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

• URL: http://arxiv.org/abs/2604.02009v1
• Date: Thu, 02 Apr 2026 13:13:17 GMT
• Title: Test-Time Adaptation for Height Completion via Self-Supervised ViT Features and Monocular Foundation Models
• Abstract summary: Prior2DSM is a training-free framework for metric DSM completion that operates entirely at test time.<n>It reduces reconstruction error while preserving structural fidelity, achieving up to a 46% reduction in RMSE.
• Score: 1.433758865948252
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 However, large-scale DSMs frequently contain incomplete or outdated regions due to acquisition limitations, reconstruction artifacts, or changes in the built environment.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.

Related papers

• Multimodal Foundation Models Adaptation based on Domain-Aware Relaxed Orthogonal Subspace for Remote Sensing [16.45880716714667]
  Domain-aware Relaxed Orthogonal Subspace adaptation (DROS)<n>DROS reformulates low-rank adaptation as data-conditioned subspace learning and flexible subspace adaptation.<n>Experiments on multiple remote sensing benchmarks demonstrate that DROS achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-09-12T02:19:11Z)
• LCPNet: Latent Consistent Proximal Unfolding Network for Infrared Small Target Detection [50.3892176822492]
  Infrared small target detection (IRSTD) aims to identify long distance small targets from complex infrared backgrounds.<n>Deep learning methods have improved IRSTD by learning discriminative image-to-mask mappings.<n>Deep unfolding methods partially address this issue by embedding model-driven iterations into neural networks.<n>We propose Latent Consistent Proximal unfolding network (LCPNet) to address these limitations.
  arXiv  Detail & Related papers  (2026-07-06T02:15:09Z)
• VAN-AD: Visual Masked Autoencoder with Normalizing Flow For Time Series Anomaly Detection [17.972690703544764]
  Time series anomaly detection (TSAD) is essential for maintaining the reliability and security of IoT-enabled service systems.<n>In this paper, we investigate the applicability of large-scale vision models to TSAD.<n>We propose VAN-AD, a novel MAE-based framework for TSAD.
  arXiv  Detail & Related papers  (2026-03-27T08:48:59Z)
• VFM-Recon: Unlocking Cross-Domain Scene-Level Neural Reconstruction with Scale-Aligned Foundation Priors [49.39553550491549]
  We present VFMRecon, the first attempt to bridge transferable VFM priors with scaleconsistent requirements in scene-level neural reconstruction.<n> Specifically, we first introduce a lightweight scale alignment stage that restores multiview scale coherence.<n>We then integrate pretrained VFM features into the neural volumetric reconstruction pipeline via lightweight task-specific adapters.
  arXiv  Detail & Related papers  (2026-03-13T05:00:44Z)
• PDE foundation model-accelerated inverse estimation of system parameters in inertial confinement fusion [36.885866084809926]
  We study an inverse problem in inertial confinement fusion (ICF): estimating system parameters (inputs) from multi-modal, snapshot-style observations (outputs)<n>We finetune the PDE foundation model and train a lightweight task-specific head to jointly reconstruct hyperspectral images and regress system parameters.<n>Experiments show consistent improvements in both reconstruction and regression losses as the amount of training data increases.
  arXiv  Detail & Related papers  (2026-03-04T21:07:43Z)
• Depth Completion as Parameter-Efficient Test-Time Adaptation [66.72360181325877]
  CAPA is a parameter-efficient test-time optimization framework that adapts pre-trained 3D foundation models (FMs) for depth completion.<n>For videos, CAPA introduces sequence-level parameter sharing, jointly adapting all frames to exploit temporal correlations, improve robustness, and enforce multi-frame consistency.
  arXiv  Detail & Related papers  (2026-02-16T13:53:23Z)
• MEMTS: Internalizing Domain Knowledge via Parameterized Memory for Retrieval-Free Domain Adaptation of Time Series Foundation Models [51.506429027626005]
  Memory for Time Series (MEMTS) is a lightweight and plug-and-play method for retrieval-free domain adaptation in time series forecasting.<n>Key component of MEMTS is a Knowledge Persistence Module (KPM), which internalizes domain-specific temporal dynamics.<n>This paradigm shift enables MEMTS to achieve accurate domain adaptation with constant-time inference and near-zero latency.
  arXiv  Detail & Related papers  (2026-02-14T14:00:06Z)
• Beyond Weight Adaptation: Feature-Space Domain Injection for Cross-Modal Ship Re-Identification [3.6907522136316975]
  Cross-Modality Ship Re-Identification (CMS Re-ID) is critical for achieving all-day and all-weather maritime target tracking.<n>We explore the potential of Vision Foundation Models (VFMs) in bridging modality gaps.<n>We propose a novel PEFT strategy termed Domain Representation Injection (DRI)
  arXiv  Detail & Related papers  (2025-12-24T02:30:23Z)
• Enhancing Generalization of Depth Estimation Foundation Model via Weakly-Supervised Adaptation with Regularization [21.788680301776207]
  We propose WeSTAR, a parameter-efficient framework that performs Weakly supervised Self-Training Adaptation with Regularization.<n>We first adopt a dense self-training objective as the primary source of structural self-supervision.<n>To further improve robustness, we introduce semantically-aware hierarchical normalization.
  arXiv  Detail & Related papers  (2025-11-18T08:16:16Z)
• Survey on Monocular Metric Depth Estimation [2.436681150766912]
  Monocular Metric Depth Estimation (MMDE) produces depth maps with absolute scale, ensuring geometric consistency.<n>This survey reviews the evolution of MMDE, from geometry-based methods to state-of-the-art deep models.<n>Methodological advances are analyzed, covering domain generalization, boundary preservation, and the integration of synthetic and real data.
  arXiv  Detail & Related papers  (2025-01-21T02:51:10Z)
• Relative Pose Estimation through Affine Corrections of Monocular Depth Priors [69.59216331861437]
  We develop three solvers for relative pose estimation that explicitly account for independent affine (scale and shift) ambiguities.<n>We propose a hybrid estimation pipeline that combines our proposed solvers with classic point-based solvers and epipolar constraints.
  arXiv  Detail & Related papers  (2025-01-09T18:58:30Z)
• SMILE: Zero-Shot Sparse Mixture of Low-Rank Experts Construction From Pre-Trained Foundation Models [85.67096251281191]
  We present an innovative approach to model fusion called zero-shot Sparse MIxture of Low-rank Experts (SMILE) construction. SMILE allows for the upscaling of source models into an MoE model without extra data or further training. We conduct extensive experiments across diverse scenarios, such as image classification and text generation tasks, using full fine-tuning and LoRA fine-tuning.
  arXiv  Detail & Related papers  (2024-08-19T17:32:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.