SwiftGS: Episodic Priors for Immediate Satellite Surface Recovery

Rong Fu; Jiekai Wu; Xiaowen Ma; Shiyin Lin; Kangan Qian; Chuang Liu; Simon James Fong

cs.CVMar 19, 2026

SwiftGS: Episodic Priors for Immediate Satellite Surface Recovery

Authors: Rong Fu, Jiekai Wu, Xiaowen Ma, Shiyin Lin, Kangan Qian, Chuang Liu, Simon James Fong

Organizations: Independent Researcher

Abstract

Rapid, large-scale 3D reconstruction from multi-date satellite imagery is vital for environmental monitoring, urban planning, and disaster response, yet remains difficult due to illumination changes, sensor heterogeneity, and the cost of per-scene optimization. We introduce SwiftGS, a meta-learned system that reconstructs 3D surfaces in a single forward pass by predicting geometry-radiation-decoupled Gaussian primitives together with a lightweight SDF, replacing expensive per-scene fitting with episodic training that captures transferable priors. The model couples a differentiable physics graph for projection, illumination, and sensor response with spatial gating that blends sparse Gaussian detail and global SDF structure, and incorporates semantic-geometric fusion, conditional lightweight task heads, and multi-view supervision from a frozen geometric teacher under an uncertainty-aware multi-task loss. At inference, SwiftGS operates zero-shot with optional compact calibration and achieves accurate DSM reconstruction and view-consistent rendering at significantly reduced computational cost, with ablations highlighting the benefits of the hybrid representation, physics-aware rendering, and episodic meta-training.

Figures & tables

Figure 1: Overview of the SwiftGS architecture for efficient, zero-shot satellite surface reconstruction. The pipeline begins with Multi-View Encoding , where per-view features and a global scene latent are extracted. A Hybrid Decoder produces a compact Gaussian set $\Gamma$ , an implicit SDF $S_{\psi}$ , and spatial gates that blend sparse and dense components. Lightweight Task-Specific Heads optionally refine geometry or appearance. A Differentiable Physics Graph renders elevation and albedo using camera geometry and illumination, supported by distilled geometric cues during training. An episodic meta-training scheme learns shared parameters $\Phi$ with a small per-scene calibration vector $\theta$ . At inference, SwiftGS runs zero-shot and outputs a DSM, consistent renderings, and a compact Gaussian memory for incremental reconstruction.

Method	Mask Type	JAX_004	JAX_068	JAX_214	JAX_260	JAX Avg	IARPA_001	IARPA_002	IARPA_003	IARPA Avg	Time (min)
EO-NeRF [ 11 ]	No Mask	1.37	1.05	1.61	1.37	1.35	1.43	1.79	1.31	1.51	900
SAT-NGP [ 18 ]	No Mask	1.63	1.27	2.18	1.79	1.72	1.54	2.11	1.69	1.78	25
Sat-Mesh [ 48 ]	No Mask	1.55	1.15	2.02	1.36	1.52	1.40	2.20	1.30	1.60	8
S2P [ 49 ]	No Mask	1.45	1.19	1.82	1.66	1.53	1.48	2.48	1.38	1.78	20
EOGS [ 14 ]	No Mask	1.45	1.10	1.73	1.55	1.46	1.58	2.00	1.27	1.62	3
s2p-hd [ 50 ]	No Mask	2.00	2.20	2.10	2.00	2.08	1.80	1.90	1.80	1.83	90

Table 1: Comprehensive evaluation of elevation reconstruction accuracy (DSM MAE in meters) across different masking strategies and geographical regions. SwiftGS demonstrates superior performance in both full-scene and foliage-masked evaluations after adding new methods.

Method	DFC19 Dataset [ 46 ]				MVS3D Dataset [ 47 ]
	MAE (m)	RMSE (m)	PAG2.5 (%)	PAG7.5 (%)	MAE (m)	RMSE (m)	PAG2.5 (%)	PAG7.5 (%)
pixelSplat [ 51 ]	176.03	189.26	0.02	0.07	29.15	38.41	6.18	18.36
MVSplat [ 52 ]	19.82	22.96	2.71	16.11	16.05	20.20	9.99	29.54
TranSplat [ 53 ]	21.96	24.94	1.86	11.40	15.81	19.01	9.44	27.85
DepthSplat [ 54 ]	24.21	26.76	0.89	6.33	15.81	19.01	9.44	27.85
HiSplat [ 55 ]	13.18	16.59	15.06	37.08	15.63	19.37	9.96	29.34

Table 2: Quantitative comparison of generalizable methods on DFC19 and MVS3D, including SwiftGS. Lower MAE and RMSE are better. Higher PAG values are better.

Table 3: Ablation studies merged: (A)

\theta

subset ablation, and (B) component & loss ablations.

Table 4: Merged ablations: (A) MVS teacher supervision strength, and (B) meta-learning hyperparameter sensitivity.

Table 5: Ablation studies (three related sub-experiments shown as subtables).

Configuration	Iterations $T$	Resid Feedback	Attention Type	DSM MAE (m)	Time (s)	Converged Episodes
No Fusion	0	No	–	1.85	1.8	8000
Single-step Fusion	1	No	Spatial	1.45	2.1	6500
	1	No	Cross-Attention	1.48	2.2	6800
	1	No	Transformer	1.46	2.5	7200
Iterative Fusion	3	No	Spatial	1.35	2.4	5200
	3	No	Cross-Attention	1.37	2.5	5400

Table 6: Ablation study on bidirectional fusion mechanisms. We vary the number of fusion iterations

T

, Residual feedback (Resid), and attention mechanisms. Metrics: DSM MAE (m) and per-scene inference time (s).

Meta-training Domains	Urban Test	Mountain Test	Farmland Test	Desert Test	Unseen Mixed	Average
Only Urban	1.18	1.45	1.52	1.58	1.68	1.48
Only Mountain	1.35	1.27	1.48	1.55	1.72	1.47
Only Farmland	1.42	1.38	1.22	1.51	1.65	1.44
Only Desert	1.48	1.40	1.58	1.32	1.70	1.52
All (Default)	1.22	1.30	1.25	1.35	1.60	1.34

Table 7: Ablation study on meta-training diversity. DSM MAE (m) on test sets after meta-training on different domains.

Training Region	North America	Europe	Asia	Mean
North America	1.22	1.28	1.31	1.27
Europe	1.29	1.25	1.33	1.29
Asia	1.34	1.30	1.24	1.29
Africa (unseen)	1.38	1.35	1.40	1.38

Table 8: Cross-domain DSM MAE (m). Rows indicate training region and columns indicate test region.

(A) Active View Selection (budgeted acquisition)
Selection Strategy	Budget Views	DSM MAE (m)	LPIPS	Info Gain	Time (s)	vs Random
Random selection	4	1.52	0.108	0.45	1.8	-
Sequential selection	4	1.48	0.106	0.52	1.8	+2.6%
Active selection (Ours)	4	1.29	0.105	0.81	2.1	+15.1%
Random selection	8	1.29	0.105	0.48	3.2	-
Sequential selection	8	1.26	0.104	0.55	3.2	+2.3%

Table 9: (A) Active view selection performance (budgets = number of selected views). (B) Continual learning evaluation after sequential training over three regions.

View Count	2 views	4 views	8 views	16+ views
EO-NeRF [ 11 ]	2.84	1.92	1.45	1.35
EOGS [ 14 ]	2.15	1.68	1.46	1.41
SwiftGS	1.89	1.52	1.29	1.22

Table 10: Sensitivity to input view count

N

. Lower DSM MAE indicates better robustness under sparse observations.

Figure 2: Shadow and lighting consistency: input, predicted shadow, rendered image, albedo, and ground truth.

Figure 3: Training curves showing stable convergence of query loss, DSM error, and shadow loss.

Figure 4: Qualitative comparison across scenes. Each row shows input images, predicted DSM and renderings from SwiftGS and EO-NeRF, along with ground truth. MAE and LPIPS errors are annotated.

Appendix figures & tables7 assets

Supplementary material from the paper’s appendix.

Appendix

Configuration	$\lambda_{\mathrm{lpips}}$	$\lambda_{\mathrm{reproj}}$	$\lambda_{\mathrm{DSM}}$	$\lambda_{\mathrm{distill}}$	$\lambda_{\mathrm{sdf}}$	$\lambda_{\mathrm{load}}$	$\lambda_{\mathrm{z}}$	$\lambda_{\mathrm{sparse}}$	MAE (m)
Default	0.1	1.0	2.0	1.0	0.5	0.01	0.001	0.1	1.22
$\lambda_{\mathrm{lpips}}\times 1.5$	0.15	1.0	2.0	1.0	0.5	0.01	0.001	0.1	1.24
$\lambda_{\mathrm{lpips}}\times 0.5$	0.05	1.0	2.0	1.0	0.5	0.01	0.001	0.1	1.25
$\lambda_{\mathrm{reproj}}\times 1.5$	0.1	1.5	2.0	1.0	0.5	0.01	0.001	0.1	1.21
$\lambda_{\mathrm{reproj}}\times 0.5$	0.1	0.5	2.0	1.0	0.5	0.01	0.001	0.1	1.28
$\lambda_{\mathrm{DSM}}\times 1.5$	0.1	1.0	3.0	1.0	0.5	0.01	0.001	0.1	1.20

Appendix

Table 11: Sensitivity analysis of loss coefficients. Reported DSM MAE (m) on validation set with perturbed coefficients.

Test Sensor	Native Resolution (m)	DSM MAE (m)	Relative Degradation
WorldView-3 (training)	0.31	1.22	–
WorldView-2	0.46	1.32	+8.2%
GeoEye-1	0.41	1.37	+12.3%

Appendix

Table 12: Cross-sensor generalization performance. Models trained on WorldView-3, tested on alternative sensors.

RPC Noise Level $\sigma$ (%)	0	2	5	10	20	50
SwiftGS (with calibration)	1.22	1.24	1.28	1.35	1.52	2.41
SwiftGS (zero-shot, no calib)	1.36	1.38	1.42	1.51	1.78	3.12
EO-NeRF (per-scene opt)	1.35	1.36	1.38	1.45	1.89	3.85

Appendix

Table 13: Robustness to RPC metadata noise. DSM MAE (m) with increasing RPC coefficient perturbation.

Processing Stage	Time (seconds)
Multi-view feature extraction	98.4
Scene latent computation	12.3
Hybrid decoder forward pass	24.7
Gaussian primitive generation	8.2
SDF query and gating evaluation	15.6
Physics-based rendering (all views)	31.8

Appendix

Table 14: Per-scene inference latency breakdown for 256m

\times

256m region.

Figure 5: Representative failure cases of SwiftGS. Top row: dense high-rise urban canyon exhibiting height hallucination due to severe occlusion. Middle row: water body with systematic elevation overestimation caused by specular reflection violating diffuse reflectance assumptions. Bottom row: extreme shadow coverage ( $>$ 60%) showing incomplete shadow removal and associated height artifacts. For each case, columns show input image, predicted DSM, error map (red indicates overestimation, blue underestimation), and ground truth DSM.

Scene Characteristic	Prevalence (%)	MAE (m)	Normalized Error	Primary Cause
Standard conditions	67.3	1.18	1.00	–
Dense high-rise urban	8.4	2.34	1.98	Severe occlusion, height ambiguity
Water bodies	6.2	2.89	2.45	Specular reflection, textureless surfaces
Extreme shadow ( $>$ 60% cover)	5.7	2.12	1.80	Illumination prior mismatch
Cloud contamination	4.8	2.56	2.17	Transient unmodeled occlusion
Steep terrain ( $>$ 45° slope)	4.1	2.03	1.72	Foreshortening, geometric distortion

Appendix

Table 15: Performance stratification by challenging scene characteristics.

Figure 6: Qualitative reconstruction comparison across four distinct scene types. Row 1 (Urban): Dense high-rise district with complex occlusion patterns and vertical structures. SwiftGS preserves sharp building boundaries and accurate roof elevations where EO-NeRF exhibits smoothing artifacts. Row 2 (Mountain): Rugged terrain with steep ridges and valleys. The hybrid representation captures fine topographic detail while maintaining global surface continuity. Row 3 (Farmland): Agricultural region with subtle elevation variations and regular field patterns. Decoupled geometry-radiance modeling accurately recovers micro-topography despite homogeneous texture. Row 4 (Coastal): Shoreline interface with sand dunes, vegetation, and water boundaries. Physics-aware rendering maintains geometric fidelity at land-water transitions. For each scene, columns display: input satellite image, SwiftGS predicted DSM, EO-NeRF predicted DSM, and LiDAR ground truth. Elevation color scheme ranges from blue (low) through green to red (high). Annotated MAE values demonstrate consistent advantages across all terrain categories.

Explore similar work

Jul 13, 2026

SalientGS: Unified SfM-to-3DGS with Importance-Guided MCMC Gaussian Allocation

Reconstructing 3D scenes from unordered images remains bottlenecked by expensive Structure-from-Motion (SfM) preprocessing and frozen pose interfaces. We present SalientGS, a unified SfM-to-3D Gaussian Splatting (3DGS) pipeline. Its central contribution is importance-guided Markov Chain Monte Carlo (MCMC) Gaussian allocation, which aggregates multi-view residuals into per-Gaussian underfit and redundancy signals. These signals define a smooth importance-weighted sampling distribution that biases both birth and relocation toward underfit regions. This reallocates capacity from well-fit areas without altering the underlying stochastic gradient Langevin dynamics (SGLD). SalientGS achieves end-to-end reconstruction in 15 minutes with state-of-the-art perceptual quality. The supplementary material provides dedicated sections for Per-Scene Qualitative Comparisons and Per-Image Learned Perceptual Image Patch Similarity (LPIPS) Analysis, including failure cases. Code and evaluation scripts are available at https://github.com/Six-Bit-TX/SalientGS.

Tianyu Xiong, Rui Li, Suning Ge +1

School of Computer Science, Northwestern Polytechnical University, Xi’an, China · CEMSE, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia

3D Gaussian Splatting Adaptive Gaussian Densification Multi-View 3D Reconstruction

Ask PDF

May 8, 2026

SatSurfGS: Generalizable 2D Gaussian Splatting for Sparse-View Satellite Surface Reconstruction

Sparse-view satellite image surface reconstruction remains highly challenging, fundamentally because the reliability of multi-view matching under satellite imaging conditions is strongly spatially heterogeneous. Affected by large photometric differences, weak textures, and repetitive textures, multi-view geometric constraints are often sparse, unevenly distributed, and locally unreliable. Although 2D Gaussian Splatting (2DGS) is more suitable than 3D Gaussian Splatting (3DGS) for the explicit representation of continuous surfaces, research on generalizable feed-forward 2DGS frameworks for sparse-view satellite surface reconstruction is still lacking. To address this issue, we propose SatSurfGS, a generalizable sparse-view surface reconstruction method for satellite imagery based on 2DGS. The proposed method builds a coarse-to-fine Gaussian attribute prediction framework and explicitly models local geometric reliability at three levels: feature learning, Gaussian parameter estimation, and training optimization. Specifically, we propose a confidence-aware monocular multi-view feature fusion module to adaptively integrate monocular priors and multi-view matching features according to local confidence; a cross-stage self-consistency residual guidance module to stabilize stage-wise Gaussian parameter refinement using the residual between the rendered height map from the previous stage and the current-stage MVS height map, together with confidence information; and a confidence bidirectional routing loss to achieve differentiated allocation of geometric and appearance supervision. Experiments on satellite datasets show that the proposed method achieves improved rendering quality, surface reconstruction accuracy, cross-dataset generalization, and inference efficiency compared with representative generalizable baselines and competitive per-scene optimization methods.

Min Chen, Wei Guo, Bin Wang +9

Faculty of Geosciences and Engineering, Southwest Jiaotong University, Chengdu, P.R. China · School of Geography and Environment, Jiangxi Normal University · College of Geodesy and Geomatics, Shandong University of Science and Technology

Remote Sensing Image Understanding Multi-View Learning Sparse-View 3D Reconstruction Feed-Forward 3D Reconstruction

Ask PDF

Aug 11, 2026

Gaussian Sculpting: End-to-End Controllable Surface Reconstruction via Field Optimization

3D Gaussian Splatting (3DGS) has recently enabled real-time novel view synthesis with impressive quality. However, it struggles to recover accurate surfaces under limited viewpoints and due to the inherent irregularity of Gaussian primitives. The resulting geometric errors are notoriously difficult to correct manually. To address these issues, we propose Gaussian Sculpting, a fully differentiable end-to-end framework for high-quality surface reconstruction. Our key insight is to anchor Gaussians onto an evolving differentiable surface, allowing them to guide signed distance field (SDF) optimization instead of extracting the surface only during post-processing. To enable stable gradient isolation during joint optimization, we design a bi-level training strategy in which the outer loop optimizes the geometry represented by the SDF, while the inner loop updates the Gaussians with the geometry fixed. We further impose constraints on Gaussian parameters to ensure consistency with the underlying surface, thereby improving both geometric and appearance fidelity during optimization. In addition, we introduce a multi-resolution subdivision scheme based on octree-like partitioning to preserve fine details while reducing memory consumption. Experiments on object-level scenes demonstrate that our method effectively removes redundant surfaces, recovers missing structures caused by limited viewpoints, and achieves strong reconstruction quality even at relatively low resolutions.

Ke Jiaxin, Juncheng Liu, Yi Wang +4

Dalian University of Technology, China · Massey University, New Zealand · Peking University, China +1

3D Gaussian Splatting 3D Reconstruction Sparse-View 3D Reconstruction

Ask PDF