# VGG-T3: Offline Feed-Forward 3D Reconstruction at Scale

arXiv: https://arxiv.org/abs/2602.23361 · HTML: https://mlsanity.com/paper/2602.23361/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 85 of its 115 references that are in the map.
- First posted on arXiv 26 Feb 2026.

## Builds on (most cited first, 30 of 85)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [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)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality](https://mlsanity.com/paper/2405.21060/) (2024)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [The Replica Dataset: A Digital Replica of Indoor Spaces](https://mlsanity.com/paper/1906.05797/) (2019)
- [ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes](https://mlsanity.com/paper/2308.11417/) (2023)
- [MegaDepth: Learning Single-View Depth Prediction from Internet Photos](https://mlsanity.com/paper/1804.00607/) (2018)
- [Scaling Vision Transformers to 22 Billion Parameters](https://mlsanity.com/paper/2302.05442/) (2023)
- [Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction](https://mlsanity.com/paper/2109.00512/) (2021)
- [Taskonomy: Disentangling Task Transfer Learning](https://mlsanity.com/paper/1804.08328/) (2018)
- [Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding](https://mlsanity.com/paper/2011.02523/) (2020)
- [From Coarse to Fine: Robust Hierarchical Localization at Large Scale](https://mlsanity.com/paper/1812.03506/) (2018)
- [Continuous 3D Perception Model with Persistent State](https://mlsanity.com/paper/2501.12387/) (2025)
- [DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision](https://mlsanity.com/paper/2312.16256/) (2023)
- [Gated Delta Networks: Improving Mamba2 with Delta Rule](https://mlsanity.com/paper/2412.06464/) (2024)
- [Gated Linear Attention Transformers with Hardware-Efficient Training](https://mlsanity.com/paper/2312.06635/) (2023)
- [TartanAir: A Dataset to Push the Limits of Visual SLAM](https://mlsanity.com/paper/2003.14338/) (2020)
- [Hungry Hungry Hippos: Towards Language Modeling with State Space Models](https://mlsanity.com/paper/2212.14052/) (2022)
- [BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks](https://mlsanity.com/paper/1911.10127/) (2019)
- [Ring Attention with Blockwise Transformers for Near-Infinite Context](https://mlsanity.com/paper/2310.01889/) (2023)
- [Parallelizing Linear Transformers with the Delta Rule over Sequence Length](https://mlsanity.com/paper/2406.06484/) (2024)

## Built on by (most cited first, 18 of 18)

- [LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory](https://mlsanity.com/paper/2603.03269/) (2026)
- [Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective](https://mlsanity.com/paper/2604.14025/) (2026)
- [D'ej`a View: Looping Transformers for Multi-View 3D Reconstruction](https://mlsanity.com/paper/2605.30215/) (2026)
- [Mamba-VGGT: Persistent Long-Sequence Video Geometry Grounded Transformer via External Sliding Window Mamba Memory](https://mlsanity.com/paper/2605.17478/) (2026)
- [R3: 3D Reconstruction via Relative Regression](https://mlsanity.com/paper/2605.26519/) (2026)
- [Anchor3R: Streaming 3D Reconstruction with Transient Anchors for Long-Horizon Visual Mapping](https://mlsanity.com/paper/2606.05035/) (2026)
- [Spark3R: Asymmetric Token Reduction Makes Fast Feed-Forward 3D Reconstruction](https://mlsanity.com/paper/2605.06270/) (2026)
- [TurboVGGT: Fast Visual Geometry Reconstruction with Adaptive Alternating Attention](https://mlsanity.com/paper/2605.14315/) (2026)
- [SAF3R: Dynamic Sparse Attention for Feed-Forward 3D Reconstruction Transformers](https://mlsanity.com/paper/2607.03612/) (2026)
- [ComPose: When to Trust Hands for Object Pose Tracking](https://mlsanity.com/paper/2605.23523/) (2026)
- [Good Token Hunting: A Hitchhiker's Guide to Token Selection for Visual Geometry Transformers](https://mlsanity.com/paper/2605.23892/) (2026)
- [Graph Sparse Sampling: Breaking the Curse of the Horizon in Continuous MDP Planning](https://mlsanity.com/paper/2607.05359/) (2026)
- [Scal3R: Learning Efficient Multi-Relative Pose Query for Scalable Online 3D Reconstruction](https://mlsanity.com/paper/2609.04201/) (2026)
- [VoxelTTO: Voxel-Aligned Feed-Forward 3D Gaussian Splatting with Test-Time Optimization](https://mlsanity.com/paper/2609.21498/) (2026)
- [Adaptive World Memory 3D Foundation Model for Scalable 3D Mapping, Localization, and Rendering](https://mlsanity.com/paper/2609.21502/) (2026)
- [CLoSeR: Closing the Loop for Long-Context Streaming Reconstruction](https://mlsanity.com/paper/2610.01927/) (2026)
- [Zebra3D: Efficient Hybrid Foundation Models For Scalable 3D Reconstruction](https://mlsanity.com/paper/2610.12727/) (2026)
- [InfiniSplat v2: Analyzing and Improving Feed-Forward 3DGS from Any Views](https://mlsanity.com/paper/2610.20341/) (2026)

## Abstract (arXiv)

We present a scalable 3D reconstruction model that addresses a critical limitation in offline feed-forward methods: their computational and memory requirements grow quadratically w.r.t. the number of input images. Our approach is built on the key insight that this bottleneck stems from the varying-length Key-Value (KV) space representation of scene geometry, which we distill into a fixed-size Multi-Layer Perceptron (MLP) via test-time training. VGG-T3 (Visual Geometry Grounded Test Time Training) scales linearly w.r.t. the number of input views, similar to online models, and reconstructs a 1k image collection in just 54 seconds, achieving a 11.6× speed-up over baselines that rely on softmax attention. Since our method retains global scene aggregation capability, our point map reconstruction error outperforming other linear-time methods by large margins. Finally, we demonstrate visual localization capabilities of our model by querying the scene representation with unseen images.