MV-RoMa: From Pairwise Matching into Multi-View Track Reconstruction

• URL: http://arxiv.org/abs/2603.27542v1
• Date: Sun, 29 Mar 2026 06:50:21 GMT
• Title: MV-RoMa: From Pairwise Matching into Multi-View Track Reconstruction
• Abstract summary: MV-RoMa is a multi-view dense matching model that estimates dense correspondences from a source image to multiple co-visible targets.<n>We propose a post-processing strategy that integrates our model's consistent multi-view correspondences as high-quality tracks for structure-from-motion (SfM)<n>MV-RoMa produces more reliable correspondences and substantially denser, more accurate 3D reconstructions than existing sparse and dense matching methods.
• Score: 14.717756921141364
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Establishing consistent correspondences across images is essential for 3D vision tasks such as structure-from-motion (SfM), yet most existing matchers operate in a pairwise manner, often producing fragmented and geometrically inconsistent tracks when their predictions are chained across views. We propose MV-RoMa, a multi-view dense matching model that jointly estimates dense correspondences from a source image to multiple co-visible targets. Specifically, we design an efficient model architecture which avoids high computational cost of full cross-attention for multi-view feature interaction: (i) multi-view encoder that leverages pair-wise matching results as a geometric prior, and (ii) multi-view matching refiner that refines correspondences using pixel-wise attention. Additionally, we propose a post-processing strategy that integrates our model's consistent multi-view correspondences as high-quality tracks for SfM. Across diverse and challenging benchmarks, MV-RoMa produces more reliable correspondences and substantially denser, more accurate 3D reconstructions than existing sparse and dense matching methods. Project page: https://icetea-cv.github.io/mv-roma/.

Related papers

• AnyMatch: Supercharging Universal Multi-Modal Image Matching with Large-Scale Single-View Images [46.95222327089868]
  We propose AnyMatch to generate rich multi-modal training data at minimal cost.<n>AnyMatch integrates monocular depth estimation, 3D reprojection, diffusion-based inpainting, and crossmodal image translation.<n>We construct Any-syn, a large-scale synthetic multi-modal dataset using AnyMatch.
  arXiv  Detail & Related papers  (2026-06-30T03:06:58Z)
• COMPOSE: Hypergraph Cover Optimization for Multi-view 3D Human Pose Estimation [58.47973015036709]
  3D pose estimation from sparse multi-views is a critical task for action recognition, sports analysis, and human-robot interaction.<n>We propose COMPOSE, a novel framework that formulates multi-view pose correspondence matching as a hypergraph problem.<n> COMPOSE achieves improvements of up to 23% in average precision over previous optimization-based methods and up to 11% over self-supervised end-to-end learned methods.
  arXiv  Detail & Related papers  (2026-01-14T18:50:17Z)
• 3D-Aware Multi-Task Learning with Cross-View Correlations for Dense Scene Understanding [18.76513756741288]
  Current approaches mainly capture cross-task relations in the 2D image space, often leading to unstructured features lacking 3D-awareness.<n>We propose to address this problem by integrating correlations across views, i.e., cost volume, as geometric consistency in the MTL network.<n> Specifically, we introduce a lightweight Cross-view Module (CvM), shared across tasks, to exchange information across views and capture cross-view correlations.
  arXiv  Detail & Related papers  (2025-11-25T18:59:34Z)
• CoMatcher: Multi-View Collaborative Feature Matching [10.432708461699578]
  We introduce CoMatcher, a deep multi-view matcher to leverage complementary context cues from different views to form a holistic 3D scene understanding.<n>Building on CoMatcher, we develop a groupwise framework that fully exploits cross-view relationships for large-scale matching tasks.
  arXiv  Detail & Related papers  (2025-04-02T16:27:44Z)
• MEt3R: Measuring Multi-View Consistency in Generated Images [47.152540564255204]
  We introduce MEt3R, a metric for multi-view consistency in generated images.<n>Our approach uses DUSt3R to obtain dense 3D reconstructions from image pairs in a feed-forward manner.
  arXiv  Detail & Related papers  (2025-01-10T20:43:33Z)
• Matryoshka Multimodal Models [92.41824727506751]
  We propose M3: Matryoshka Multimodal Models, which learns to represent visual content as nested sets of visual tokens. We find that COCO-style benchmarks only need around 9 visual tokens to obtain accuracy similar to that of using all 576 tokens.
  arXiv  Detail & Related papers  (2024-05-27T17:59:56Z)
• RGM: A Robust Generalizable Matching Model [49.60975442871967]
  We propose a deep model for sparse and dense matching, termed RGM (Robust Generalist Matching) To narrow the gap between synthetic training samples and real-world scenarios, we build a new, large-scale dataset with sparse correspondence ground truth. We are able to mix up various dense and sparse matching datasets, significantly improving the training diversity.
  arXiv  Detail & Related papers  (2023-10-18T07:30:08Z)
• Unifying Flow, Stereo and Depth Estimation [121.54066319299261]
  We present a unified formulation and model for three motion and 3D perception tasks. We formulate all three tasks as a unified dense correspondence matching problem. Our model naturally enables cross-task transfer since the model architecture and parameters are shared across tasks.
  arXiv  Detail & Related papers  (2022-11-10T18:59:54Z)
• Direct Multi-view Multi-person 3D Pose Estimation [138.48139701871213]
  We present Multi-view Pose transformer (MvP) for estimating multi-person 3D poses from multi-view images. MvP directly regresses the multi-person 3D poses in a clean and efficient way, without relying on intermediate tasks. We show experimentally that our MvP model outperforms the state-of-the-art methods on several benchmarks while being much more efficient.
  arXiv  Detail & Related papers  (2021-11-07T13:09:20Z)
• Isometric Multi-Shape Matching [50.86135294068138]
  Finding correspondences between shapes is a fundamental problem in computer vision and graphics. While isometries are often studied in shape correspondence problems, they have not been considered explicitly in the multi-matching setting. We present a suitable optimisation algorithm for solving our formulation and provide a convergence and complexity analysis.
  arXiv  Detail & Related papers  (2020-12-04T15:58:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.