Visual Geometry Grounded Transformer

Follow this topic Ask about this topic

Momentum

5 papers in the last four weeks, down 17% on the four weeks before. 0.1% of all new papers.

Jul 6Week of Sep 21

Latest papers 69

All topics

StreamCacheVGGT: Streaming Visual Geometry Transformers with Robust Scoring and Hybrid Cache Compression
Apr 16, 2026Xuanyi Liu, Chunan Yu, Deyi Ji +6Visual Geometry Grounded Transformer Cache
KOKONI 3D, Moxin Technology · Nanjing University of Science and Technology · University of Science and Technology of China +4
Keep It CALM: Toward Calibration-Free Kilometer-Level SLAM with Visual Geometry Foundation Models via an Assistant Eye
Apr 16, 2026Tianjun Zhang, Fengyi Zhang, Tianchen Deng +2Simultaneous Localization And Mapping Visual Geometry Grounded Transformer
School of Automation and Intelligent Sensing, and Shanghai Key Laboratory of Navigation and Location Based Services, Shanghai Jiao Tong University, Shanghai 200240, China · School of Electrical Engineering and Computer Science, The University of Queensland, Brisbane 4067, Australia · School of Computer Science and Technology, Tongji University, Shanghai 201804, China
VIGOR: VIdeo Geometry-Oriented Reward for Temporal Generative Alignment
Mar 17, 2026Tengjiao Yin, Jinglei Shi, Heng Guo +1Video Diffusion Models Visual Geometry Grounded Transformer
VCIP & TMCC & DISSec, College of Computer Science, Nankai University · Beijing University of Posts and Telecommunications · LIX, École Polytechnique, IP Paris
GeoNVS: Geometry Grounded Video Diffusion for Novel View Synthesis
Mar 16, 2026Minjun Kang, Inkyu Shin, Taeyeop Lee +3Novel View Synthesis Video Diffusion Models
KAIST, South Korea · Luma AI, USA
SalFormer360: a transformer-based saliency estimation model for 360-degree videos
Feb 4, 2026Mahmoud Z. A. Wahba, Francesco Barbato, Sara Baldoni +1Saliency Visual Geometry Grounded Transformer
Department of Information Engineering, University of Padova, Via Gradenigo 6b, 35131, Padua, Italy
RayRoPE: Projective Ray Positional Encoding for Multi-view Attention
Jan 21, 2026Yu Wu, Minsik Jeon, Jen-Hao Rick Chang +2Multi-View Positional Encoding
Carnegie Mellon University · Apple
PGOT: A Physics-Geometry Operator Transformer for Complex PDEs
Dec 29, 2025Zhuo Zhang, Xi Yang, Ying Miao +5Visual Geometry Grounded Transformer Mesh Generation
National University of Defense Technology · Peking University · National University of Singapore +2
UniPR-3D: Towards Universal Visual Place Recognition with Visual Geometry Grounded Transformer
Dec 24, 2025Tianchen Deng, Xun Chen, Ziming Li +5Visual Place Recognition Visual Geometry Grounded Transformer
Shanghai Jiao Tong University · Nanyang Technological University · University of Macau +1
eVGGT: An Efficient Geometry-Aware Vision Encoder for Visuomotor Policies
Sep 19, 2025An Dinh Vuong, Minh Nhat Vu, Ian ReidVisuomotor Policy Visual Geometry Grounded Transformer
Department of Computer Vision, Mohammed bin Zayed University of Artificial Intelligence, UAE · AIT Austrian Institute of Technology GmbH, Austria

Apr 16, 2026, cs.CVJ/K move · Enter open · S save

StreamCacheVGGT: Streaming Visual Geometry Transformers with Robust Scoring and Hybrid Cache Compression

Xuanyi Liu, Chunan Yu, Deyi Ji, Qi Zhu+5

KOKONI 3D, Moxin Technology · Nanjing University of Science and Technology · University of Science and Technology of China+4

Visual Geometry Grounded Transformer Cache Key-Value Cache Compression Reconstruction Fidelity Gaussian Salience

Open paper AskPDF arXiv

Reconstructing dense 3D geometry from continuous video streams requires stable inference under a constant memory budget. Existing

O(1)

frameworks primarily rely on a ``pure eviction'' paradigm, which suffers from significant information destruction due to binary token deletion and evaluation noise from localized, single-layer scoring. To address these bottlenecks, we propose StreamCacheVGGT, a training-free framework that reimagines cache management through two synergistic modules: Cross-Layer Consistency-Enhanced Scoring (CLCES) and Hybrid Cache Compression (HCC). CLCES mitigates activation noise by tracking token importance trajectories across the Transformer hierarchy, employing order-statistical analysis to identify sustained geometric salience. Leveraging these robust scores, HCC transcends simple eviction by introducing a three-tier triage strategy that merges moderately important tokens into retained anchors via nearest-neighbor assignment on the key-vector manifold. This approach preserves essential geometric context that would otherwise be lost. Extensive evaluations on five benchmarks (7-Scenes, NRGBD, ETH3D, Bonn, and KITTI) demonstrate that StreamCacheVGGT sets a new state-of-the-art, delivering superior reconstruction accuracy and long-term stability while strictly adhering to constant-cost constraints.

Momentum

Related topics

Latest papers 69