AI Paper Atlas

Research map / 3D vision / 3D generation

Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery

Jie-Ying Lee, Yi-Ruei Liu, Shr-Ruei Tsai, Wei-Cheng Chang, Chung-Ho Wu, Jiewen Chan, Zhenjun Zhao, Chieh Hubert Lin, Yu-Lun Liu

ECCV 2026 · 3D vision › 3D generation · approach: Feed-forward 3D asset generation and editing · 28 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add appearance modeling to the reconstruction stage (ablation)Skyfall-GS reconstruction · JAX_068FID_CLIP: Failed -> 41.90Improved
add opacity regularization (ablation)Skyfall-GS reconstruction · JAX_068FID_CLIP: 41.90 -> 39.95Improved
add pseudo-camera depth supervision (ablation)Skyfall-GS reconstruction · JAX_068FID_CLIP: 39.95 -> 38.01Improved
add pseudo-camera depth supervision (ablation)Skyfall-GS reconstruction · JAX_068 (DFC2019 LiDAR DSM)MAE (m): 2.980 -> 2.250Improved
add opacity regularization (ablation)Skyfall-GS reconstruction · JAX_068 (DFC2019 LiDAR DSM)MAE (m): 3.542 -> 2.980Improved
use two refined samples per view instead of one (ablation)Skyfall-GS synthesis · JAX_068FID_CLIP: 34.11 -> 28.35Improved
increase samples per view from 2 to 5 (ablation)Skyfall-GS synthesis · JAX_068CMMD: 2.875 -> 2.677 (FID 28.35 -> 29.17, time 6.37 -> 9.80 h)Mixed
use high-to-low curriculum instead of random elevation sampling (ablation)Skyfall-GS synthesis · JAX_068FID_CLIP: 33.79 -> 28.35Improved
use high-to-low instead of reversed (low-to-high) curriculum (ablation)Skyfall-GS synthesis · JAX_068FID_CLIP: 53.03 -> 28.35Improved
use context-aware prompts instead of context-free prompts (ablation)Skyfall-GS synthesis · JAX_068FID_CLIP: 30.78 -> 28.35No clear effect
use FlowEdit-based refinement instead of SDEdit (ablation)Skyfall-GS synthesis · JAX_068FID_CLIP: 64.74 -> 28.35Improved
add diffusion-based IDU refinement on top of satellite reconstruction (vs Mip-Splatting)Skyfall-GS · DFC2019FID_CLIP: 86.72 -> 27.03Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy