# Robust 3D Alignment of Generative Reconstructions via Partial Monocular Observations

arXiv: https://arxiv.org/abs/2607.00498 · HTML: https://mlsanity.com/paper/2607.00498/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 49 references that are in the map.
- First posted on arXiv 1 Jul 2026.

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

- [Depth Anything 3: Recovering the Visual Space from Any Views](https://mlsanity.com/paper/2511.10647/) (2025)
- [Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation](https://mlsanity.com/paper/1901.02970/) (2019)
- [PREDATOR: Registration of 3D Point Clouds with Low Overlap](https://mlsanity.com/paper/2011.13005/) (2020)
- [TEASER: Fast and Certifiable Point Cloud Registration](https://mlsanity.com/paper/2001.07715/) (2020)
- [RoboPoint: A Vision-Language Model for Spatial Affordance Prediction for Robotics](https://mlsanity.com/paper/2406.10721/) (2024)
- [SAM 3D: 3Dfy Anything in Images](https://mlsanity.com/paper/2511.16624/) (2025)
- [TripoSR: Fast 3D Object Reconstruction from a Single Image](https://mlsanity.com/paper/2403.02151/) (2024)
- [Deep Global Registration](https://mlsanity.com/paper/2004.11540/) (2020)
- [D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features](https://mlsanity.com/paper/2003.03164/) (2020)
- [CoFiNet: Reliable Coarse-to-fine Correspondences for Robust Point Cloud Registration](https://mlsanity.com/paper/2110.14076/) (2021)
- [Scan2CAD: Learning CAD Model Alignment in RGB-D Scans](https://mlsanity.com/paper/1811.11187/) (2018)
- [SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration](https://mlsanity.com/paper/2011.12149/) (2020)
- [KISS-ICP: In Defense of Point-to-Point ICP -- Simple, Accurate, and Robust Registration If Done the Right Way](https://mlsanity.com/paper/2209.15397/) (2022)
- [Graduated Non-Convexity for Robust Spatial Perception: From Non-Minimal Solvers to Global Outlier Rejection](https://mlsanity.com/paper/1909.08605/) (2019)
- [3D Registration with Maximal Cliques](https://mlsanity.com/paper/2305.10854/) (2023)
- [GeoTransformer: Fast and Robust Point Cloud Registration with Geometric Transformer](https://mlsanity.com/paper/2308.03768/) (2023)
- [MiMo-Embodied: X-Embodied Foundation Model Technical Report](https://mlsanity.com/paper/2511.16518/) (2025)
- [GraspGen: A Diffusion-based Framework for 6-DOF Grasping with On-Generator Training](https://mlsanity.com/paper/2507.13097/) (2025)
- [Decompositional Neural Scene Reconstruction with Generative Diffusion Prior](https://mlsanity.com/paper/2503.14830/) (2025)
- [PARE-Net: Position-Aware Rotation-Equivariant Networks for Robust Point Cloud Registration](https://mlsanity.com/paper/2407.10142/) (2024)
- [HiPose: Hierarchical Binary Surface Encoding and Correspondence Pruning for RGB-D 6DoF Object Pose Estimation](https://mlsanity.com/paper/2311.12588/) (2023)
- [ZeroGrasp: Zero-Shot Shape Reconstruction Enabled Robotic Grasping](https://mlsanity.com/paper/2504.10857/) (2025)
- [LiTAMIN2: Ultra Light LiDAR-based SLAM using Geometric Approximation applied with KL-Divergence](https://mlsanity.com/paper/2103.00784/) (2021)
- [Register Any Point: Scaling 3D Point Cloud Registration by Flow Matching](https://mlsanity.com/paper/2512.01850/) (2025)
- [Efficient and Robust Point Cloud Registration via Heuristics-guided Parameter Search](https://mlsanity.com/paper/2404.06155/) (2024)
- [ZeroReg: Zero-Shot Point Cloud Registration with Foundation Models](https://mlsanity.com/paper/2312.03032/) (2023)
- [CLIPPER+: A Fast Maximal Clique Algorithm for Robust Global Registration](https://mlsanity.com/paper/2402.15464/) (2024)
- [RARE: Refine Any Registration of Pairwise Point Clouds via Zero-Shot Learning](https://mlsanity.com/paper/2507.19950/) (2025)
- [PointRegGPT: Boosting 3D Point Cloud Registration using Generative Point-Cloud Pairs for Training](https://mlsanity.com/paper/2407.14054/) (2024)
- [Toward Zero-Shot Point Cloud Registration Across Diverse Scales, Scenes, and Sensor Setups](https://mlsanity.com/paper/2601.02759/) (2026)

## Abstract (arXiv)

Aligning generative 3D reconstructions with partial monocular observations is a critical but under-explored challenge in computer vision. This task is inherently ill-posed due to severe asymmetries between noisy, sparse monocular inputs and dense generative priors, whose scale ambiguity and geometric hallucinations, combined with the lack of initial overlap, render traditional registration pipelines ineffective. To resolve these issues, we propose a training-free and interpretable geometric alignment framework that grounds generative 3D priors via a 3D similarity transformation (Sim(3)), which can recover accurate metric scale and pose. Specifically, we introduce an explicit scale factor to resolve metric ambiguity and employ a coarse-to-fine alignment strategy, leveraging geometry-aware descriptors for robust initialization and a decoupled closed-form solver for precision refinement. In addition, we introduce a Hallucination Filtering operation to effectively suppress outliers caused by hallucinated geometry. To evaluate alignment performance under these extreme conditions, we introduce GenPMOAlign--Where2Place, a rigorous benchmark specifically designed for Generative-to-Partial Monocular Observational Alignment. Experiments demonstrate that our method achieves stable and accurate registration, substantially outperforming both classical geometric pipelines and state-of-the-art learning-based baselines. Code and the benchmark will be publicly released.