VFM-Recon: Unlocking Cross-Domain Scene-Level Neural Reconstruction with Scale-Aligned Foundation Priors

• URL: http://arxiv.org/abs/2603.12657v1
• Date: Fri, 13 Mar 2026 05:00:44 GMT
• Title: VFM-Recon: Unlocking Cross-Domain Scene-Level Neural Reconstruction with Scale-Aligned Foundation Priors
• Abstract summary: 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.
• Score: 49.39553550491549
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Scene-level neural volumetric reconstruction from monocular videos remains challenging, especially under severe domain shifts. Although recent advances in vision foundation models (VFMs) provide transferable generalized priors learned from large-scale data, their scaleambiguous predictions are incompatible with the scale consistency required by volumetric fusion. To address this gap, we present VFMRecon, the first attempt to bridge transferable VFM priors with scaleconsistent requirements in scene-level neural reconstruction. Specifically, we first introduce a lightweight scale alignment stage that restores multiview scale coherence. We then integrate pretrained VFM features into the neural volumetric reconstruction pipeline via lightweight task-specific adapters, which are trained for reconstruction while preserving the crossdomain robustness of pretrained representations. We train our model on ScanNet train split and evaluate on both in-distribution ScanNet test split and out-of-distribution TUM RGB-D and Tanks and Temples datasets. The results demonstrate that our model achieves state-of-theart performance across all datasets domains. In particular, on the challenging outdoor Tanks and Temples dataset, our model achieves an F1 score of 70.1 in reconstructed mesh evaluation, substantially outperforming the closest competitor, VGGT, which only attains 51.8.

Related papers

• Test-Time Adaptation for Height Completion via Self-Supervised ViT Features and Monocular Foundation Models [1.433758865948252]
  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.
  arXiv  Detail & Related papers  (2026-04-02T13:13:17Z)
• Sparse Data Tree Canopy Segmentation: Fine-Tuning Leading Pretrained Models on Only 150 Images [0.8294874285381528]
  Tree canopy detection from aerial imagery is an important task for environmental monitoring, urban planning, and ecosystem analysis.<n>Simulating real-life data annotation scarcity, the Solafune Tree Canopy Detection competition provides a small and imbalanced dataset of only 150 annotated images.<n>We evaluate five representative architectures, YOLOv11, Mask R-CNN, DeepLabv3, Swin-UNet, and DINOv2, to assess their suitability for canopy segmentation under extreme data scarcity.
  arXiv  Detail & Related papers  (2026-01-16T01:20:32Z)
• Efficient Self-Supervised Learning for Earth Observation via Dynamic Dataset Curation [67.23953699167274]
  Self-supervised learning (SSL) has enabled the development of vision foundation models for Earth Observation (EO)<n>In EO, this challenge is amplified by the redundancy and heavy-tailed distributions common in satellite imagery.<n>We propose a dynamic dataset pruning strategy designed to improve SSL pre-training by maximizing dataset diversity and balance.
  arXiv  Detail & Related papers  (2025-04-09T15:13:26Z)
• Re-Visible Dual-Domain Self-Supervised Deep Unfolding Network for MRI Reconstruction [48.30341580103962]
  We propose a novel re-visible dual-domain self-supervised deep unfolding network to address these issues.<n>We design a deep unfolding network based on Chambolle and Pock Proximal Point Algorithm (DUN-CP-PPA) to achieve end-to-end reconstruction.<n> Experiments conducted on the fastMRI and IXI datasets demonstrate that our method significantly outperforms state-of-the-art approaches in terms of reconstruction performance.
  arXiv  Detail & Related papers  (2025-01-07T12:29:32Z)
• Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs [76.40876036912537]
  Large Language Models (LLMs) demonstrate strong few-shot adaptability without requiring fine-tuning.<n>Current Visual Foundation Models (VFMs) require explicit fine-tuning with sufficient tuning data.<n>We propose a framework, LoRA Recycle, that distills a meta-LoRA from diverse pre-tuned LoRAs with a meta-learning objective.
  arXiv  Detail & Related papers  (2024-12-03T07:25:30Z)
• Self-Supervised Pre-Training for Transformer-Based Person Re-Identification [54.55281692768765]
  Transformer-based supervised pre-training achieves great performance in person re-identification (ReID) Due to the domain gap between ImageNet and ReID datasets, it usually needs a larger pre-training dataset to boost the performance. This work aims to mitigate the gap between the pre-training and ReID datasets from the perspective of data and model structure.
  arXiv  Detail & Related papers  (2021-11-23T18:59:08Z)
• Unsupervised MRI Reconstruction via Zero-Shot Learned Adversarial Transformers [0.0]
  We introduce a novel unsupervised MRI reconstruction method based on zero-Shot Learned Adrial TransformERs (SLATER) A zero-shot reconstruction is performed on undersampled test data, where inference is performed by optimizing network parameters. Experiments on brain MRI datasets clearly demonstrate the superior performance of SLATER against several state-of-the-art unsupervised methods.
  arXiv  Detail & Related papers  (2021-05-15T02:01:21Z)
• On Robustness and Transferability of Convolutional Neural Networks [147.71743081671508]
  Modern deep convolutional networks (CNNs) are often criticized for not generalizing under distributional shifts. We study the interplay between out-of-distribution and transfer performance of modern image classification CNNs for the first time. We find that increasing both the training set and model sizes significantly improve the distributional shift robustness.
  arXiv  Detail & Related papers  (2020-07-16T18:39:04Z)

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.