TeaMatch: Teachable Cross-Modal Representation Learning for 2D-3D Matching

• URL: http://arxiv.org/abs/2608.09590v1
• Date: Mon, 10 Aug 2026 13:24:01 GMT
• Title: TeaMatch: Teachable Cross-Modal Representation Learning for 2D-3D Matching
• Abstract summary: TeaMatch is a novel framework that introduces teachability as a criterion for cross-modal representation learning.<n>Our framework can be seamlessly integrated into existing coarse-to-fine matching pipelines without additional inference cost.
• Score: 3.911341147858216
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Learning reliable correspondences between images and point clouds is fundamental for 2D-3D matching. Despite recent progress in detection-free methods, existing approaches primarily optimize matching within a single model and often struggle to maintain reliable correspondences under challenging conditions such as noisy inputs, low overlap, and ambiguous structures. In this work, we propose TeaMatch, a novel framework that introduces teachability as a criterion for cross-modal representation learning. We define teachability as the ability of a representation to be effectively recovered by weak learners under degraded inputs, reflecting its structural consistency and robustness. To this end, we construct a set of task-specific weak students that simulate common failure modes and train them to imitate the teacher on a training split while evaluating their recoverability on a disjoint meta split. The teacher is then optimized to improve the students' ability to recover reliable correspondences, guided by correspondence-level and geometry-aware constraints. Our framework can be seamlessly integrated into existing coarse-to-fine matching pipelines without additional inference cost. Extensive experiments demonstrate that TeaMatch improves matching robustness and achieves state-of-the-art performance on challenging 2D-3D matching benchmarks.

Related papers

• ConeSep: Cone-based Robust Noise-Unlearning Compositional Network for Composed Image Retrieval [60.051600134831226]
  This paper systematically investigates the Noisy Triplet Correspondence (NTC) problem introduced by annotations.<n>We propose a Cone-based robuSt noisE-unlearning comPositional network (ConeSep) to address these challenges.
  arXiv  Detail & Related papers  (2026-04-22T08:59:21Z)
• TRiCo: Triadic Game-Theoretic Co-Training for Robust Semi-Supervised Learning [15.638836465479619]
  TRiCo is a novel triadic game-theoretic co-training framework that rethinks the structure of semi-supervised learning.<n>By addressing key limitations in existing SSL frameworks, TRiCo provides a principled and generalizable solution.
  arXiv  Detail & Related papers  (2025-09-25T20:10:41Z)
• Match me if you can: Semi-Supervised Semantic Correspondence Learning with Unpaired Images [76.47980643420375]
  This paper builds on the hypothesis that there is an inherent data-hungry matter in learning semantic correspondences. We demonstrate a simple machine annotator reliably enriches paired key points via machine supervision. Our models surpass current state-of-the-art models on semantic correspondence learning benchmarks like SPair-71k, PF-PASCAL, and PF-WILLOW.
  arXiv  Detail & Related papers  (2023-11-30T13:22:15Z)
• Q-REG: End-to-End Trainable Point Cloud Registration with Surface Curvature [81.25511385257344]
  We present a novel solution, Q-REG, which utilizes rich geometric information to estimate the rigid pose from a single correspondence. Q-REG allows to formalize the robust estimation as an exhaustive search, hence enabling end-to-end training. We demonstrate in the experiments that Q-REG is agnostic to the correspondence matching method and provides consistent improvement both when used only in inference and in end-to-end training.
  arXiv  Detail & Related papers  (2023-09-27T20:58:53Z)
• Noisy-Correspondence Learning for Text-to-Image Person Re-identification [50.07634676709067]
  We propose a novel Robust Dual Embedding method (RDE) to learn robust visual-semantic associations even with noisy correspondences. Our method achieves state-of-the-art results both with and without synthetic noisy correspondences on three datasets.
  arXiv  Detail & Related papers  (2023-08-19T05:34:13Z)
• Understanding and Constructing Latent Modality Structures in Multi-modal Representation Learning [53.68371566336254]
  We argue that the key to better performance lies in meaningful latent modality structures instead of perfect modality alignment. Specifically, we design 1) a deep feature separation loss for intra-modality regularization; 2) a Brownian-bridge loss for inter-modality regularization; and 3) a geometric consistency loss for both intra- and inter-modality regularization.
  arXiv  Detail & Related papers  (2023-03-10T14:38:49Z)
• SRFeat: Learning Locally Accurate and Globally Consistent Non-Rigid Shape Correspondence [36.44119664239748]
  We present a learning-based framework that combines the local accuracy of contrastive learning with the global consistency of geometric approaches. Our framework is general and is applicable to local feature learning in both the 3D and 2D domains.
  arXiv  Detail & Related papers  (2022-09-16T09:11:12Z)
• PointACL:Adversarial Contrastive Learning for Robust Point Clouds Representation under Adversarial Attack [73.3371797787823]
  Adversarial contrastive learning (ACL) is considered an effective way to improve the robustness of pre-trained models. We present our robust aware loss function to train self-supervised contrastive learning framework adversarially. We validate our method, PointACL on downstream tasks, including 3D classification and 3D segmentation with multiple datasets.
  arXiv  Detail & Related papers  (2022-09-14T22:58:31Z)
• S2DNet: Learning Accurate Correspondences for Sparse-to-Dense Feature Matching [36.48376198922595]
  S2DNet is a novel feature matching pipeline designed and trained to efficiently establish robust and accurate correspondences. We show that S2DNet achieves state-of-the-art results on the HPatches benchmark, as well as on several long-term visual localization datasets.
  arXiv  Detail & Related papers  (2020-04-03T17:04:34Z)

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.