# Test-Time Adaptation for Height Completion via Self-Supervised ViT Features and Monocular Foundation Models

arXiv: https://arxiv.org/abs/2604.02009 · HTML: https://mlsanity.com/paper/2604.02009/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 49 references that are in the map.
- First posted on arXiv 2 Apr 2026.

## Builds on (most cited first, 29 of 29)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [Depth Pro: Sharp Monocular Metric Depth in Less Than a Second](https://mlsanity.com/paper/2410.02073/) (2024)
- [Deep ViT Features as Dense Visual Descriptors](https://mlsanity.com/paper/2112.05814/) (2021)
- [MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details](https://mlsanity.com/paper/2507.02546/) (2025)
- [MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimation](https://mlsanity.com/paper/2307.14460/) (2023)
- [Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimation](https://mlsanity.com/paper/2412.14015/) (2024)
- [Bilateral Propagation Network for Depth Completion](https://mlsanity.com/paper/2403.11270/) (2024)
- [Text2Earth: Unlocking Text-driven Remote Sensing Image Generation with a Global-Scale Dataset and a Foundation Model](https://mlsanity.com/paper/2501.00895/) (2025)
- [Depth Anything with Any Prior](https://mlsanity.com/paper/2505.10565/) (2025)
- [IM2HEIGHT: Height Estimation from Single Monocular Imagery via Fully Residual Convolutional-Deconvolutional Network](https://mlsanity.com/paper/1802.10249/) (2018)
- [Test-Time Adaptation for Depth Completion](https://mlsanity.com/paper/2402.03312/) (2024)
- [Multi-view Reconstruction via SfM-guided Monocular Depth Estimation](https://mlsanity.com/paper/2503.14483/) (2025)
- [GlobalBuildingAtlas: An Open Global and Complete Dataset of Building Polygons, Heights and LoD1 3D Models](https://mlsanity.com/paper/2506.04106/) (2025)
- [Depth Any Canopy: Leveraging Depth Foundation Models for Canopy Height Estimation](https://mlsanity.com/paper/2408.04523/) (2024)
- [Towards 3D Scene Reconstruction from Locally Scale-Aligned Monocular Video Depth](https://mlsanity.com/paper/2202.01470/) (2022)
- [SynRS3D: A Synthetic Dataset for Global 3D Semantic Understanding from Monocular Remote Sensing Imagery](https://mlsanity.com/paper/2406.18151/) (2024)
- [Void Filling of Digital Elevation Models with Deep Generative Models](https://mlsanity.com/paper/1811.12693/) (2018)
- [Zero-shot Depth Completion via Test-time Alignment with Affine-invariant Depth Prior](https://mlsanity.com/paper/2502.06338/) (2025)
- [Enhancing Monocular Height Estimation via Sparse LiDAR-Guided Correction](https://mlsanity.com/paper/2505.06905/) (2025)
- [Depth Completion as Parameter-Efficient Test-Time Adaptation](https://mlsanity.com/paper/2602.14751/) (2026)
- [StreamTTO: Efficient Online Test-Time Optimization for Video Depth Completion](https://mlsanity.com/paper/2603.01765/) (2026)
- [Monocular One-Shot Metric-Depth Alignment for RGB-Based Robot Grasping](https://mlsanity.com/paper/2506.17110/) (2025)
- [Propagating Sparse Depth via Depth Foundation Model for Out-of-Distribution Depth Completion](https://mlsanity.com/paper/2508.04984/) (2025)
- [Reconstructing Building Height from Spaceborne TomoSAR Point Clouds Using a Dual-Topology Network](https://mlsanity.com/paper/2601.00658/) (2026)
- [A Novel Solution for Drone Photogrammetry with Low-overlap Aerial Images using Monocular Depth Estimation](https://mlsanity.com/paper/2503.04513/) (2025)
- [Enhancing Generalization of Depth Estimation Foundation Model via Weakly-Supervised Adaptation with Regularization](https://mlsanity.com/paper/2511.14238/) (2025)

## Abstract (arXiv)

Accurate digital surface models (DSMs) are essential for many geospatial applications, including urban monitoring, environmental analyses, infrastructure management, and change detection. However, large-scale DSMs frequently contain incomplete or outdated regions due to acquisition limitations, reconstruction artifacts, or changes in the built environment. Traditional height completion approaches primarily rely on spatial interpolation or which assume spatial continuity and therefore fail when objects are missing. Recent learning-based approaches improve reconstruction quality but typically require supervised training on sensor-specific datasets, limiting their generalization across domains and sensing conditions. We propose Prior2DSM, a training-free framework for metric DSM completion that operates entirely at test time by leveraging foundation models. Unlike previous height completion approaches that require task-specific training, the proposed method combines self-supervised Vision Transformer (ViT) features from DINOv3 with monocular depth foundation models to propagate metric information from incomplete height priors through semantic feature-space correspondence. Test-time adaptation (TTA) is performed using parameter-efficient low-rank adaptation (LoRA) together with a lightweight multilayer perceptron (MLP), which predicts spatially varying scale and shift parameters to convert relative depth estimates into metric heights. Experiments demonstrate consistent improvements over interpolation based methods, prior-based rescaling height approaches, and state-of-the-art monocular depth estimation models. Prior2DSM reduces reconstruction error while preserving structural fidelity, achieving up to a 46% reduction in RMSE compared to linear fitting of MDE, and further enables DSM updating and coupled RGB-DSM generation.