VGGT-Segmentor: Geometry-Enhanced Cross-View Segmentation

• URL: http://arxiv.org/abs/2604.13596v2
• Date: Thu, 16 Apr 2026 00:59:15 GMT
• Title: VGGT-Segmentor: Geometry-Enhanced Cross-View Segmentation
• Abstract summary: We introduce VGGT-Segmentor (VGGT-S), a geometric framework that unifies pixel-accurate semantic segmentation.<n>On the Ego-Exo4D benchmark, VGGT-S sets a new state-of-the-art, achieving 67.7% and 68.0% average IoU for Ego to Exo and Exo to Ego tasks, respectively.
• Score: 17.578132395389755
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Instance-level object segmentation across disparate egocentric and exocentric views is a fundamental challenge in visual understanding, critical for applications in embodied AI and remote collaboration. This task is exceptionally difficult due to severe changes in scale, perspective, and occlusion, which destabilize direct pixel-level matching. While recent geometry-aware models like VGGT provide a strong foundation for feature alignment, we find they often fail at dense prediction tasks due to significant pixel-level projection drift, even when their internal object-level attention remains consistent. To bridge this gap, we introduce VGGT-Segmentor (VGGT-S), a framework that unifies robust geometric modeling with pixel-accurate semantic segmentation. VGGT-S leverages VGGT's powerful cross-view feature representation and introduces a novel Union Segmentation Head. This head operates in three stages: mask prompt fusion, point-guided prediction, and iterative mask refinement, effectively translating high-level feature alignment into a precise segmentation mask. Furthermore, we propose a single-image self-supervised training strategy that eliminates the need for paired annotations and enables strong generalization. On the Ego-Exo4D benchmark, VGGT-S sets a new state-of-the-art, achieving 67.7% and 68.0% average IoU for Ego to Exo and Exo to Ego tasks, respectively, significantly outperforming prior methods. Notably, our correspondence-free pretrained model surpasses most fully-supervised baselines, demonstrating the effectiveness and scalability of our approach.

Related papers

• What VGGT Knows About Overlap: Probing Geometric Foundation Models for Co-Visibility [14.143547667315419]
  VGGT implicitly encodes co-visibility as an emergent behavior.<n>We introduce specialization Co-VGGT, which freezes VGGT and trains only a lightweight layer-wise mixture-of-experts head.<n>On the Co-VisiON benchmark, Co-VGGT surpasses the human annotation baseline and improves over prior work by more than 25% pairwise and 10% multiview.
  arXiv  Detail & Related papers  (2026-07-10T15:17:02Z)
• Towards Foundation Models for 3D Scene Understanding: Instance-Aware Self-Supervised Learning for Point Clouds [53.82500407523346]
  PointINS is an instance-oriented self-supervised framework that enriches point cloud representations through geometry-aware learning.<n>PointINS achieves on average +3.5% mAP improvement for indoor instance segmentation and +4.1% PQ gain for outdoor panoptic segmentation.
  arXiv  Detail & Related papers  (2026-03-26T08:31:06Z)
• GLASS: Graph and Vision-Language Assisted Semantic Shape Correspondence [16.503835991826367]
  We present GLASS, a framework that bridges the gap by integrating geometric spectral analysis with rich semantic priors from vision-language foundation models.<n> GLASS introduces three key innovations: (i) a view-consistent strategy that enables robust multi-view visual feature extraction from powerful vision foundation models.<n>It achieves average geodesic errors of 0.21, 4.5, and 5.6 on the inter-class benchmark SMAL and non-isometric benchmarks SMAL and TOPKIDS, reducing errors from URSSM baselines of 0.49, 6.0, and 8.9 by 57%, 25%, and 37%, respectively.
  arXiv  Detail & Related papers  (2026-03-08T14:33:50Z)
• STVG-R1: Incentivizing Instance-Level Reasoning and Grounding in Videos via Reinforcement Learning [65.36458157092207]
  In vision-language models (VLMs), misalignment between textual descriptions and visual coordinates often induces hallucinations.<n>We propose a novel visual prompting paradigm that avoids the difficult problem of aligning coordinates across modalities.<n>We introduce STVG-R1, the first reinforcement learning framework for STVG, which employs a task-driven reward to jointly optimize temporal accuracy, spatial consistency, and structural format regularization.
  arXiv  Detail & Related papers  (2026-02-12T08:53:32Z)
• GPA-VGGT:Adapting VGGT to Large Scale Localization by Self-Supervised Learning with Geometry and Physics Aware Loss [15.633839321933385]
  Recent advancements in Visual Geometry Grounded Transformer (VGGT) models have shown great promise in camera pose estimation and 3D reconstruction.<n>These models typically rely on ground truth labels for training, posing challenges when adapting to unlabeled and unseen scenes.<n>We propose a self-supervised framework to train VGGT with unlabeled data, thereby enhancing its localization capability in large-scale environments.
  arXiv  Detail & Related papers  (2026-01-23T16:46:59Z)
• 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)
• Dense Semantic Matching with VGGT Prior [49.42199006453071]
  We propose an approach that retains VGGT's intrinsic strengths by reusing early feature stages, fine-tuning later ones, and adding a semantic head for bidirectional correspondences.<n>Our approach achieves superior geometry awareness, matching reliability, and manifold preservation, outperforming previous baselines.
  arXiv  Detail & Related papers  (2025-09-25T14:56:11Z)
• Faster VGGT with Block-Sparse Global Attention [11.473406315508647]
  We propose a replacement for the dense global attention operation based on highly optimized block-sparse kernels.<n>Our retrofit requires no retraining of the backbone, extends to both VGGT and $pi3$, and supports large image collections.
  arXiv  Detail & Related papers  (2025-09-08T18:16:09Z)
• Self-Enhanced Image Clustering with Cross-Modal Semantic Consistency [57.961869351897384]
  We propose a framework based on cross-modal semantic consistency for efficient image clustering.<n>Our framework first builds a strong foundation via Cross-Modal Semantic Consistency.<n>In the first stage, we train lightweight clustering heads to align with the rich semantics of the pre-trained model.<n>In the second stage, we introduce a Self-Enhanced fine-tuning strategy.
  arXiv  Detail & Related papers  (2025-08-02T08:12:57Z)
• Unsupervised Domain Adaptation for Monocular 3D Object Detection via Self-Training [57.25828870799331]
  We propose STMono3D, a new self-teaching framework for unsupervised domain adaptation on Mono3D. We develop a teacher-student paradigm to generate adaptive pseudo labels on the target domain. STMono3D achieves remarkable performance on all evaluated datasets and even surpasses fully supervised results on the KITTI 3D object detection dataset.
  arXiv  Detail & Related papers  (2022-04-25T12:23:07Z)

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.