# Dens3R: A Foundation Model for 3D Geometry Prediction

arXiv: https://arxiv.org/abs/2507.16290 · HTML: https://mlsanity.com/paper/2507.16290/

## Key facts

- Cited by 46 papers in the map (data through 14 Oct 2026).
- Builds on 69 of its 93 references that are in the map.
- First posted on arXiv 22 Jul 2025.

## Builds on (most cited first, 30 of 69)

- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields](https://mlsanity.com/paper/2103.13415/) (2021)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction](https://mlsanity.com/paper/2106.10689/) (2021)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data](https://mlsanity.com/paper/2401.10891/) (2024)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections](https://mlsanity.com/paper/2008.02268/) (2020)
- [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019)
- [Volume Rendering of Neural Implicit Surfaces](https://mlsanity.com/paper/2106.12052/) (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)
- [Playing for Data: Ground Truth from Computer Games](https://mlsanity.com/paper/1608.02192/) (2016)
- [Objaverse-XL: A Universe of 10M+ 3D Objects](https://mlsanity.com/paper/2307.05663/) (2023)
- [Extending Context Window of Large Language Models via Positional Interpolation](https://mlsanity.com/paper/2306.15595/) (2023)
- [MegaDepth: Learning Single-View Depth Prediction from Internet Photos](https://mlsanity.com/paper/1804.00607/) (2018)
- [Argoverse: 3D Tracking and Forecasting with Rich Maps](https://mlsanity.com/paper/1911.02620/) (2019)
- [Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering](https://mlsanity.com/paper/2312.00109/) (2023)
- [ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth](https://mlsanity.com/paper/2302.12288/) (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)
- [AdaBins: Depth Estimation using Adaptive Bins](https://mlsanity.com/paper/2011.14141/) (2020)
- [TartanAir: A Dataset to Push the Limits of Visual SLAM](https://mlsanity.com/paper/2003.14338/) (2020)
- [BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks](https://mlsanity.com/paper/1911.10127/) (2019)
- [UniDepth: Universal Monocular Metric Depth Estimation](https://mlsanity.com/paper/2403.18913/) (2024)
- [Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass](https://mlsanity.com/paper/2501.13928/) (2025)

## Built on by (most cited first, 30 of 46)

- [WorldMirror: Universal 3D World Reconstruction with Any-Prior Prompting](https://mlsanity.com/paper/2510.10726/) (2025)
- [Gen3R: 3D Scene Generation Meets Feed-Forward Reconstruction](https://mlsanity.com/paper/2601.04090/) (2026)
- [VGGT4D: Mining Motion Cues in Visual Geometry Transformers for 4D Scene Reconstruction](https://mlsanity.com/paper/2511.19971/) (2025)
- [VGGT-Omega](https://mlsanity.com/paper/2605.15195/) (2026)
- [From Editor to Dense Geometry Estimator](https://mlsanity.com/paper/2509.04338/) (2025)
- [MoRE: 3D Visual Geometry Reconstruction Meets Mixture-of-Experts](https://mlsanity.com/paper/2510.27234/) (2025)
- [AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backend](https://mlsanity.com/paper/2511.20343/) (2025)
- [FlashVGGT: Efficient and Scalable Visual Geometry Transformers with Compressed Descriptor Attention](https://mlsanity.com/paper/2512.01540/) (2025)
- [Generalizing Visual Geometry Priors to Sparse Gaussian Occupancy Prediction](https://mlsanity.com/paper/2602.21552/) (2026)
- [LoMa: Local Feature Matching Revisited](https://mlsanity.com/paper/2604.04931/) (2026)
- [MoRe: Motion-aware Feed-forward 4D Reconstruction Transformer](https://mlsanity.com/paper/2603.05078/) (2026)
- [VGGT-X: When VGGT Meets Dense Novel View Synthesis](https://mlsanity.com/paper/2509.25191/) (2025)
- [UniPR-3D: Towards Universal Visual Place Recognition with Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2512.21078/) (2025)
- [MVInverse: Feed-forward Multi-view Inverse Rendering in Seconds](https://mlsanity.com/paper/2512.21003/) (2025)
- [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)
- [Video Understanding: From Geometry and Semantics to Unified Models](https://mlsanity.com/paper/2603.17840/) (2026)
- [TrajVG: 3D Trajectory-Coupled Visual Geometry Learning](https://mlsanity.com/paper/2602.04439/) (2026)
- [Understanding the Impact of Geometric Foundation Models on Vision-Language-Action Models](https://mlsanity.com/paper/2605.24642/) (2026)
- [Large Depth Completion Model from Sparse Observations](https://mlsanity.com/paper/2605.30115/) (2026)
- [Mem4D: Decoupling Static and Dynamic Memory for Dynamic Scene Reconstruction](https://mlsanity.com/paper/2508.07908/) (2025)
- [GeoWorld: Providing Full-frame Geometry Features to Facilitate 3D Scene Generation](https://mlsanity.com/paper/2511.23191/) (2025)
- [DAGE: Dual-Stream Architecture for Efficient and Fine-Grained Geometry Estimation](https://mlsanity.com/paper/2603.03744/) (2026)
- [GGPT: Geometry Grounded Point Transformer](https://mlsanity.com/paper/2603.11174/) (2026)
- [HD-VGGT: High-Resolution Visual Geometry Transformer](https://mlsanity.com/paper/2603.27222/) (2026)
- [Towards Consistent Video Geometry Estimation](https://mlsanity.com/paper/2605.30060/) (2026)
- [FoundationGeo: Learning Spatial Pixel-Wise Fields for Monocular Metric Geometry](https://mlsanity.com/paper/2607.11588/) (2026)
- [R3DP: Real-Time 3D-Aware Policy for Embodied Manipulation](https://mlsanity.com/paper/2603.14498/) (2026)
- [SurGe: Improved Surface Geometry in Point Maps](https://mlsanity.com/paper/2605.31577/) (2026)
- [MoWorld: A Flash World Model](https://mlsanity.com/paper/2607.06216/) (2026)

## Abstract (arXiv)

Recent advances in dense 3D reconstruction have led to significant progress, yet achieving accurate unified geometric prediction remains a major challenge. Most existing methods are limited to predicting a single geometry quantity from input images. However, geometric quantities such as depth, surface normals, and point maps are inherently correlated, and estimating them in isolation often fails to ensure consistency, thereby limiting both accuracy and practical applicability. This motivates us to explore a unified framework that explicitly models the structural coupling among different geometric properties to enable joint regression. In this paper, we present Dens3R, a 3D foundation model designed for joint geometric dense prediction and adaptable to a wide range of downstream tasks. Dens3R adopts a two-stage training framework to progressively build a pointmap representation that is both generalizable and intrinsically invariant. Specifically, we design a lightweight shared encoder-decoder backbone and introduce position-interpolated rotary positional encoding to maintain expressive power while enhancing robustness to high-resolution inputs. By integrating image-pair matching features with intrinsic invariance modeling, Dens3R accurately regresses multiple geometric quantities such as surface normals and depth, achieving consistent geometry perception from single-view to multi-view inputs. Additionally, we propose a post-processing pipeline that supports geometrically consistent multi-view inference. Extensive experiments demonstrate the superior performance of Dens3R across various dense 3D prediction tasks and highlight its potential for broader applications.