# Test3R: Learning to Reconstruct 3D at Test Time

arXiv: https://arxiv.org/abs/2506.13750 · HTML: https://mlsanity.com/paper/2506.13750/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 72 references that are in the map.
- First posted on arXiv 16 Jun 2025.

## Builds on (most cited first, 30 of 43)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [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)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [How Can We Know What Language Models Know?](https://mlsanity.com/paper/1911.12543/) (2019)
- [MVSNet: Depth Inference for Unstructured Multi-view Stereo](https://mlsanity.com/paper/1804.02505/) (2018)
- [Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision](https://mlsanity.com/paper/1912.07372/) (2019)
- [P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks](https://mlsanity.com/paper/2110.07602/) (2021)
- [LightGlue: Local Feature Matching at Light Speed](https://mlsanity.com/paper/2306.13643/) (2023)
- [Continuous 3D Perception Model with Persistent State](https://mlsanity.com/paper/2501.12387/) (2025)
- [MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion](https://mlsanity.com/paper/2410.03825/) (2024)
- [Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching](https://mlsanity.com/paper/1912.06378/) (2019)
- [Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass](https://mlsanity.com/paper/2501.13928/) (2025)
- [D2-Net: A Trainable CNN for Joint Detection and Description of Local Features](https://mlsanity.com/paper/1905.03561/) (2019)
- [Neural RGB-D Surface Reconstruction](https://mlsanity.com/paper/2104.04532/) (2021)
- [3D Reconstruction with Spatial Memory](https://mlsanity.com/paper/2408.16061/) (2024)
- [Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstruction](https://mlsanity.com/paper/2205.15848/) (2022)
- [DeMoN: Depth and Motion Network for Learning Monocular Stereo](https://mlsanity.com/paper/1612.02401/) (2016)
- [Pixel-Perfect Structure-from-Motion with Featuremetric Refinement](https://mlsanity.com/paper/2108.08291/) (2021)
- [NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo](https://mlsanity.com/paper/2109.01129/) (2021)
- [Robust Test-Time Adaptation in Dynamic Scenarios](https://mlsanity.com/paper/2303.13899/) (2023)
- [DeepV2D: Video to Depth with Differentiable Structure from Motion](https://mlsanity.com/paper/1812.04605/) (2018)
- [Neural-Guided RANSAC: Learning Where to Sample Model Hypotheses](https://mlsanity.com/paper/1905.04132/) (2019)
- [Self-Supervised Policy Adaptation during Deployment](https://mlsanity.com/paper/2007.04309/) (2020)
- [Learning by Transduction](https://mlsanity.com/paper/1301.7375/) (2013)

## Built on by (most cited first, 20 of 20)

- [TTT3R: 3D Reconstruction as Test-Time Training](https://mlsanity.com/paper/2509.26645/) (2025)
- [Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Survey](https://mlsanity.com/paper/2507.14501/) (2025)
- [VGGT-Omega](https://mlsanity.com/paper/2605.15195/) (2026)
- [TokenGS: Decoupling 3D Gaussian Prediction from Pixels with Learnable Tokens](https://mlsanity.com/paper/2604.15239/) (2026)
- [Test-Time Training with KV Binding Is Secretly Linear Attention](https://mlsanity.com/paper/2602.21204/) (2026)
- [tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction](https://mlsanity.com/paper/2602.20160/) (2026)
- [TTSA3R: Training-Free Temporal-Spatial Adaptive Persistent State for Streaming 3D Reconstruction](https://mlsanity.com/paper/2601.22615/) (2026)
- [Review of Feed-forward 3D Reconstruction: From DUSt3R to VGGT](https://mlsanity.com/paper/2507.08448/) (2025)
- [Fin3R: Fine-tuning Feed-forward 3D Reconstruction Models via Monocular Knowledge Distillation](https://mlsanity.com/paper/2511.22429/) (2025)
- [Depth Completion as Parameter-Efficient Test-Time Adaptation](https://mlsanity.com/paper/2602.14751/) (2026)
- [CloseUpShot: Close-up Novel View Synthesis from Sparse-views via Point-conditioned Diffusion Model](https://mlsanity.com/paper/2511.13121/) (2025)
- [Learning 3D Reconstruction with Priors in Test Time](https://mlsanity.com/paper/2604.03878/) (2026)
- [Online3R: Online Learning for Consistent Sequential Reconstruction Based on Geometry Foundation Model](https://mlsanity.com/paper/2604.09480/) (2026)
- [Free Geometry: Refining 3D Reconstruction from Longer Versions of Itself](https://mlsanity.com/paper/2604.14048/) (2026)
- [ASV3D: Adapting Diffusion-Based Single-View 3D Reconstruction with Extra Imagery](https://mlsanity.com/paper/2608.08132/) (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)
- [Streaming4D: Accelerate 4D World Models via Block-wise Video Generation and Incremental Reconstruction](https://mlsanity.com/paper/2609.00610/) (2026)
- [LVSPM: Long Sequence View Synthesis and Pose Estimation Model](https://mlsanity.com/paper/2610.10960/) (2026)
- [PURE: Refining Feed-forward 3D Reconstruction with Unlabeled Post-training](https://mlsanity.com/paper/2610.14698/) (2026)

## Abstract (arXiv)

Dense matching methods like DUSt3R regress pairwise pointmaps for 3D reconstruction. However, the reliance on pairwise prediction and the limited generalization capability inherently restrict the global geometric consistency. In this work, we introduce Test3R, a surprisingly simple test-time learning technique that significantly boosts geometric accuracy. Using image triplets (I1,I2,I3), Test3R generates reconstructions from pairs (I1,I2) and (I1,I3). The core idea is to optimize the network at test time via a self-supervised objective: maximizing the geometric consistency between these two reconstructions relative to the common image I1. This ensures the model produces cross-pair consistent outputs, regardless of the inputs. Extensive experiments demonstrate that our technique significantly outperforms previous state-of-the-art methods on the 3D reconstruction and multi-view depth estimation tasks. Moreover, it is universally applicable and nearly cost-free, making it easily applied to other models and implemented with minimal test-time training overhead and parameter footprint. Code is available at https://github.com/nopQAQ/Test3R.