Diversity-aware View Partitioning for Scalable VGGT

• URL: http://arxiv.org/abs/2607.01885v2
• Date: Sat, 04 Jul 2026 12:43:50 GMT
• Title: Diversity-aware View Partitioning for Scalable VGGT
• Abstract summary: VGGT achieve strong performance by jointly reasoning over multiple views with global attention.<n>We propose a training-free and plug-and-play inference framework that organizes views into diversity-aware balanced chunks.<n>Our framework also complements existing VGGT variants, enabling scalable multi-view reconstruction without sacrificing geometric fidelity.
• Score: 48.654660686945526
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Geometry transformers such as VGGT achieve strong performance by jointly reasoning over multiple views with global attention. However, scaling them to large view collections remains challenging due to the quadratic cost of attention. Moreover, our empirical analysis reveals that the reconstruction quality in VGGT is sensitive to the distribution of viewpoints. Simply increasing the number of views without sufficient viewpoint diversity can even degrade performance, as redundant views introduce highly similar tokens that dilute informative geometric signals in the attention mechanism. Motivated by this observation, we propose a training-free and plug-and-play VGGT inference framework that organizes views into diversity-aware balanced chunks. The chunks are constructed through combinatorial graph partitioning over visual dissimilarity and spatial dispersion. This view organization allows the transformer to focus attention on geometrically informative views while reducing redundant attention interactions. To estimate spatial dispersion without full pose estimation, we approximate spatial relationships via a soft pose propagation strategy based on visual similarity from a small set of seed frames. Extensive experiments demonstrate improved performance in camera pose estimation, multi-view depth prediction, and 3D reconstruction while reducing memory usage and inference latency. Our framework also complements existing VGGT variants, enabling scalable multi-view reconstruction without sacrificing geometric fidelity.

Related papers

• AVSplat: Dense-View Feed-Forward 3D Gaussian Splatting with Assist-View Preconditioning [78.53780077475876]
  We present AVSplat, a framework that turns additional views into reliable signals for both aggregation and representation.<n>For representation, we use adaptive temperature-aware voxel fusion that sharpens attribution under high occupancy.<n> AVSplat restores positive view scaling where performance remains stable or improves as more input views are added.
  arXiv  Detail & Related papers  (2026-09-05T06:33:04Z)
• VIEW2SPACE: Studying Multi-View Visual Reasoning from Sparse Observations [47.94531550391802]
  Multi-view visual reasoning is essential for intelligent systems that must understand complex environments from sparse and discrete viewpoints.<n>In real-world scenarios, reasoning across views requires integrating partial observations without explicit guidance.<n>We leverage physically grounded simulation to construct diverse, high-fidelity 3D scenes with precise per-view metadata.
  arXiv  Detail & Related papers  (2026-03-17T13:36:30Z)
• Reference-Free Omnidirectional Stereo Matching via Multi-View Consistency Maximization [22.711843818785454]
  Free OmniMVS can aggregate pair-wise correlations into a robust, omni-aware, and global consensus.<n>To realize visibility-aware consensus, we propose a lightweight attention mechanism that adaptively fuses the correlation vectors.<n>Experiments on diverse benchmark datasets demonstrate the superiority of our method for globally consistent, visibility-aware, and scale-aware depth estimation.
  arXiv  Detail & Related papers  (2026-03-16T09:23:23Z)
• Reloc-VGGT: Visual Re-localization with Geometry Grounded Transformer [40.778996326009185]
  We present the first visual localization framework that performs multi-view spatial integration through an early-fusion mechanism.<n>Our framework is built upon the VGGT backbone, which encodes multi-view 3D geometry.<n>We propose a novel sparse mask attention strategy that reduces computational cost by avoiding the quadratic complexity of global attention.
  arXiv  Detail & Related papers  (2025-12-26T06:12:17Z)
• 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)
• Zero-P-to-3: Zero-Shot Partial-View Images to 3D Object [55.93553895520324]
  We propose a novel training-free approach that integrates local dense observations and multi-source priors for reconstruction.<n>Our method introduces a fusion-based strategy to effectively align these priors in DDIM sampling, thereby generating multi-view consistent images to supervise invisible views.
  arXiv  Detail & Related papers  (2025-05-29T03:51:37Z)
• Deep Incomplete Multi-view Clustering with Distribution Dual-Consistency Recovery Guidance [69.58609684008964]
  We propose BURG, a novel method for incomplete multi-view clustering with distriBution dUal-consistency Recovery Guidance.<n>We treat each sample as a distinct category and perform cross-view distribution transfer to predict the distribution space of missing views.<n>To compensate for the lack of reliable category information, we design a dual-consistency guided recovery strategy that includes intra-view alignment guided by neighbor-aware consistency and cross-view alignment guided by prototypical consistency.
  arXiv  Detail & Related papers  (2025-03-14T02:27:45Z)
• Multi-Spectral Image Stitching via Spatial Graph Reasoning [52.27796682972484]
  We propose a spatial graph reasoning based multi-spectral image stitching method. We embed multi-scale complementary features from the same view position into a set of nodes. By introducing long-range coherence along spatial and channel dimensions, the complementarity of pixel relations and channel interdependencies aids in the reconstruction of aligned multi-view features.
  arXiv  Detail & Related papers  (2023-07-31T15:04:52Z)

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.