mlsanityData to 14 Oct 2026

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

arXiv 2609.25966 ↗First posted 22 Sep 2026cs.CVcited by 0

Not on the map. Why?

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.

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

29 of 45 references.

References · 29

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  5. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  6. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  7. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  8. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  9. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,443
  10. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,320
  11. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,214
  12. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
17 more
  1. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 984
  2. 2019Attention Augmented Convolutional Networkscited by 363
  3. 2019Deep Closest Point: Learning Representations for Point Cloud Registrationcited by 321
  4. 2020PREDATOR: Registration of 3D Point Clouds with Low Overlapcited by 290
  5. 2022Geometric Transformer for Fast and Robust Point Cloud Registrationcited by 202
  6. 2016Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registrationcited by 159
  7. 2021CoFiNet: Reliable Coarse-to-fine Correspondences for Robust Point Cloud Registrationcited by 152
  8. 2023EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimationcited by 79
  9. 2020Fast and Robust Iterative Closest Pointcited by 67
  10. 20192D3D-MatchNet: Learning to Match Keypoints Across 2D Image and 3D Point Cloudcited by 62
  11. 2021P2-Net: Joint Description and Detection of Local Features for Pixel and Point Matchingcited by 42
  12. 20232D3D-MATR: 2D-3D Matching Transformer for Detection-free Registration between Images and Point Cloudscited by 27
  13. 2023Deep Graph-based Spatial Consistency for Robust Non-rigid Point Cloud Registrationcited by 15
  14. 2025Bridge 2D-3D: Uncertainty-aware Hierarchical Registration Network with Domain Alignmentcited by 14
  15. 2023End-to-end 2D-3D Registration between Image and LiDAR Point Cloud for Vehicle Localizationcited by 9
  16. 2025Diff2I2P: Differentiable Image-to-Point Cloud Registration with Diffusion Priorcited by 8
  17. 2024PFGS: High Fidelity Point Cloud Rendering via Feature Splattingcited by 7

Built on by

Not cited yet.