GrounDiff: Diffusion-Based Ground Surface Generation from Digital Surface Models

• URL: http://arxiv.org/abs/2511.10391v1
• Date: Fri, 14 Nov 2025 01:48:48 GMT
• Title: GrounDiff: Diffusion-Based Ground Surface Generation from Digital Surface Models
• Authors: Oussema Dhaouadi, Johannes Meier, Jacques Kaiser, Daniel Cremers,
• Abstract summary: Ground Diffusion (GrounDiff) is the first diffusion-based framework that iteratively removes non-ground structures.<n>We evaluate our method on the DSM-to-DTM translation task across diverse datasets.<n>Our method achieves up to 81% lower distance error compared to specialized techniques on the GeRoD benchmark.
• Score: 42.398429909141306
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Digital Terrain Models (DTMs) represent the bare-earth elevation and are important in numerous geospatial applications. Such data models cannot be directly measured by sensors and are typically generated from Digital Surface Models (DSMs) derived from LiDAR or photogrammetry. Traditional filtering approaches rely on manually tuned parameters, while learning-based methods require well-designed architectures, often combined with post-processing. To address these challenges, we introduce Ground Diffusion (GrounDiff), the first diffusion-based framework that iteratively removes non-ground structures by formulating the problem as a denoising task. We incorporate a gated design with confidence-guided generation that enables selective filtering. To increase scalability, we further propose Prior-Guided Stitching (PrioStitch), which employs a downsampled global prior automatically generated using GrounDiff to guide local high-resolution predictions. We evaluate our method on the DSM-to-DTM translation task across diverse datasets, showing that GrounDiff consistently outperforms deep learning-based state-of-the-art methods, reducing RMSE by up to 93% on ALS2DTM and up to 47% on USGS benchmarks. In the task of road reconstruction, which requires both high precision and smoothness, our method achieves up to 81% lower distance error compared to specialized techniques on the GeRoD benchmark, while maintaining competitive surface smoothness using only DSM inputs, without task-specific optimization. Our variant for road reconstruction, GrounDiff+, is specifically designed to produce even smoother surfaces, further surpassing state-of-the-art methods. The project page is available at https://deepscenario.github.io/GrounDiff/.

Related papers

• UniSH: Unifying Scene and Human Reconstruction in a Feed-Forward Pass [83.7071371474926]
  UniSH is a unified, feed-forward framework for joint metric-scale 3D scene and human reconstruction.<n>Our framework bridges strong, disparate priors from scene reconstruction and HMR.<n>Our model achieves state-of-the-art performance on human-centric scene reconstruction.
  arXiv  Detail & Related papers  (2026-01-03T16:06:27Z)
• Digital Elevation Model Estimation from RGB Satellite Imagery using Generative Deep Learning [1.0207955314209534]
  This study proposes an approach to generate DEM from freely available RGB satellite imagery using generative deep learning.<n>We first developed a global dataset consisting of 12K RGB-DEM pairs using Landsat satellite imagery and NASA's SRTM digital elevation data.<n>A unique preprocessing pipeline was implemented to select high-quality, cloud-free regions and aggregate normalized RGB composites from Landsat imagery.
  arXiv  Detail & Related papers  (2025-11-26T23:50:00Z)
• GauSSmart: Enhanced 3D Reconstruction through 2D Foundation Models and Geometric Filtering [50.675710727721786]
  We propose GauSSmart, a hybrid method that bridges 2D foundational models and 3D Gaussian Splatting reconstruction.<n>Our approach integrates established 2D computer vision techniques, including convex filtering and semantic feature supervision.<n>We validate our approach across three datasets, where GauSSmart consistently outperforms existing Gaussian Splatting.
  arXiv  Detail & Related papers  (2025-10-16T03:38:26Z)
• DEPTHOR++: Robust Depth Enhancement from a Real-World Lightweight dToF and RGB Guidance [14.818201604060144]
  DEPTHOR++ is a practical and novel depth completion framework.<n>It enhances robustness to noisy dToF inputs from three key aspects.<n>On the ZJU-L5 dataset and real-world samples, our training strategy significantly boosts existing depth completion models.
  arXiv  Detail & Related papers  (2025-09-30T16:41:11Z)
• Generating Synthetic Stereo Datasets using 3D Gaussian Splatting and Expert Knowledge Transfer [16.040335263873278]
  We introduce a 3D Gaussian Splatting (3DGS)-based pipeline for stereo dataset generation, offering an efficient alternative to Neural Radiance Fields (NeRF)-based methods.<n>We find that when fine-tuning stereo models on 3DGS-generated datasets, we demonstrate competitive performance in zero-shot generalization benchmarks.
  arXiv  Detail & Related papers  (2025-06-05T11:41:09Z)
• DONOD: Efficient and Generalizable Instruction Fine-Tuning for LLMs via Model-Intrinsic Dataset Pruning [22.704995231753397]
  Ad-hoc instruction fine-tuning of large language models (LLMs) is widely adopted for domain-specific adaptation.<n>We propose DONOD, a lightweight model-intrinsic data pruning method.<n>By filtering out 70% of the whole dataset, we improve target-domain accuracy by 14.90% and cross-domain accuracy by 5.67%.
  arXiv  Detail & Related papers  (2025-04-21T02:25:03Z)
• DEPTHOR: Depth Enhancement from a Practical Light-Weight dToF Sensor and RGB Image [8.588871458005114]
  We propose a novel completion-based method, named DEPTHOR, for depth enhancement in computer vision.<n>First, we simulate real-world dToF data from the accurate ground truth in synthetic datasets to enable noise-robust training.<n>Second, we design a novel network that incorporates monocular depth estimation (MDE), leveraging global depth relationships and contextual information to improve prediction in challenging regions.
  arXiv  Detail & Related papers  (2025-04-02T11:02:21Z)
• GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image [94.56927147492738]
  We introduce GeoWizard, a new generative foundation model designed for estimating geometric attributes from single images. We show that leveraging diffusion priors can markedly improve generalization, detail preservation, and efficiency in resource usage. We propose a simple yet effective strategy to segregate the complex data distribution of various scenes into distinct sub-distributions.
  arXiv  Detail & Related papers  (2024-03-18T17:50:41Z)
• GIFD: A Generative Gradient Inversion Method with Feature Domain Optimization [52.55628139825667]
  Federated Learning (FL) has emerged as a promising distributed machine learning framework to preserve clients' privacy. Recent studies find that an attacker can invert the shared gradients and recover sensitive data against an FL system by leveraging pre-trained generative adversarial networks (GAN) as prior knowledge. We propose textbfGradient textbfInversion over textbfFeature textbfDomains (GIFD), which disassembles the GAN model and searches the feature domains of the intermediate layers.
  arXiv  Detail & Related papers  (2023-08-09T04:34:21Z)
• ZARTS: On Zero-order Optimization for Neural Architecture Search [94.41017048659664]
  Differentiable architecture search (DARTS) has been a popular one-shot paradigm for NAS due to its high efficiency. This work turns to zero-order optimization and proposes a novel NAS scheme, called ZARTS, to search without enforcing the above approximation. In particular, results on 12 benchmarks verify the outstanding robustness of ZARTS, where the performance of DARTS collapses due to its known instability issue.
  arXiv  Detail & Related papers  (2021-10-10T09:35:15Z)

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.