Cover Image

LiteVGGT: Boosting Vanilla VGGT via Geometry-aware Cached Token Merging

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shu, Zhijian, Lin, Cheng, Xie, Tao, Yin, Wei, Li, Ben, Pu, Zhiyuan, Li, Weize, Yao, Yao, Cao, Xun, Guo, Xiaoyang, Long, Xiao-Xiao
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

VGGT-World: Transforming VGGT into an Autoregressive Geometry World Model
by: Sun, Xiangyu, et al.
Published: (2026)

HTTM: Head-wise Temporal Token Merging for Faster VGGT
by: Wang, Weitian, et al.
Published: (2025)

FrameVGGT: Geometry-Aligned Frame-Level Memory for Bounded Streaming VGGT
by: Xu, Zhisong, et al.
Published: (2026)

StreamCacheVGGT: Streaming Visual Geometry Transformers with Robust Scoring and Hybrid Cache Compression
by: Liu, Xuanyi, et al.
Published: (2026)

VGGT: Visual Geometry Grounded Transformer
by: Wang, Jianyuan, et al.
Published: (2025)

PaceVGGT: Pre-Alternating-Attention Token Pruning for Visual Geometry Transformers
by: Li, Haotang, et al.
Published: (2026)

VGGT-$Ω$
by: Wang, Jianyuan, et al.
Published: (2026)

VGGT-SLAM++
by: Mandal, Avilasha, et al.
Published: (2026)

Reloc-VGGT: Visual Re-localization with Geometry Grounded Transformer
by: Deng, Tianchen, et al.
Published: (2025)

VGGT-Det: Mining VGGT Internal Priors for Sensor-Geometry-Free Multi-View Indoor 3D Object Detection
by: Cao, Yang, et al.
Published: (2026)

Dense Semantic Matching with VGGT Prior
by: Yang, Songlin, et al.
Published: (2025)

GPA-VGGT:Adapting VGGT to Large Scale Localization by Self-Supervised Learning with Geometry and Physics Aware Loss
by: Xu, Yangfan, et al.
Published: (2026)

HD-VGGT: High-Resolution Visual Geometry Transformer
by: Chen, Tianrun, et al.
Published: (2026)

FastVGGT: Training-Free Acceleration of Visual Geometry Transformer
by: Shen, You, et al.
Published: (2025)

VGGT-X: When VGGT Meets Dense Novel View Synthesis
by: Liu, Yang, et al.
Published: (2025)

VGGT-Segmentor: Geometry-Enhanced Cross-View Segmentation
by: Gao, Yulu, et al.
Published: (2026)

VGGT-MPR: VGGT-Enhanced Multimodal Place Recognition in Autonomous Driving Environments
by: Xu, Jingyi, et al.
Published: (2026)

XStreamVGGT: Extremely Memory-Efficient Streaming Vision Geometry Grounded Transformer with KV Cache Compression
by: Su, Zunhai, et al.
Published: (2026)

XStreamVGGT: Extremely Memory-Efficient Streaming Vision Geometry Grounded Transformer with KV Cache Compression
by: Su, Zunhai, et al.
Published: (2026)

VGGT4D: Mining Motion Cues in Visual Geometry Transformers for 4D Scene Reconstruction
by: Hu, Yu, et al.
Published: (2025)

StereoVGGT: A Training-Free Visual Geometry Transformer for Stereo Vision
by: Chen, Ziyang, et al.
Published: (2026)

OmniVGGT: Omni-Modality Driven Visual Geometry Grounded Transformer
by: Peng, Haosong, et al.
Published: (2025)

InfiniteVGGT: Visual Geometry Grounded Transformer for Endless Streams
by: Yuan, Shuai, et al.
Published: (2026)

VGGT-Occ: Geometry-Grounded and Density-Aware Gated Fusion for 3D Occupancy Prediction
by: Chen, Xun, et al.
Published: (2026)

4DLangVGGT: 4D Language-Visual Geometry Grounded Transformer
by: Wu, Xianfeng, et al.
Published: (2025)

PAGE-4D: VGGT-4D Perception via Disentangled Pose and Geometry Estimation
by: Zhou, Kaichen, et al.
Published: (2025)

SceneVGGT: VGGT-based online 3D semantic SLAM for indoor scene understanding and navigation
by: Gelencsér-Horváth, Anna, et al.
Published: (2026)

VGGT-Long: Chunk it, Loop it, Align it -- Pushing VGGT's Limits on Kilometer-scale Long RGB Sequences
by: Deng, Kai, et al.
Published: (2025)

TurboVGGT: Fast Visual Geometry Reconstruction with Adaptive Alternating Attention
by: Huang, David, et al.
Published: (2026)

VGGT-360: Geometry-Consistent Zero-Shot Panoramic Depth Estimation
by: Yuan, Jiayi, et al.
Published: (2026)

FlashVGGT: Efficient and Scalable Visual Geometry Transformers with Compressed Descriptor Attention
by: Wang, Zipeng, et al.
Published: (2025)

AVGGT: Rethinking Global Attention for Accelerating VGGT
by: Sun, Xianbing, et al.
Published: (2025)

SwiftVGGT: A Scalable Visual Geometry Grounded Transformer for Large-Scale Scenes
by: Lee, Jungho, et al.
Published: (2025)

DriveVGGT: Calibration-Constrained Visual Geometry Transformers for Multi-Camera Autonomous Driving
by: Jia, Xiaosong, et al.
Published: (2025)

DynamicVGGT: Learning Dynamic Point Maps for 4D Scene Reconstruction in Autonomous Driving
by: He, Zhuolin, et al.
Published: (2026)

Analyzing the Mechanism of Attention Collapse in VGGT from a Dynamics Perspective
by: Li, Huan, et al.
Published: (2025)

VGGT-CD: Training-Free Robust Registration for 3D Change Detection
by: Zhang, Wei, et al.
Published: (2026)

EventVGGT: Exploring Cross-Modal Distillation for Consistent Event-based Depth Estimation
by: Ren, Yinrui, et al.
Published: (2026)

S-VGGT: Structure-Aware Subscene Decomposition for Scalable 3D Foundation Models
by: Li, Xinze, et al.
Published: (2026)

VGGT-Motion: Motion-Aware Calibration-Free Monocular SLAM for Long-Range Consistency
by: Xiong, Zhuang, et al.
Published: (2026)