A Reproducible Reconstruction and Evaluation Framework for Photorealistic Lunar Analog Scene Reconstruction Toward Digital Twins

Antar Mazumder; Ryan Hartzell; Luke Boyd; Alexander Robinson; Neha Sharma; Chance Carnival; Frances Zhu

cs.ROOct 31, 2026

A Reproducible Reconstruction and Evaluation Framework for Photorealistic Lunar Analog Scene Reconstruction Toward Digital Twins

Authors: Antar Mazumder, Ryan Hartzell, Luke Boyd, Alexander Robinson, Neha Sharma, Chance Carnival, Frances Zhu

Organizations: Dept. of Mechanical Engineering, Colorado School of Mines, Golden, CO, USA · Dept. of Eletrical Engineering, Colorado School of Mines, Golden, CO, USA

Abstract

In this paper, we present a reconstruction pipeline that empirically quantifies the photorealistic scene reconstruction accuracy from both human-controlled and rover mast camera monocular feeds against physical ground truth as a function of Lunar traversal effects (e.g., motion blur, haze due to lofted regolith, trajectory bias, and sparse views). First, we benchmark six variants of 3D Gaussian Splatting (3DGS) across three Lunar analog scenes on held-out test sets using standard photometric metrics. We then establish how under traversal effects, this test-set-specific Novel View Synthesis (NVS) performance does not proportionally scale to the same photometric metrics in the reconstructed DTs. Our results quantify that splat training metrics alone are insufficient predictors of Cross-Reconstruction Photorealistic NVS Fidelity (CRPNVS), and that factors such as rover trajectory bias and geometric scene coverage play a critical role in determining the photorealistic quality of the reconstructed scenes targeting Lunar analog Digital Twins. Additionally, we pilot study Coverage Score ( $S_c$ ), a geometry-based diagnostic derived from COLMAP poses and point cloud structure that provides a meaningful heuristic about the highest achievable CRPNVS structural fidelity, independently of splat training performance in the absence of a human-controlled reference. These findings establish a standardized, human control-referenced evaluation pipeline for photorealistic scene reconstruction for Lunar-analog Digital Twin development and future planetary exploration. Code and project page: https://rose-lab-admin.github.io/rose-lunar-dt-rec

Figures & tables

Fig. 1: Under traversal effects, high training metrics on held-out test images fail to guarantee similar level of novel view synthesis performance across the entire reconstructed testbed.

Fig. 2: End-to-end photorealistic scene reconstruction and evaluation pipeline from data collection to simulation-ready Lunar-analog DT asset generation for Isaac Sim 5. CRPNVS: Cross-Reconstruction Photorealistic Novel View Synthesis; $\mathbf{S_{c}}$ denotes Coverage Score.

Scene 1 500 imgs (Train: 437; Test: 63)
Method	$\mathrm{PSNR}_{Tr}\uparrow$	$\mathrm{SSIM}_{Tr}\uparrow$	$\mathrm{LPIPS}_{Tr}\downarrow$
3DGS	31.04 $\pm$ 2.51	0.88 $\pm$ .04	0.30 $\pm$ .05
BAGS	25.05 $\pm$ 2.41	0.72 $\pm$ .06	0.29 $\pm$ .04
GaussianPro (DA3)	30.15 $\pm$ 2.14	0.85 $\pm$ .03	0.37 $\pm$ .03
GaussianPro (rend.)	30.17 $\pm$ 2.14	0.85 $\pm$ .03	0.37 $\pm$ .03
Mip-Splatting	31.28 $\pm$ 2.49	0.89 $\pm$ .04	0.25 $\pm$ .05

TABLE I: Rover-derived splat training benchmark across three Lunar analog scenes. All models trained for 30,000 iterations at

819\times 463

pixels. Values reported as mean

\pm

std.

Fig. 3: A single alignment from the three-panel comparison used in CRPNVS assessment. $\mathcal{R}_{\mathrm{Rov}}$ splat shows visible floaters on top of the matched ground plane.

Scene 1 – Diffused Indoor Light CRPNVS: $3\times 900$ imgs $\times\,7$ elevation offsets
	$\mathrm{PSNR}\uparrow$		$\mathrm{SSIM}\uparrow$		$\mathrm{LPIPS}\downarrow$
Method	vs $\mathcal{R}_{\mathrm{Ctrl}}$	vs $\mathrm{GT}$	vs $\mathcal{R}_{\mathrm{Ctrl}}$	vs $\mathrm{GT}$	vs $\mathcal{R}_{\mathrm{Ctrl}}$	vs $\mathrm{GT}$
3DGS	12.48 $\pm$ 1.45	12.31 $\pm$ 1.42	0.52 $\pm$ .11	0.48 $\pm$ .10	0.59 $\pm$ .09	0.66 $\pm$ .09
BAGS	13.29 $\pm$ 1.18	13.11 $\pm$ 1.30	0.59 $\pm$ .06	0.54 $\pm$ .06	0.56 $\pm$ .10	0.64 $\pm$ .09
GaussianPro (DA3)	12.06 $\pm$ 1.45	11.96 $\pm$ 1.42	0.49 $\pm$ .09	0.45 $\pm$ .12	0.62 $\pm$ .06	0.71 $\pm$ .08
GaussianPro (rend.)	12.11 $\pm$ 2.00	11.95 $\pm$ 1.57	0.49 $\pm$ .09	0.45 $\pm$ .11	0.62 $\pm$ .06	0.71 $\pm$ .08

TABLE II:

\mathcal{R}_{\mathrm{Rov}}

CRPNVS benchmark with frame resolution

960\times 540

pixels. Values reported as mean

\pm

std.

Scene 1 900 imgs (Train: 787; Test: 113)
Method	$\mathrm{PSNR}_{Tr}\uparrow$	$\mathrm{SSIM}_{Tr}\uparrow$	$\mathrm{LPIPS}_{Tr}\downarrow$
3DGS [ 13 ]	32.48 $\pm$ 3.57	0.92 $\pm$ 0.06	0.22 $\pm$ 0.09
BAGS [ 24 ]	31.35 $\pm$ 3.36	0.91 $\pm$ 0.06	0.23 $\pm$ 0.10
GaussianPro (DA3) [ 22 ]	31.67 $\pm$ 3.30	0.91 $\pm$ 0.06	0.23 $\pm$ 0.09
GaussianPro (rend.) [ 22 ]	31.66 $\pm$ 3.26	0.91 $\pm$ 0.06	0.23 $\pm$ 0.09
Mip-Splatting [ 23 ]	32.56 $\pm$ 3.56	0.92 $\pm$ 0.06	0.20 $\pm$ 0.09

TABLE III: Splat Training and CRPNVS benchmark across three Lunar analog scenes (Human-Control) compared against physical ground truth. All models trained for 30,000 iterations at

{\sim}960\times 540

pixels. Values reported as mean

\pm

std.

Scene	Modality	Tag	$\#$ Markers	Error	Spread
1	$\mathcal{R}_{\mathrm{Ctrl},i}$	ArUco 4×4	5/6	$+0.58\%$	$2.85\%$
1	$\mathcal{R}_{\mathrm{Rov}}$	ArUco 4×4	3/6	$+0.42\%$	$23.33\%$
2	$\mathcal{R}_{\mathrm{Ctrl},i}$	ArUco 4×4	5/6	$-3.22\%$	$16.61\%$
2	$\mathcal{R}_{\mathrm{Rov}}$	ArUco 4×4	3/6	$+7.57\%$	$22.15\%$
3	$\mathcal{R}_{\mathrm{Ctrl},i}$	AprilTag 36h11	3/4	$-0.04\%$	$2.75\%$
3	$\mathcal{R}_{\mathrm{Rov}}$	AprilTag 36h11	1/4	$-0.18\%$	$14.38\%$

TABLE IV: COLMAP [ 1 ] scale accuracy from triangulated fiducial markers.

Fig. 4: Scene 3’s less linear rover camera traverse yields higher

W_{f}

and

W_{d}

than scene 2 despite harsher dust conditions, explaining its superior CRPNVS SSIM.

3D Reconstruction

3D reconstruction recovers a scene’s shape, appearance, and camera motion from images, video, depth, or other sensor measurements.

See all 992 papers

MoonGS: High-quality Representation of the Lunar Surface via Gaussian Splatting Using Robust Depth Features from Image Pairs
Oct 5, 2026Yun Jiang, Bo Zheng, Yingying Zhang +73D Gaussian Splatting 3D Reconstruction
Jilin University, Changchun, China · Shanghai Aerospace Control Technology Institute, Shanghai, China · Beijing Institute of Control Engineering, Beijing, China +2
Efficacy of Monocular Depth Estimation in Lunar Environments
Oct 27, 2026Michael W. Lanighan, Kenji Brameld, Seth GeeMonocular Depth Estimation 3D Reconstruction
TRACLabs Inc., 1331 Gemini Street; Houston, TX 77058.
Visual Relocalization from Sparse Views in Aliased and Low-Texture Environments via Novel View Synthesis
Jul 24, 2026Maria Peribañez, Javier Civera, Rudolph Triebel +13D Gaussian Splatting Camera Pose Estimation
University of Zaragoza, Spain · German Aerospace Center (DLR), Institute of Robotics and Mechatronics · Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany

Oct 5, 2026J/K move · Enter open · S save

MoonGS: High-quality Representation of the Lunar Surface via Gaussian Splatting Using Robust Depth Features from Image Pairs

Yun Jiang, Bo Zheng, Yingying Zhang, Xueming Xiao+6

Jilin University, Changchun, China · Shanghai Aerospace Control Technology Institute, Shanghai, China · Beijing Institute of Control Engineering, Beijing, China+2

3D Gaussian Splatting 3D Reconstruction Novel View Synthesis Sparse-View 3D Reconstruction Feed-Forward 3D Reconstruction

Open paper AskPDF arXiv

High-quality 3D reconstruction of lunar terrain from sparse rover images is indispensable for autonomous lunar exploration, but remains challenging because viewpoint overlap is insufficient, surface textures are weak, and data volume is limited. We propose MoonGS, the first feed-forward 3D Gaussian Splatting framework tailored to lunar scenes. Given only two input images, MoonGS predicts pixel-aligned Gaussian primitives in a single forward pass and renders photorealistic novel views without any per-scene optimization. MoonGS (i) adopts an adaptable backbone design that seamlessly integrates advanced vision foundation models to extract robust depth features; (ii) integrates semantic priors in two manners: merging semantic cues with visual features to refine Gaussian parameter estimation, and adopting a semantic ranking loss that regularizes background depth; and (iii) employs an entropy-guided heuristic resampling strategy to augment sparse observations by selecting the most informative distant viewpoints with negligible overhead. Experiments on the LuSNAR benchmark and our synthetic weak-texture MoonBlender dataset show that MoonGS surpasses state-of-the-art feed-forward NeRF/3DGS baselines by +4.9 dB PSNR, +0.29 SSIM, and 40% lower LPIPS while maintaining sub-second inference. Furthermore, we validate the broad applicability of our framework by demonstrating that it effectively leverages state-of-the-art backbones, including VGGT, to significantly boost performance. Qualitative evaluations on Chang'e mission imagery also show the best visual quality among compared methods, indicating robustness on real lunar data. The source code and dataset are publicly available at https://github.com/InRobots/MoonBlender.

Abstract

3D Reconstruction

Explore similar work

MoonGS: High-quality Representation of the Lunar Surface via Gaussian Splatting Using Robust Depth Features from Image Pairs

Efficacy of Monocular Depth Estimation in Lunar Environments

Visual Relocalization from Sparse Views in Aliased and Low-Texture Environments via Novel View Synthesis