10 papers
Geometric Foundation Model Distillation for Efficient Lunar 3D Reconstruction
Clémentine Grethen, Florient Chouteau, Géraldine Morin +1
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 cri…
EvoGS: Constructing Continuous-Layered Gaussian Splatting with Evolution Tree for Scalable 3D Streaming
Yuang Shi, Simone Gasparini, Géraldine Morin +1
Streaming 3D Gaussian Splatting requires highly scalable, progressive representations. Existing progressive methods rely on \textit{discrete layering}, accumulating separate splat…
MoonAnything: A Vision Benchmark with Large-Scale Lunar Supervised Data
Clémentine Grethen, Yuang Shi, Simone Gasparini +1
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 dat…
Lunar-G2R: Geometry-to-Reflectance Learning for High-Fidelity Lunar BRDF Estimation
Clementine Grethen, Nicolas Menga, Roland Brochard +4
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 renderi…
Sketch&Patch++: Efficient Structure-Aware 3D Gaussian Representation
Yuang Shi, Géraldine Morin, Simone Gasparini +1
We observe that Gaussians exhibit distinct roles and characteristics analogous to traditional artistic techniques -- like how artists first sketch outlines before filling in broade…
Adapting Stereo Vision From Objects To 3D Lunar Surface Reconstruction with the StereoLunar Dataset
Clementine Grethen, Simone Gasparini, Geraldine Morin +3
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 l…