) (2022)
- [OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Models](https://mlsanity.com/paper/2301.07673/) (2023)
- [Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridging](https://mlsanity.com/paper/2503.22236/) (2025)
- [Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views](https://mlsanity.com/paper/1505.05641/) (2015)
- [Learning Vision from Models Rivals Learning Vision from Data](https://mlsanity.com/paper/2312.17742/) (2023)
- [Diffusion Handles: Enabling 3D Edits for Diffusion Models by Lifting Activations to 3D](https://mlsanity.com/paper/2312.02190/) (2023)
- [Do Vision-Language Models Represent Space and How? Evaluating Spatial Frame of Reference Under Ambiguities](https://mlsanity.com/paper/2410.17385/) (2024)
- [Omni6DPose: A Benchmark and Model for Universal 6D Object Pose Estimation and Tracking](https://mlsanity.com/paper/2406.04316/) (2024)
- [SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation](https://mlsanity.com/paper/2502.13143/) (2025)

## Built on by (most cited first, 23 of 23)

- [HumanEgo: Zero-Shot Robot Learning from Minutes of Human Egocentric Videos](https://mlsanity.com/paper/2605.24934/) (2026)
- [HiSpatial: Taming Hierarchical 3D Spatial Understanding in Vision-Language Models](https://mlsanity.com/paper/2603.25411/) (2026)
- [Axolotl3D: a Unified Framework for Faithful 3D Shape Completion](https://mlsanity.com/paper/2607.20660/) (2026)
- [SATURN: Symbolic Spatial Reasoning for Multi-Perspective Grounding](https://mlsanity.com/paper/2606.22694/) (2026)
- [OmniView-Space: Reinforcing Spatial Reasoning via Multi-Perspective Spatial Mapping](https://mlsanity.com/paper/2607.00881/) (2026)
- [SpatialCLI: Learning to Reason With Spatial Tools, Then Without Them](https://mlsanity.com/paper/2607.27703/) (2026)
- [Geometry Matters: 3D Foundation Priors for Learning Semantic Correspondence](https://mlsanity.com/paper/2605.30093/) (2026)
- [Skill-3D: Evolving Scene-Aware Skills for Agentic 3D Spatial Reasoning](https://mlsanity.com/paper/2606.07436/) (2026)
- [SEMAGIC: Learning Semantically Consistent Deformable 3D Representations from In-the-Wild Images](https://mlsanity.com/paper/2605.27938/) (2026)
- [Every9D-21M: Large-Scale Real-World 9D Canonicalization of Everyday Objects](https://mlsanity.com/paper/2605.28270/) (2026)
- [BoxCtrl: 3D-Aware Visual Prompting for Geometric Image Editing](https://mlsanity.com/paper/2606.23270/) (2026)
- [Emergence of a Shared Canonical Object Frame from In-the-Wild Videos](https://mlsanity.com/paper/2606.30058/) (2026)
- [Global Pose Control for Generative View Synthesis in Normalized Object Coordinate Space](https://mlsanity.com/paper/2607.02712/) (2026)
- [UniPose9D: Universal Category-Agnostic Object Pose Estimation](https://mlsanity.com/paper/2607.09985/) (2026)
- [DiTailed: Ensuring Visual Object Consistency in Text-Image-to-Image Flow Matching Models](https://mlsanity.com/paper/2607.12539/) (2026)
- [SUFLECA: Scaling Up Feature Learning for CAD-to-image Alignment](https://mlsanity.com/paper/2607.15058/) (2026)
- [Geo3R: Mitigating Spatial Reasoning Hallucination in Multimodal Large Language Models](https://mlsanity.com/paper/2607.21085/) (2026)
- [CANIS: Generation-Assisted 3D Canonicalization via an Image-Semantic Bridge](https://mlsanity.com/paper/2608.07256/) (2026)
- [PoseAdapter: Dual-Stream 2.5D Controllable Image Generation for Complex Multi-Object Scenes](https://mlsanity.com/paper/2608.15583/) (2026)
- [Object-Uni: A Unified Model for Object-Centric Spatial Understanding and Controllable Generation](https://mlsanity.com/paper/2608.22757/) (2026)
- [Toward Comprehensive 3D Grounding: Orientation Grounding through Vision-Language Models](https://mlsanity.com/paper/2609.33109/) (2026)
- [LeRF: Learning Reference Coordinate Frames for Perspective Taking Reasoning](https://mlsanity.com/paper/2609.36219/) (2026)
- [SemCam: Semantic Camera Motion Control for Video Generation](https://mlsanity.com/paper/2610.05141/) (2026)

## Abstract (arXiv)

This work presents Orient Anything V2, an enhanced foundation model for unified understanding of object 3D orientation and rotation from single or paired images. Building upon Orient Anything V1, which defines orientation via a single unique front face, V2 extends this capability to handle objects with diverse rotational symmetries and directly estimate relative rotations. These improvements are enabled by four key innovations: 1) Scalable 3D assets synthesized by generative models, ensuring broad category coverage and balanced data distribution; 2) An efficient, model-in-the-loop annotation system that robustly identifies 0 to N valid front faces for each object; 3) A symmetry-aware, periodic distribution fitting objective that captures all plausible front-facing orientations, effectively modeling object rotational symmetry; 4) A multi-frame architecture that directly predicts relative object rotations. Extensive experiments show that Orient Anything V2 achieves state-of-the-art zero-shot performance on orientation estimation, 6DoF pose estimation, and object symmetry recognition across 11 widely used benchmarks. The model demonstrates strong generalization, significantly broadening the applicability of orientation estimation in diverse downstream tasks.