Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

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

About

3D vision foundation models like Visual Geometry Grounded Transformer (VGGT) have advanced greatly in geometric perception. However, it is time-consuming and memory-intensive for long sequences, limiting application to large-scale scenes beyond hundreds of images. To address this, we propose LiteVGGT, achieving up to 10x speedup and substantial memory reduction, enabling efficient processing of 1000-image scenes. We derive two key insights for 3D reconstruction: (1) tokens from local image regions have inherent geometric correlations, leading to high similarity and computational redundancy; (2) token similarity across adjacent network layers remains stable, allowing for reusable merge decisions. Guided by these, we design a simple yet efficient strategy, dubbed geometry-aware cached token merging. We analyze each token's geometric importance, optimizing anchor token selection to better preserve key information for reconstruction. We also cache and reuse merge indices across layers, substantially reducing latency with minimal accuracy impact. This strategy retains VGGT's core performance, enabling efficient fine-tuning and FP8 quantization for further gains. Extensive experiments validate LiteVGGT's effectiveness, scalability, and robustness. Project page: https://garlicba.github.io/LiteVGGT/

Zhijian Shu, Cheng Lin, Tao Xie, Wei Yin, Ben Li, Zhiyuan Pu, Weize Li, Yao Yao, Xun Cao, Xiaoyang Guo, Xiao-Xiao Long• 2025

Related benchmarks

TaskDatasetResultRank
3D ReconstructionNeural RGB-D (NRGBD)
Acc Mean0.031
38
3D Reconstruction7 Scenes--
32
Camera pose estimationCO3D v2
AUC@3083.2
29
Surface ReconstructionTanks&Temples
Mean0.57
27
Point Cloud ReconstructionScanNet-50 11
Chamfer Distance (CD)0.365
11
Point Cloud ReconstructionScanNet 50 11 (96 images)
CD0.329
6
Point Cloud ReconstructionScanNet 50 11 (1000 images)
CD0.428
5
Point Cloud ReconstructionDTU
Accuracy0.652
5
Camera pose estimationTanks & Temples 16 (test)
Barn88.5
4
Camera pose estimationDTU (test)
AUC@3093.3
3
Showing 10 of 10 rows

Other info

Follow for update