AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Reconstructing Satellites in 3D From Amateur Telescope Images

Zhiming Chang, Boyang Liu, Yifei Xia, Youming Guo, Boxin Shi, He Sun

TPAMI 2025 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting · 13 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 controlled Gaussian growth regulation (ablation)full pipeline · Simulation 1SSIM: 0.87 -> 0.90Improved
add BnB pose refinement (ablation)full pipeline · Simulation 1PSNR: 22.51 -> 25.33Improved
add BnB pose refinement after initialization (ablation)pose pipeline · synthetic pose estimationATE: 2.61 -> 2.43Improved
add point cloud filtering (ablation)full pipeline · Simulation 1SSIM: 0.62 -> 0.90Improved
add image pre-processing (ablation)full pipeline · Simulation 1PSNR: 20.87 -> 25.33Improved
add modified SfM init, controlled growth, BnB and filtering to original GS (ablation)Gaussian Splatting · Simulation 1PSNR: 20.96 -> 25.33Improved
add VRT denoising after stacking and sharpening (ablation)pre-processing pipeline · Simulation 1PSNR: 27.60 -> 27.74Improved
add wavelet sharpening to stacking (ablation)pre-processing pipeline · Simulation 1PSNR: 27.00 -> 27.60Improved
add SelfDeblur to stacking (ablation)pre-processing pipeline · Simulation 1PSNR: 27.00 -> 23.89Hurt
constrain NeRF sampling region (BARF Con.) (ablation)BARF · Simulation 1PSNR: 17.64 -> 24.20Improved
use our modified SfM initialization instead of Dust3rpose initialization · synthetic pose estimationATE: 138.81 -> 2.61Improved
GS with BnB instead of NeRF-- or BARF for reconstructionreconstruction · Simulation 1PSNR: 16.09 -> 25.32Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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