FUSER: Feed-Forward MUltiview 3D Registration Transformer and SE(3)$^N$ Diffusion Refinement

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jiang, Haobo, Xie, Jin, Yang, Jian, Yu, Liang, Zheng, Jianmin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910168144412672
author Jiang, Haobo
Xie, Jin
Yang, Jian
Yu, Liang
Zheng, Jianmin
author_facet Jiang, Haobo
Xie, Jin
Yang, Jian
Yu, Liang
Zheng, Jianmin
contents Registration of multiview point clouds conventionally relies on extensive pairwise matching to build a pose graph for global synchronization, which is computationally expensive and inherently ill-posed without holistic geometric constraints. This paper proposes FUSER, the first feed-forward multiview registration transformer that jointly processes all scans in a unified, compact latent space to directly predict global poses without any pairwise estimation. To maintain tractability, FUSER encodes each scan into low-resolution superpoint features via a sparse 3D CNN that preserves absolute translation cues, and performs efficient intra- and inter-scan reasoning through a Geometric Alternating Attention module. Particularly, we transfer 2D attention priors from off-the-shelf foundation models to enhance 3D feature interaction and geometric consistency. Building upon FUSER, we further introduce FUSER-DF, an SE(3)$^N$ diffusion refinement framework to correct FUSER's estimates via denoising in the joint SE(3)$^N$ space. FUSER acts as a surrogate multiview registration model to construct the denoiser, and a prior-conditioned SE(3)$^N$ variational lower bound is derived for denoising supervision. Extensive experiments on 3DMatch, ScanNet and ArkitScenes demonstrate that our approach achieves the superior registration accuracy and outstanding computational efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2512_09373
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FUSER: Feed-Forward MUltiview 3D Registration Transformer and SE(3)$^N$ Diffusion Refinement
Jiang, Haobo
Xie, Jin
Yang, Jian
Yu, Liang
Zheng, Jianmin
Computer Vision and Pattern Recognition
Registration of multiview point clouds conventionally relies on extensive pairwise matching to build a pose graph for global synchronization, which is computationally expensive and inherently ill-posed without holistic geometric constraints. This paper proposes FUSER, the first feed-forward multiview registration transformer that jointly processes all scans in a unified, compact latent space to directly predict global poses without any pairwise estimation. To maintain tractability, FUSER encodes each scan into low-resolution superpoint features via a sparse 3D CNN that preserves absolute translation cues, and performs efficient intra- and inter-scan reasoning through a Geometric Alternating Attention module. Particularly, we transfer 2D attention priors from off-the-shelf foundation models to enhance 3D feature interaction and geometric consistency. Building upon FUSER, we further introduce FUSER-DF, an SE(3)$^N$ diffusion refinement framework to correct FUSER's estimates via denoising in the joint SE(3)$^N$ space. FUSER acts as a surrogate multiview registration model to construct the denoiser, and a prior-conditioned SE(3)$^N$ variational lower bound is derived for denoising supervision. Extensive experiments on 3DMatch, ScanNet and ArkitScenes demonstrate that our approach achieves the superior registration accuracy and outstanding computational efficiency.
title FUSER: Feed-Forward MUltiview 3D Registration Transformer and SE(3)$^N$ Diffusion Refinement
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.09373