AI Paper Atlas

Research map / 3D vision / 3D generation

Sat2City: 3D City Generation from A Single Satellite Image with Cascaded Latent Diffusion

Tongyan Hua, Lutao Jiang, Ying-Cong Chen, Wufan Zhao

ICCV 2025 · 3D vision › 3D generation · approach: Score distillation for text-to-3D · 12 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 Re-Hash neck with dual-stage training instead of a unified latent (ablation)Sat2City VAE · Sat2City datasetcolor training lossImproved
separate latent spaces for color via dual-stage training instead of unified geometry-color latent (ablation)Sat2City VAE · Sat2City datasetgradient conflict / color lossImproved
add inverse sampling instead of direct color splatting (ablation)Sat2City · Sat2City datasetrendering artifacts (qualitative)Improved
add dense latent diffusion stage to the cascade (ablation)Sat2City · Sat2City datasetgeneration quality (qualitative)Improved
keep sparse latent stage supplying pruning decisions to appearance decoding (ablation)Sat2City · Sat2City datasetappearance decoding (qualitative)Improved
use Sat2City instead of BlockFusionSat2City · Sat2City datasetMMD (CD): 0.0326 -> 0.0165Improved
use Sat2City instead of BlockFusionSat2City · Sat2City datasetCOV (CD, %): 50.49 -> 100.00Improved
use Sat2City instead of BlockFusionSat2City · Sat2City datasetCOV (EMD, %): 55.66 -> 60.00Improved
direct 3D generation instead of Sat2Scene 2D renderingSat2City · user studyTPQ: 6.17 -> 7.35Improved
Sat2City instead of retrained Sat2Scene on low-density point cloudsSat2City · Sat2City dataset (user study)TSC: 3.30 -> 8.03Improved
direct 3D generation instead of CityDreamer 2D renderingSat2City · user studyTSC: 6.63 -> 8.03Improved

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