arXiv subjects

Simone Gasparini

Publications and source records attributed to Simone Gasparini.

10 recordsLinked to original sources

arXiv2026

Geometric Foundation Model Distillation for Efficient Lunar 3D Reconstruction

Large 3D foundation models such as MASt3R achieve state-of-the-art stereo reconstruction but are computationally demanding for deployment under strict hardware constraints -- a critical limitation in domains such as planetary exploration, where onboard computing is severely restricted. We study how far such models can be compressed through knowledge distillation, using lunar stereo reconstruction as a challenging and practically relevant case study. Starting from a 688M-parameter MASt3R teacher fine-tuned on lunar imagery, we distill its dense geometric predictions into a family of lightweight students spanning different encoder types (CNN vs ViT), decoder widths and depths, and training strategies. To bridge the dimensional mismatch between teacher and student, we propose a structured SVD-based initialization that projects the teacher's decoder weights into the student's smaller latent space, yielding a warm start that significantly improves convergence and final performance. Based on our results on lunar data, we can obtain a distilled student that retains most of teacher's reconstruction accuracy while reducing the model size up to 7 times, and even outperforms a baseline trained directly with sparse ground-truth annotations. Beyond compression, our study highlights both principles and practical insights for distilling geometric foundation models: a convolutional encoder underperforms transformer-based alternatives (though pretraining availability remains a confounding factor), preserving encoder capacity is more critical than maintaining a large decoder, feature-level distillation consistently outperforms output-only supervision, and SVD-based initialization improves optimisation stability. These findings provide practical guidelines for deploying 3D reconstruction models in resource-constrained environments.

cs.CV↗

arXiv2026

EvoGS: Constructing Continuous-Layered Gaussian Splatting with Evolution Tree for Scalable 3D Streaming

Streaming 3D Gaussian Splatting requires highly scalable, progressive representations. Existing progressive methods rely on \textit{discrete layering}, accumulating separate splat sets for each level of detail. This structural independence between layers inherently leads to error accumulation, severe splat redundancy, and uncontrolled quality transitions. We propose EvoGS, the first \textit{continuous-layering} representation. Organized as an Evolution Tree, EvoGS generates finer details via an explicit, wavelet-inspired parent-child refinement. This empowers child nodes to structurally correct ancestral errors, yield inherently sparse and highly compressible inter-layer signals. Extensive experiments show EvoGS eliminates splat redundancy from over 65\% to under 25\%. Compared to state-of-the-art baselines, it reduces transmission payload and GPU VRAM footprint by up to 2.4$\times$ and 5.5$\times$, respectively, and achieves smooth quality transitions optimal for real-time adaptive streaming. Project page: https://yuang-ian.github.io/evogs/

cs.CV↗

arXiv2026

MoonAnything: A Vision Benchmark with Large-Scale Lunar Supervised Data

Accurate perception of lunar surfaces is critical for modern lunar exploration missions. However, developing robust learning-based perception systems is hindered by the lack of datasets that provide both geometric and photometric supervision. Existing lunar datasets typically lack either geometric ground truth, photometric realism, illumination diversity, or large-scale coverage. In this paper, we introduce MoonAnything, a unified benchmark built on real lunar topography with physically-based rendering, providing the first comprehensive geometric and photometric supervision under diverse illumination with large scale. The benchmark comprises two complementary sub-datasets : i) LunarGeo provides stereo images with corresponding dense depth maps and camera calibration enabling 3D reconstruction and pose estimation; ii) LunarPhoto provides photorealistic images using a spatially-varying BRDF model, along with multi-illumination renderings under real solar configurations, enabling reflectance estimation and illumination-robust perception. Together, these datasets offer over 130K samples with comprehensive supervision. Beyond lunar applications, MoonAnything offers a unique setting and challenging testbed for algorithms under low-textured, high-contrast conditions and applies to other airless celestial bodies and could generalize beyond. We establish baselines using state-of-the-art methods and release the complete dataset along with generation tools to support community extension: https://github.com/clementinegrethen/MoonAnything.

cs.CV↗

arXiv2026

Lunar-G2R: Geometry-to-Reflectance Learning for High-Fidelity Lunar BRDF Estimation

We address the problem of estimating realistic, spatially varying reflectance for complex planetary surfaces such as the lunar regolith, which is critical for high-fidelity rendering and vision-based navigation. Existing lunar rendering pipelines rely on simplified or spatially uniform BRDF models whose parameters are difficult to estimate and fail to capture local reflectance variations, limiting photometric realism. We propose Lunar-G2R, a geometry-to-reflectance learning framework that predicts spatially varying BRDF parameters directly from a lunar digital elevation model (DEM), without requiring multi-view imagery, controlled illumination, or dedicated reflectance-capture hardware at inference time. The method leverages a U-Net trained with differentiable rendering to minimize photometric discrepancies between real orbital images and physically based renderings under known viewing and illumination geometry. Experiments on a geographically held-out region of the Tycho crater show that our approach reduces photometric error by 38 % compared to a state-of-the-art baseline, while achieving higher PSNR and SSIM and improved perceptual similarity, capturing fine-scale reflectance variations absent from spatially uniform models. To our knowledge, this is the first method to infer a spatially varying reflectance model directly from terrain geometry.

cs.CV↗

arXiv2026

Sketch&Patch++: Efficient Structure-Aware 3D Gaussian Representation

We observe that Gaussians exhibit distinct roles and characteristics analogous to traditional artistic techniques -- like how artists first sketch outlines before filling in broader areas with color, some Gaussians capture high-frequency features such as edges and contours, while others represent broader, smoother regions analogous to brush strokes that add volume and depth. Based on this observation, we propose a hybrid representation that categorizes Gaussians into (i) Sketch Gaussians, which represent high-frequency, boundary-defining features, and (ii) Patch Gaussians, which cover low-frequency, smooth regions. This semantic separation naturally enables layered progressive streaming, where the compact Sketch Gaussians establish the structural skeleton before Patch Gaussians incrementally refine volumetric detail. In this work, we extend our previous method to arbitrary 3D scenes by proposing a novel hierarchical adaptive categorization framework that operates directly on the 3DGS representation. Our approach employs multi-criteria density-based clustering, combined with adaptive quality-driven refinement. This method eliminates dependency on external 3D line primitives while ensuring optimal parametric encoding effectiveness. Our comprehensive evaluation across diverse scenes, including both man-made and natural environments, demonstrates that our method achieves up to 1.74 dB improvement in PSNR, 6.7% in SSIM, and 41.4% in LPIPS at equivalent model sizes compared to uniform pruning baselines. For indoor scenes, our method can maintain visual quality with only 0.5\% of the original model size. This structure-aware representation enables efficient storage, adaptive streaming, and rendering of high-fidelity 3D content across bandwidth-constrained networks and resource-limited devices.

cs.CV↗

arXiv2025

Adapting Stereo Vision From Objects To 3D Lunar Surface Reconstruction with the StereoLunar Dataset

Accurate 3D reconstruction of lunar surfaces is essential for space exploration. However, existing stereo vision reconstruction methods struggle in this context due to the Moon's lack of texture, difficult lighting variations, and atypical orbital trajectories. State-of-the-art deep learning models, trained on human-scale datasets, have rarely been tested on planetary imagery and cannot be transferred directly to lunar conditions. To address this issue, we introduce LunarStereo, the first open dataset of photorealistic stereo image pairs of the Moon, simulated using ray tracing based on high-resolution topography and reflectance models. It covers diverse altitudes, lighting conditions, and viewing angles around the lunar South Pole, offering physically grounded supervision for 3D reconstruction tasks. Based on this dataset, we adapt the MASt3R model to the lunar domain through fine-tuning on LunarStereo. We validate our approach through extensive qualitative and quantitative experiments on both synthetic and real lunar data, evaluating 3D surface reconstruction and relative pose estimation. Extensive experiments on synthetic and real lunar data validate the approach, demonstrating significant improvements over zero-shot baselines and paving the way for robust cross-scale generalization in extraterrestrial environments.

cs.CV↗

arXiv2025

ROI-GS: Interest-based Local Quality 3D Gaussian Splatting

We tackle the challenge of efficiently reconstructing 3D scenes with high detail on objects of interest. Existing 3D Gaussian Splatting (3DGS) methods allocate resources uniformly across the scene, limiting fine detail to Regions Of Interest (ROIs) and leading to inflated model size. We propose ROI-GS, an object-aware framework that enhances local details through object-guided camera selection, targeted Object training, and seamless integration of high-fidelity object of interest reconstructions into the global scene. Our method prioritizes higher resolution details on chosen objects while maintaining real-time performance. Experiments show that ROI-GS significantly improves local quality (up to 2.96 dB PSNR), while reducing overall model size by $\approx 17\%$ of baseline and achieving faster training for a scene with a single object of interest, outperforming existing methods.

cs.GR↗

arXiv2025

ROI-NeRFs: Hi-Fi Visualization of Objects of Interest within a Scene by NeRFs Composition

Efficient and accurate 3D reconstruction is essential for applications in cultural heritage. This study addresses the challenge of visualizing objects within large-scale scenes at a high level of detail (LOD) using Neural Radiance Fields (NeRFs). The aim is to improve the visual fidelity of chosen objects while maintaining the efficiency of the computations by focusing on details only for relevant content. The proposed ROI-NeRFs framework divides the scene into a Scene NeRF, which represents the overall scene at moderate detail, and multiple ROI NeRFs that focus on user-defined objects of interest. An object-focused camera selection module automatically groups relevant cameras for each NeRF training during the decomposition phase. In the composition phase, a Ray-level Compositional Rendering technique combines information from the Scene NeRF and ROI NeRFs, allowing simultaneous multi-object rendering composition. Quantitative and qualitative experiments conducted on two real-world datasets, including one on a complex eighteen's century cultural heritage room, demonstrate superior performance compared to baseline methods, improving LOD for object regions, minimizing artifacts, and without significantly increasing inference time.

cs.CV↗

arXiv2024

A Note on Geometric Calibration of Multiple Cameras and Projectors

Geometric calibration of cameras and projectors is an essential step that must be performed before any imaging system can be used. There are many well-known geometric calibration methods for calibrating systems comprised of multiple cameras, but simultaneous geometric calibration of multiple projectors and cameras has received less attention. This leaves unresolved several practical issues which must be considered to achieve the simplicity of use required for real world applications. In this work we discuss several important components of a real-world geometric calibration procedure used in our laboratory to calibrate surface imaging systems comprised of many projectors and cameras. We specifically discuss the design of the calibration object and the image processing pipeline used to analyze it in the acquired images. We also provide quantitative calibration results in the form of reprojection errors and compare them to the classic approaches such as Zhang's calibration method.

cs.CV↗

arXiv2024

LapisGS: Layered Progressive 3D Gaussian Splatting for Adaptive Streaming

The rise of Extended Reality (XR) requires efficient streaming of 3D online worlds, challenging current 3DGS representations to adapt to bandwidth-constrained environments. This paper proposes LapisGS, a layered 3DGS that supports adaptive streaming and progressive rendering. Our method constructs a layered structure for cumulative representation, incorporates dynamic opacity optimization to maintain visual fidelity, and utilizes occupancy maps to efficiently manage Gaussian splats. This proposed model offers a progressive representation supporting a continuous rendering quality adapted for bandwidth-aware streaming. Extensive experiments validate the effectiveness of our approach in balancing visual fidelity with the compactness of the model, with up to 50.71% improvement in SSIM, 286.53% improvement in LPIPS with 23% of the original model size, and shows its potential for bandwidth-adapted 3D streaming and rendering applications.

cs.CV↗