The paper introduces DPA-I2P, a depth-guided projective alignment method for image-to-point-cloud registration in autonomous driving. It employs Ray-Conditioned Metric Depth Encoding and Projection-Consistent Vision Lifting to align depth and visual cues geometrically, and uses Cross-Modal Query Pruning to enhance matching stability. Experiments on KITTI and nuScenes show significant reductions in rotation and translation errors compared to existing implicit baselines.
By Wenxin Zhang, Hang Li, Zhiwei Xu, Qiankun Dong, Gang Wang, Tao Li
The paper introduces DPA-I2P, a depth‑guided projective alignment method for image‑to‑point‑cloud registration in autonomous driving. It employs Ray‑Conditioned Metric Depth Encoding and Projection‑Consistent Vision Lifting to align depth and visual cues geometrically, and uses Cross‑Modal Query Pruning to filter unreliable matches during refinement. Experiments on KITTI and nuScenes show significant improvements, reducing rotation and translation errors by up to 55.6% compared to existing implicit baselines.
GRIP is a pose‑conditioned refinement framework that improves pixel‑to‑point matching for image‑to‑point‑cloud registration. It mitigates the mismatch between grid‑based image descriptors and unordered point cloud descriptors by softly rendering learned 3D point features onto the image grid using Gaussian feature splatting. The resulting rendered point‑derived feature map is fused with image features via a pixel‑aligned transformer, enabling visual semantic and geometric cues to interact in a shared 2D representation, which is then decoded and propagated to finer resolutions for dense correspondence estimation and final pose refinement. Experiments on RGB‑D Scenes V2 and 7 Scenes show state‑of‑the‑art inlier ratios and competitive registration recall, especially under stricter evaluation thresholds.
By Karim Slimani, Catherine Achard, Eric Marchand, Brahim Tamadazte
The paper introduces Ex‑Sim(3)‑Reg, a fast and robust method for pruning 2D‑3D correspondences by reformulating the problem as an extended Sim(3) registration that explicitly accounts for depth noise. The authors provide a theoretical justification and demonstrate that their approach improves registration recall by up to 24.7% on several benchmark datasets, outperforming state‑of‑the‑art baselines. The code for the method is publicly available on GitHub.
By Pei An, Muyao Peng, Junfeng Ding, Jiaqi Yang, Liangliang Nan
The paper introduces the Register Anything Model (RAM), a unified approach for 3D point cloud registration that can robustly estimate 6‑DoF transformations across a wide range of domains, including indoor, outdoor, and object scenes. RAM overcomes domain‑specific challenges by employing a geometry‑aware normalization that voxelizes and standardizes point clouds based on their geometric properties, followed by a hierarchical coarse‑to‑fine pipeline with a geometric transformer that focuses on local consistency. Experiments on 12 benchmarks show that RAM achieves state‑of‑the‑art inlier ratios and registration recall, outperforming methods trained on individual domains and demonstrating strong generalization.
By Zheng Qin, Junhua Xi, Yan Huang, Jiahong Lai, Anwen Huang, Qiong Li, Guangda Zhang, Kai Xu
SAGE (Semantic-Augmented Geometric Experts) is a new point‑cloud registration method that incorporates frozen, pre‑trained semantic representations into the registration pipeline without extra sensors or fine‑tuning. It uses a Semantic‑Guided Mixture of Experts (SG‑MoE) to route data so that each expert specializes in specific semantic‑geometric patterns, thereby reducing mismatches that plague geometry‑only approaches. On the 3DLoMatch benchmark, SAGE achieves the highest registration recall and, with the same number of refinement iterations, also attains the best inlier ratio and recall on both 3DLoMatch and 3DMatch.
By Tomoyasu Shimada, Kazuhiko Murasaki, Shoichiro Takeda, Shogo Sato, Riku Inoue, Toshihiko Nishimura, Ryuichi Tanida
arXiv:2506. 22784v2 Announce Type: replace-cross Abstract: Point-pixel registration between LiDAR point clouds and camera images is a fundamental yet challenging task in autonomous driving and robotic perception.
By Yu Han, Zhiwei Huang, Yanting Zhang, Fangjun Ding, Shen Cai, Xiaoyu Tang, Yanchao Dong, Rui Fan
DMM-Align introduces a closed‑loop framework for 2D‑3D registration that jointly refines correspondences, estimates pose, and learns representations using a shared differentiable geometric state. The method employs two diffusion processes: a geometry‑aware diffusion that improves the soft matching matrix for robust correspondence estimation, and a geometry‑conditioned diffusion teacher that feeds pose‑induced supervision back into feature learning. Experiments on 7‑Scenes and RGB‑D Scenes V2 show that DMM‑Align outperforms strong baselines, particularly in low‑overlap and heavily occluded scenarios, demonstrating the value of closed‑loop geometric feedback.
By Chongjian Wang, Junjie Gao
The paper introduces PointVGGT, a zero‑shot framework for multiview RGB‑D point cloud registration that replaces the traditional pairwise‑then‑global pipeline. It employs a foundation‑then‑refinement paradigm, using visual geometry foundation models to directly recover metrically consistent global poses and then refining them with voxelized spatial hashing and IRLS‑based bundle adjustment. Experiments on indoor, object‑centric, and outdoor datasets demonstrate superior registration accuracy and computational efficiency without any training.
By Haobo Jiang, Liang Yu, Jianmin Zheng
arXiv:2609.36644v1 Announce Type: new
Abstract: Cross-attention is a crucial component in learning-based image-to-point-cloud (I2P) registration. Although existing cross-attention mechanisms have ach...
By Pei An, Jiaqi Yang, Yulong Wang, Siwen Quan, Liangliang Nan
The paper introduces GMPCR, a non‑learning spectral consistency‑guided framework for multiview point cloud registration in low‑overlap scenes. GMPCR refines initial correspondences into a second‑order compatibility structure, uses spectral analysis to filter unreliable matches and select informative scan pairs, and then applies maximal‑clique hypothesis generation for robust relative transformations. The resulting sparse pose graph is further refined with an adaptive history‑aware synchronization scheme, and a recovery mechanism allows previously down‑weighted edges to regain confidence, achieving high registration recalls on benchmark datasets while reducing computational cost.
By Tianyu Li, Yanghong Lin, Shudong Zhou, Kui Yang, Jingru Zhang, Li Fang, Wei Yao
Cross-modal place recognition (CMPR) aims to identify the same location across heterogeneous sensing modalities, such as vision and LiDAR. Existing methods commonly bridge the modality gap using complex alignment modules, multi-stage training, or full fine-tuning of pretrained backbones.