LWLukas Winiwarter

Lukas Winiwarter

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Lukas Winiwarter has a total of 264 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    BathyFacto: Refraction-aware two-media Neural Radiance Fields for bathymetry

    by Markus Brezovsky, Anatol Günthner, Frederik Schulte, Lukas Winiwarter, Boris Jutzi, Gottfried Mandlburger

  • Open Access

    A spatially explicit UAV-based decision support tool to assess the protective effect of lying deadwood on snow avalanche release

    by Leon J. Bührle, Tommaso Baggio, Lukas Winiwarter, Marc Adams, Emanuele Lingua, Paul Richter, Frederik Schulte, Kathrin Holstein, Peter Bebi, Thomas Marke, et al.

  • Open Access

    A Spatially Explicit UAV-based Decision Support Tool to Assess the Protective Effect of Lying 2 Deadwood on Snow Avalanche Release

    by Leon J. Bührle, Tommaso Baggio, Lukas Winiwarter, Marc Adams, Emanuele Lingua, Paul Richter, Frederik Schulte, Kathrin Holstein, Peter Bebi, Thomas Marke, et al.

    Mountain forests provide essential ecosystem services, including protection against snow avalanches. Severe disturbances such as windthrow and bark beetle outbreaks generate large amounts of lying deadwood, altering forest structure and affecting avalanche protection. Climate change and legacy effects of past land use are increasing the frequency and severity of such disturbances, while management resources remain limited, highlighting the need for objective decision support tools (DSTs) for evidence-based post-disturbance forest management. We present a spatially explicit DST for deriving spatial indicators related to the protective effect of lying deadwood against avalanche release by integrating terrain, forest structure, and deadwood characteristics. Using high-resolution UAV-derived data, the DSTderivesdeadwoodstructure,models winter terrain under increasing snow depths, and identifies critical snow depths at which surface roughness is reduced. Comparisons with snow-on orthophotos confirm the robustness of the modeled winter terrain. Application across different UAV sensor systems, from low-cost photogrammetry to LiDAR, demonstrates the framework’s broad applicability, showing that even low-cost systems provide suffi ciently accurate results. Analyses across multiple Alpine study sites and post-disturbance management strategies reveal that both the amount and spatial configuration of deadwood control the protective effect. Unmanaged areas maintain the highest protection, requiring snow depths exceeding ∼1.6 m for potential avalanche release, with only minor reductions over a six-year period (∼15% in total). Complete deadwood removal considerably reduces protection, whereas partial removal still provides substantial protection under low-snow conditions. Our open-source DST provides a transparent and practitioner-oriented indicator framework for assessing the protective effects of lying deadwood against snow avalanches under changing disturbance regimes.

  • Open Access

    Using NeRFs for UAV-based 3D reconstruction of complex scenes: A comparison to MVS

    by Frederik Schulte, Perpetual Akwensi, Lukas Winiwarter

    High-resolution 3D documentation of cultural heritage sites is essential for their preservation. While terrestrial laser scanning (TLS) remains the gold standard, it is often cost-intensive compared to photogrammetry. This study evaluates three image-based reconstruction techniques, Multi-View Stereo (MVS), Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS), by applying them to a complex scene featuring a chapel and its surrounding vegetation, sensed from an uncrewed aerial vehicle (UAV). A hybrid TLS/MVS model provides a high-accuracy reference. Using identical interior and exterior camera parameters of the 105 UAV-acquired images, we generate dense point clouds with all methods and assess geometric accuracy and completeness using the M3C2 algorithm. Results show that MVS achieves superior accuracy (standard deviation of all M3C2 distances: MVS = 0.11 m, NeRF = 0.15 m), whereas NeRF attains up to 20% higher completeness, particularly in low-texture and vegetation-occluded regions. The 3DGS point cloud was deemed too sparse and was therefore not used for further analysis. The study highlights the potential of NeRFs to recover partially occluded or sparsely textured geometries that are challenging for MVS and suggests a complementary use of both approaches for cost-efficient documentation of cultural heritage.

  • Open Access

    Investigating the Potential of SfM, MVS, and Monocular Depth Estimation for Water Surface Reconstruction

    by Anatol Günthner, Markus Brezovsky, Frederik Schulte, Lukas Winiwarter, Gottfried Mandlburger, Boris Jutzi

    Reconstructing the water surface in refractive domains such as rivers and lakes is challenging, since light bending at the air-water interface alters the apparent geometry and breaks the straight-ray assumption of conventional image-based 3D reconstruction. Accurate water surface models are therefore a key prerequisite for many refraction-aware applications. This contribution investigates the potential of three passive image-based methods, Structure from Motion (SfM), Multi-View Stereo (MVS), and Monocular Depth Estimation (MDE), to derive a geometrically consistent water surface model from UAV imagery of the Pielach River study site in Austria. The dataset represents a demanding scenario with clear, fast-flowing water and low texture, which causes strong refraction and poor feature stability. Quantitative comparisons against LiDAR-derived reference surfaces show that SfM yields sparse and inconsistent points, MVS reconstructs the riverbed instead of the water surface, and MDE exhibits scale and offset inconsistencies despite explicit calibration using SfM reprojections. Completeness remains below 45% for all methods with mean vertical deviations in the decimetre-to-metre range. The results indicate that current image-based approaches are insufficient for reliable water-surface reconstruction in such settings, reinforcing the need for an explicitly derived surface model as input to refraction-aware modeling, for example in bathymetric reconstruction and future refractive neural rendering methods, rather than relying on implicitly learned water surfaces.

  • Open Access

    CENS: A Coverage-Efficient Pixel Sampling Strategy for Enhancing NeRF-Generated Point Cloud Fidelity

    by Perpetual Hope Akwensi, Frederik Schulte, Lukas Winiwarter

    Many geospatial workflows critically depend on high-fidelity 3D point clouds for applications such as change detection, orthophoto generation, and modeling. However, NeRF-generated point clouds often suffer from sampling inefficiencies inherent in the predominant random pixel sampling approach. We identify spatial redundancy as one such inefficiency: random sampling has the inevitable consequence of sampling large, low-texture patches more frequently than detailed, high-frequency textured regions. As a result, low-texture areas tend to be oversampled and other pixels remain unsampled – regardless of their importance to the reconstruction task. To overcome this, we propose CENS (Coverage-Efficient Non-Redundant Sampling), a deterministic pixel sampling strategy that maximizes spatial coverage, eliminates intra-image sample repetition, and ensures reproducibility via structured initialization. Evaluated on the Jamtal valley dataset, CENS achieves comparable geometric accuracy (cloud-to-mesh (C2M) distances: μ = - 0.0027 vs. -0.0011 m; σ = 0.027 vs. 0.028 m) using 50% fewer training steps (11,232 vs. 22,464), while yielding 28.2% more points, higher orthophoto fidelity, and improved point cloud completeness. Beyond CENS, we also explored NeRFs for ALS point cloud simulation, achieving realistic occlusion patterns and accuracy within UAV photogrammetry standards (VRMSE = 24 mm; HRMSE = 17 mm). Crucially, CENS positions NeRFs as a scalable, practical solution for geospatial point cloud and orthophoto generation, advancing them toward real-world mapping workflows, and integrates seamlessly into NeRFStudio.

  • Open Access

    Enhancing Multi-Temporal 3D Reconstruction of River Corridor Dynamics with Deterministic NeRF Sampling Strategies

    by Perpetual Akwensi, Frederik Schulte, Lukas Winiwarter

    Effective monitoring of hydro-geomorphological processes such as sediment displacement and channel migration using UAV-captured RGB images requires accurate, temporally consistent 3D reconstructions that enable the estimation of height/volume changes across multiple acquisitions epochs, despite variations in imaging conditions, flight paths, and camera geometries. Neural Radiance Fields (NeRF) offer a powerful framework for reconstructing complex fluvial environments from multi-view imagery. However, standard NeRF training relies on equal‑probability random pixel sampling, a strategy that introduces stochasticity into the reconstruction process and undermines the temporal repeatability required for change detection. When separate NeRFs are trained for different epochs the random sampling of pixels – combined with differing camera poses – leads to inconsistent ray distributions and surface sampling, and reduced comparability of resulting reconstructions. These effects are particularly detrimental in dynamic river corridors where low-texture surfaces, water reflections and surface motions already limit reconstruction coverage and stability.We propose Coverage-Efficient Non-redundant Sampling (CENS) as a grid-based deterministic alternative to random pixel sampling in NeRF training, combined with a pose-consistent inference framework, to improve temporal reconstruction repeatability for hydro-geomorphic change analysis. Instead of randomly sampling pixels per iteration, we impose a spatially deterministic sampling grid that ensures intra-epoch spatial coverage and consistency. To address the challenge of differing camera poses between epochs, we introduce a cross‑epoch evaluation strategy in which all epochs are queried using a shared set of reference camera poses – either drawn from one epoch’s camera set or defined as a synthetic virtual camera lattice – after alignment to a common world coordinate frame. This enables pose‑consistent rendering across time even when the original acquisition geometries differ.Rendered depth maps from these shared viewpoints are then projected onto a fixed world-space grid, enabling cell-wise comparison of height and volume change. This two-layer determinism—fixed sampling during training and fixed camera/grid sampling during inference—decouples temporal analysis from the stochastic and pose‑dependent variability inherent in standard NeRF pipelines.We will evaluate the method on multi‑epoch UAV imagery of an active river reach, comparing reconstructions trained with traditional random pixel sampling against those produced using the proposed CENS approach. With improved intra-epoch spatial coverage and geometric stability, combined with pose-consistent inference, we anticipate that the proposed approach will yield more coherent inter-epoch estimates of sediment elevation, channel-bed change and/or bank erosion, with lower uncertainty in low-textured or reflective regions. We expect corresponding 3D points from different epochs to align more consistently in world space, enabling more reliable detection of subtle geomorphic adjustments like bar migration, scour-fill cycles, and/or sediment redistribution.This study aims to demonstrate that sampling strategy and inference geometry are critical, yet previously overlooked, determinants of temporal repeatability in NeRF-based hydro-geomorphological monitoring. By replacing stochastic pixel sampling with deterministic grids and enforcing shared inference poses across epochs, we introduce a simple but potentially powerful modification that may enhance the reliability of NeRF-derived height/volume change estimates in dynamic river environments. The approach could open new possibilities for long‑term environmental and hydro-geomorphological research where spatiotemporal consistency is essential.

  • Top Cited Papers
    Open Access

    Multispectral airborne laser scanning for tree species classification: A benchmark of machine learning and deep learning algorithms

    by Josef Taher, Eric Hyyppä, Matti Hyyppä, Klaara Salolahti, Xiaowei Yu, Leena Matikainen, Antero Kukko, Matti Lehtomäki, Harri Kaartinen, Sopitta Thurachen, et al.


  • Light detection and ranging of natural systems

    by Liam A. K. Irwin, Nicholas C. Coops, Katharina Anders, Gottfried Mandlburger, Lukas Winiwarter


  • Open Access

    The Global Canopy Atlas: analysis-ready maps of 3D structure for the world’s woody ecosystems

    by Fabian Jörg Fischer, Becky Morgan, Toby Jackson, Jérôme Chave, David Coomes, Kc Cushman, Ricardo Dalagnol, Michele Dalponte, Laura Duncanson, Sassan Saatchi, et al.

    Woody canopies regulate exchanges of energy, water and carbon, and their three-dimensional (3D) structure supports much of terrestrial biodiversity. Remote sensing technologies such as airborne laser scanning (ALS) now enable the 3D mapping of entire landscapes. However, we lack the large, harmonized and geographically representative ALS collections needed to build a global picture of woody ecosystem structure. To address this challenge, we developed the Global Canopy Atlas (GCA): 3,458 ALS acquisitions transformed into standardized and analysis-ready maps of canopy height and elevation at 1 m 2 resolution. The GCA covers 56,554 km 2 across all major biomes. 19% of this area has been scanned multiple times, and 87% of all GCA products are openly available, covering 95% of the total area. To showcase its wide range of applications, we applied the GCA in three case studies. First, we validated three global satellite-derived canopy height maps, finding poor performance at native resolution (1-30 m, R 2 < 0.38) and moderate performance at 250 m resolution (R 2 < 0.65). Second, analyzing global patterns in canopy gap size frequency we discovered an unexpectedly large variation of power law exponents from branch to stand level (α = 1.52 to 2.38), pointing to a fundamental scale-dependence of forest structure. Third, we developed a framework to standardize forest turnover quantification from multi-source, multi-temporal ALS. In a temperate forest in North America it revealed that 21% of canopy gaps closed within 12 years of opening and would thus be missed by infrequent monitoring. As demonstrated by these case studies, the GCA provides a novel data source for ecologists, foresters, remote sensing scientists and the ecosystem modelling community that substantially advances our ability to understand the structure and dynamics of woody ecosystems at global scales.