# GRIP: Gaussian Rendering as a Cross-Modal Bridge for Image-to-Point Cloud Registration

arXiv: https://arxiv.org/abs/2609.25966 · HTML: https://mlsanity.com/paper/2609.25966/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 45 references that are in the map.
- First posted on arXiv 22 Sep 2026.

## Builds on (most cited first, 29 of 29)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [On the Continuity of Rotation Representations in Neural Networks](https://mlsanity.com/paper/1812.07035/) (2018)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [Attention Augmented Convolutional Networks](https://mlsanity.com/paper/1904.09925/) (2019)
- [Deep Closest Point: Learning Representations for Point Cloud Registration](https://mlsanity.com/paper/1905.03304/) (2019)
- [PREDATOR: Registration of 3D Point Clouds with Low Overlap](https://mlsanity.com/paper/2011.13005/) (2020)
- [Geometric Transformer for Fast and Robust Point Cloud Registration](https://mlsanity.com/paper/2202.06688/) (2022)
- [Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registration](https://mlsanity.com/paper/1605.03344/) (2016)
- [CoFiNet: Reliable Coarse-to-fine Correspondences for Robust Point Cloud Registration](https://mlsanity.com/paper/2110.14076/) (2021)
- [EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimation](https://mlsanity.com/paper/2303.12787/) (2023)
- [Fast and Robust Iterative Closest Point](https://mlsanity.com/paper/2007.07627/) (2020)
- [2D3D-MatchNet: Learning to Match Keypoints Across 2D Image and 3D Point Cloud](https://mlsanity.com/paper/1904.09742/) (2019)
- [P2-Net: Joint Description and Detection of Local Features for Pixel and Point Matching](https://mlsanity.com/paper/2103.01055/) (2021)
- [2D3D-MATR: 2D-3D Matching Transformer for Detection-free Registration between Images and Point Clouds](https://mlsanity.com/paper/2308.05667/) (2023)
- [Deep Graph-based Spatial Consistency for Robust Non-rigid Point Cloud Registration](https://mlsanity.com/paper/2303.09950/) (2023)
- [Bridge 2D-3D: Uncertainty-aware Hierarchical Registration Network with Domain Alignment](https://mlsanity.com/paper/2504.01641/) (2025)
- [End-to-end 2D-3D Registration between Image and LiDAR Point Cloud for Vehicle Localization](https://mlsanity.com/paper/2306.11346/) (2023)
- [Diff2I2P: Differentiable Image-to-Point Cloud Registration with Diffusion Prior](https://mlsanity.com/paper/2507.06651/) (2025)
- [PFGS: High Fidelity Point Cloud Rendering via Feature Splatting](https://mlsanity.com/paper/2407.03857/) (2024)

## Abstract (arXiv)

This paper introduces GRIP, a pose-conditioned refinement framework for pixel-to-point matching and 2D to 3D registration. Given an initial coarse pose estimate, GRIP addresses the structural mismatch between grid based image descriptors and unordered point cloud descriptors by softly rendering learned 3D point features onto the image grid through Gaussian feature splatting. The rendered point derived feature map is then fused with image features by a pixel aligned transformer, enabling visual semantic and geometric cues to interact in a shared 2D representation. The refined features are decoded and propagated to finer resolutions for dense correspondence estimation and final pose refinement. Experiments on RGB D Scenes V2 and 7 Scenes demonstrate state of the art inlier ratio and competitive registration recall, with stronger performance under stricter evaluation thresholds.