# FlashVGGT: Efficient and Scalable Visual Geometry Transformers with Compressed Descriptor Attention

arXiv: https://arxiv.org/abs/2512.01540 · HTML: https://mlsanity.com/paper/2512.01540/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 50 of its 69 references that are in the map.
- First posted on arXiv 1 Dec 2025.

## Builds on (most cited first, 30 of 50)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [Perceiver: General Perception with Iterative Attention](https://mlsanity.com/paper/2103.03206/) (2021)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [Vision Transformers Need Registers](https://mlsanity.com/paper/2309.16588/) (2023)
- [Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction](https://mlsanity.com/paper/2109.00512/) (2021)
- [Continuous 3D Perception Model with Persistent State](https://mlsanity.com/paper/2501.12387/) (2025)
- [Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference](https://mlsanity.com/paper/2406.10774/) (2024)
- [BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks](https://mlsanity.com/paper/1911.10127/) (2019)
- [ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data](https://mlsanity.com/paper/2111.08897/) (2021)
- [MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion](https://mlsanity.com/paper/2410.03825/) (2024)
- [Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass](https://mlsanity.com/paper/2501.13928/) (2025)
- [MapAnything: Universal Feed-Forward Metric 3D Reconstruction](https://mlsanity.com/paper/2509.13414/) (2025)
- [Neural RGB-D Surface Reconstruction](https://mlsanity.com/paper/2104.04532/) (2021)
- [DeepMVS: Learning Multi-view Stereopsis](https://mlsanity.com/paper/1804.00650/) (2018)
- [EfficientFormer: Vision Transformers at MobileNet Speed](https://mlsanity.com/paper/2206.01191/) (2022)
- [Visual Geometry Grounded Deep Structure From Motion](https://mlsanity.com/paper/2312.04563/) (2023)
- [Token Merging for Fast Stable Diffusion](https://mlsanity.com/paper/2303.17604/) (2023)
- [Global Structure-from-Motion Revisited](https://mlsanity.com/paper/2407.20219/) (2024)

## Built on by (most cited first, 17 of 17)

- [MeMix: Writing Less, Remembering More for Streaming 3D Reconstruction](https://mlsanity.com/paper/2603.15330/) (2026)
- [Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective](https://mlsanity.com/paper/2604.14025/) (2026)
- [Keyframe-Based Feed-Forward Visual Odometry](https://mlsanity.com/paper/2601.16020/) (2026)
- [Lite3R: A Model-Agnostic Framework for Efficient Feed-Forward 3D Reconstruction](https://mlsanity.com/paper/2605.11354/) (2026)
- [TurboVGGT: Fast Visual Geometry Reconstruction with Adaptive Alternating Attention](https://mlsanity.com/paper/2605.14315/) (2026)
- [Diversity-aware View Partitioning for Scalable VGGT](https://mlsanity.com/paper/2607.01885/) (2026)
- [SAF3R: Dynamic Sparse Attention for Feed-Forward 3D Reconstruction Transformers](https://mlsanity.com/paper/2607.03612/) (2026)
- [PrePARE: Pre-AA Token Pruning for Frozen Multi-View Geometry Transformers](https://mlsanity.com/paper/2605.08371/) (2026)
- [Not All Tasks Quantize Equally: Fisher-Guided Quantization for Visual Geometry Transformer](https://mlsanity.com/paper/2605.15828/) (2026)
- [Efficient 3D Content Reconstruction and Generation](https://mlsanity.com/paper/2605.18052/) (2026)
- [UniT: Unified Geometry Learning with Group Autoregressive Transformer](https://mlsanity.com/paper/2605.21131/) (2026)
- [Good Token Hunting: A Hitchhiker's Guide to Token Selection for Visual Geometry Transformers](https://mlsanity.com/paper/2605.23892/) (2026)
- [EigeNet: Geometry-Informed Multi-Modal Learning for Few-shot Novel View RIR Prediction](https://mlsanity.com/paper/2605.28101/) (2026)
- [Scal3R: Learning Efficient Multi-Relative Pose Query for Scalable Online 3D Reconstruction](https://mlsanity.com/paper/2609.04201/) (2026)
- [SpatialSpeak: QA-Native Reconstruction with Local and Global Context for Spatial Chain-of-Thought Reasoning](https://mlsanity.com/paper/2609.33616/) (2026)
- [OTT3R: Multi-View 3D Reconstruction and Fast Dataset Generation at 1% Compute](https://mlsanity.com/paper/2609.36374/) (2026)
- [Zebra3D: Efficient Hybrid Foundation Models For Scalable 3D Reconstruction](https://mlsanity.com/paper/2610.12727/) (2026)

## Abstract (arXiv)

3D reconstruction from multi-view images is a core challenge in computer vision. Recently, feed-forward methods have emerged as efficient and robust alternatives to traditional per-scene optimization techniques. Among them, state-of-the-art models like the Visual Geometry Grounding Transformer (VGGT) leverage full self-attention over all image tokens to capture global relationships. However, this approach suffers from poor scalability due to the quadratic complexity of self-attention and the large number of tokens generated in long image sequences. In this work, we introduce FlashVGGT, an efficient alternative that addresses this bottleneck through a descriptor-based attention mechanism. Instead of applying dense global attention across all tokens, FlashVGGT compresses spatial information from each frame into a compact set of descriptor tokens. Global attention is then computed as cross-attention between the full set of image tokens and this smaller descriptor set, significantly reducing computational overhead. Moreover, the compactness of the descriptors enables online inference over long sequences via a chunk-recursive mechanism that reuses cached descriptors from previous chunks. Experimental results show that FlashVGGT achieves reconstruction accuracy competitive with VGGT while reducing inference time to just 9.3% of VGGT for 1,000 images, and scaling efficiently to sequences exceeding 3,000 images. Our project page is available at https://wzpscott.github.io/flashvggt_page/.