MVOFormer: Flow-Semantic Transformer for Robust Monocular Visual Odometry

• URL: http://arxiv.org/abs/2606.16474v1
• Date: Mon, 15 Jun 2026 09:39:28 GMT
• Title: MVOFormer: Flow-Semantic Transformer for Robust Monocular Visual Odometry
• Abstract summary: MVOFormer is a novel transformer framework for robust monocular visual odometry.<n>MVOFormer achieves superior zero-shot generalization and robustness, significantly outperforming prior learning-based frame-to-frame methods.
• Score: 11.059456227749914
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Monocular visual odometry (MVO) is foundational to autonomous navigation and robotic localization. However, existing learning-based MVO approaches often struggle with either a lack of interpretable, complementary features or overly complex multi-stage architectures. These limitations inherently restrict their robustness and cross-domain generalization. In this work, we propose MVOFormer, a novel transformer framework for robust monocular visual odometry. Our architecture features a Flow-Semantic Dual Branch Encoder that synergizes dense geometric motion cues with object-centric semantic priors, explicitly distinguishing static structures from dynamic distractors. These representations are then fused by an Iterative Multimodal Decoder, enabling coarse-to-fine pose refinement while dynamically suppressing attention on unreliable regions. Extensive evaluations demonstrate that, without any target-domain fine-tuning, MVOFormer achieves superior zero-shot generalization and robustness, significantly outperforming prior learning-based frame-to-frame methods across diverse benchmarks including TartanAir, KITTI, TUM-RGBD, and ETH3D-SLAM.

Related papers

• When Simplicity Wins: Bottleneck-Aware Context Modeling for Lightweight Semantic Segmentation [58.325533783810016]
  We propose SiConMo, a lightweight yet effective framework for semantic segmentation.<n>We show that simplicity arises from a key design principle: at very low computational budgets, the bottleneck is the most efficient stage to integrate local and global context.<n> experiments on ADE20K, PASCAL Context, Cityscapes, and COCO-Stuff demonstrate that SiConMo achieves a state-of-the-art accuracy-efficiency trade-off.
  arXiv  Detail & Related papers  (2026-08-19T14:47:07Z)
• Robust Multimodal Dynamic Object Segmentation [14.277810365296071]
  We present a dynamic object segmentation framework that can generate both precise and complete dynamic masks.<n>Our approach achieves state-of-the-art performance in both dynamic object segmentation and static scene reconstruction tasks.
  arXiv  Detail & Related papers  (2026-07-20T16:51:48Z)
• TurboVGGT: Fast Visual Geometry Reconstruction with Adaptive Alternating Attention [21.29668311125256]
  TurboVGGT employs an efficient visual geometry transformer with adaptive alternating attention for fast multi-view 3D reconstruction.<n>In the adaptive sparse global attention, TurboVGGT adaptively learns representative tokens with varying sparsity levels for global geometry modeling.<n>Experiments on multiple 3D reconstruction benchmarks demonstrate that TurboVGGT achieves fast multi-view reconstruction while maintaining competitive reconstruction quality.
  arXiv  Detail & Related papers  (2026-05-14T03:24:09Z)
• PoseFM: Relative Camera Pose Estimation Through Flow Matching [0.0]
  We propose PoseFM, a framework to reformulate monocular frame-to-frame VO as a generative task using Flow Matching (FM)<n>By leveraging FM, we model camera motion as a distribution rather than a point estimate, learning to transform noise into realistic pose predictions via continuous-time ODEs.<n>In our evaluations, PoseFM achieves strong performance on TartanAir, KITTI and TUM-RGBD benchmarks, achieving the lowest absolute trajectory error (ATE) on some of the trajectories.
  arXiv  Detail & Related papers  (2026-04-24T08:36:53Z)
• Hierarchical Granularity Alignment and State Space Modeling for Robust Multimodal AU Detection in the Wild [12.893641381621459]
  We propose a novel multimodal framework driven by Hierarchical Granularity Alignment and State Space Models.<n>We overcome the receptive field limitations of conventional temporal convolutional networks by introducing a Vision-Mamba architecture.<n>This approach enables temporal modeling with O(N) linear complexity, effectively capturing ultra-long-range dynamics without performance degradation.
  arXiv  Detail & Related papers  (2026-03-11T21:05:59Z)
• Perception-Aware Multimodal Spatial Reasoning from Monocular Images [57.42071289037214]
  spatial reasoning from monocular images is essential for autonomous driving.<n>Current Vision-Language Models (VLMs) still struggle with fine-grained geometric perception.<n>We propose a perception-aware multimodal reasoning framework that equipsVLMs with explicit object-centric grounding ability.
  arXiv  Detail & Related papers  (2026-03-07T02:05:12Z)
• VLMFusionOcc3D: VLM Assisted Multi-Modal 3D Semantic Occupancy Prediction [0.0]
  VLMFusionOcc3D is a robust multimodal framework for dense 3D semantic occupancy prediction in autonomous driving.<n>We introduce Weather-Aware Adaptive Fusion, a dynamic gating mechanism that utilizes vehicle metadata and weather-conditioned prompts to re-weight sensor contributions.<n>Our approach achieves significant improvements in challenging weather scenarios, offering a scalable and robust solution for complex urban navigation.
  arXiv  Detail & Related papers  (2026-03-03T05:22:28Z)
• MVGGT: Multimodal Visual Geometry Grounded Transformer for Multiview 3D Referring Expression Segmentation [59.75554954111619]
  We introduce Multi-view 3D Referring Expression (MV-3DRES), where the model must recover scene structure and segment the referred object directly from sparse multi-view images.<n>We propose the Multimodal Visual Geometry Grounded Transformer (MVGGT), an efficient end-to-end framework that integrates language information into sparse-view geometric reasoning.<n>Experiments show that MVGGT establishes the first strong baseline and achieves both high accuracy and fast inference, outperforming existing alternatives.
  arXiv  Detail & Related papers  (2026-01-11T11:44:07Z)
• DynaPURLS: Dynamic Refinement of Part-aware Representations for Skeleton-based Zero-Shot Action Recognition [51.80782323686666]
  We introduce textbfDynaPURLS, a unified framework that establishes robust, multi-scale visual-semantic correspondences.<n>Our framework leverages a large language model to generate hierarchical textual descriptions that encompass both global movements and local body-part dynamics.<n>Experiments on three large-scale benchmark datasets, including NTU RGB+D 60/120 and PKU-MMD, demonstrate that DynaPURLS significantly outperforms prior art.
  arXiv  Detail & Related papers  (2025-12-12T10:39:10Z)
• OneCAT: Decoder-Only Auto-Regressive Model for Unified Understanding and Generation [91.45421429922506]
  OneCAT is a unified multimodal model that seamlessly integrates understanding, generation, and editing.<n>Our framework eliminates the need for external components such as Vision Transformers (ViT) or vision tokenizer during inference.
  arXiv  Detail & Related papers  (2025-09-03T17:29:50Z)
• GMF-Drive: Gated Mamba Fusion with Spatial-Aware BEV Representation for End-to-End Autonomous Driving [5.450011907283289]
  This paper introduces GMF-Drive, an end-to-end framework that overcomes challenges through two principled innovations.<n>First, we supersede the information-limited histogram-based LiDAR representation with a geometrically-augmented pillar format.<n>Second, we propose a novel hierarchical mamba fusion architecture that substitutes an expensive transformer with a highly efficient, spatially-aware state-space model.
  arXiv  Detail & Related papers  (2025-08-08T08:17:18Z)
• VRS-UIE: Value-Driven Reordering Scanning for Underwater Image Enhancement [104.78586859995333]
  State Space Models (SSMs) have emerged as a promising backbone for vision tasks due to their linear complexity and global receptive field.<n>The predominance of large-portion, homogeneous but useless oceanic backgrounds can dilute the feature representation responses of sparse yet valuable targets.<n>We propose a novel Value-Driven Reordering Scanning framework for Underwater Image Enhancement (UIE)<n>Our framework sets a new state-of-the-art, delivering superior enhancement performance (surpassing WMamba by 0.89 dB on average) by effectively suppressing water bias and preserving structural and color fidelity.
  arXiv  Detail & Related papers  (2025-05-02T12:21:44Z)

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.