# Emergent Extreme-View Geometry in 3D Foundation Models

arXiv: https://arxiv.org/abs/2511.22686 · HTML: https://mlsanity.com/paper/2511.22686/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 68 references that are in the map.
- First posted on arXiv 27 Nov 2025.

## Builds on (most cited first, 30 of 45)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [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)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models](https://mlsanity.com/paper/2106.10199/) (2021)
- [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)
- [MegaDepth: Learning Single-View Depth Prediction from Internet Photos](https://mlsanity.com/paper/1804.00607/) (2018)
- [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)
- [Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass](https://mlsanity.com/paper/2501.13928/) (2025)
- [Neural RGB-D Surface Reconstruction](https://mlsanity.com/paper/2104.04532/) (2021)
- [RoMa: Robust Dense Feature Matching](https://mlsanity.com/paper/2305.15404/) (2023)
- [ReFusion: 3D Reconstruction in Dynamic Environments for RGB-D Cameras Exploiting Residuals](https://mlsanity.com/paper/1905.02082/) (2019)
- [FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Views](https://mlsanity.com/paper/2502.12138/) (2025)
- [PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Prediction](https://mlsanity.com/paper/2311.12024/) (2023)
- [MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motion](https://mlsanity.com/paper/2409.19152/) (2024)
- [PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustment](https://mlsanity.com/paper/2306.15667/) (2023)
- [Cameras as Rays: Pose Estimation via Ray Diffusion](https://mlsanity.com/paper/2402.14817/) (2024)
- [RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wild](https://mlsanity.com/paper/2208.05963/) (2022)
- [FastVGGT: Training-Free Acceleration of Visual Geometry Transformer](https://mlsanity.com/paper/2509.02560/) (2025)
- [Easi3R: Estimating Disentangled Motion from DUSt3R Without Training](https://mlsanity.com/paper/2503.24391/) (2025)
- [RelPose++: Recovering 6D Poses from Sparse-view Observations](https://mlsanity.com/paper/2305.04926/) (2023)
- [What Matters in Transformers? Not All Attention is Needed](https://mlsanity.com/paper/2406.15786/) (2024)
- [MegaScenes: Scene-Level View Synthesis at Scale](https://mlsanity.com/paper/2406.11819/) (2024)
- [SparsePose: Sparse-View Camera Pose Regression and Refinement](https://mlsanity.com/paper/2211.16991/) (2022)
- [Wide-Baseline Relative Camera Pose Estimation with Directional Learning](https://mlsanity.com/paper/2106.03336/) (2021)

## Built on by (most cited first, 6 of 6)

- [Beyond 2D Matching: A Unified Single-Stage Framework for Geometry-Aware Cross-View Object Geo-Localization](https://mlsanity.com/paper/2606.30576/) (2026)
- [Zero-Shot Novel Depth Synthesis Using 3D Foundation Models Scene Representations](https://mlsanity.com/paper/2609.04174/) (2026)
- [RoMa-Omega: What Feed-Forward 3D Models Know About Image Matching](https://mlsanity.com/paper/2609.09507/) (2026)
- [GeoCond: A Conditioning-Aware Reliability Adapter for Feed-Forward 3D Reconstruction](https://mlsanity.com/paper/2609.18465/) (2026)
- [When Wider Views Fail: Stress-Testing Feed-Forward 3D Reconstruction](https://mlsanity.com/paper/2609.24839/) (2026)
- [RDGSplat: Render-Dedicated Geometry for Novel View Synthesis](https://mlsanity.com/paper/2610.09173/) (2026)

## Abstract (arXiv)

3D foundation models (3DFMs) have recently transformed 3D vision, enabling joint prediction of depths, poses, and point maps directly from images. Yet their ability to reason under extreme, non-overlapping views remains largely unexplored. In this work, we study their internal representations and find that 3DFMs exhibit an emergent understanding of extreme-view geometry, despite never being trained for such conditions. To further enhance these capabilities, we introduce a lightweight alignment scheme that refines their internal 3D representation by tuning only a small subset of backbone bias terms, leaving all decoder heads frozen. This targeted adaptation substantially improves relative pose estimation under extreme viewpoints without degrading per-image depth or point quality. Additionally, we contribute MegaUnScene, a new benchmark of Internet scenes unseen by existing 3DFMs, with dedicated test splits for both relative pose estimation and dense 3D reconstruction. All code and data will be released.