AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Revisiting Pose Sensitivity in Splat-based Computed Tomography under Sparse-view Reconstruction

Kiseok Choi, Hyeongjun Cho, Inchul Kim, Min H. Kim

CVPR 2026 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting · 0 citations (OpenAlex)

Read the paper

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 joint pose self-calibration to splat CTR2-Gaussian · Broccoli, noisy datasetPSNR (dB): 22.21 -> 30.20Improved
add joint pose self-calibration to splat CTR2-Gaussian · Broccoli, noise-free datasetPSNR (dB): 36.54 -> 34.70Hurt
add joint pose self-calibration to splat CTR2-Gaussian · Beetle, no pose noisePSNR (dB): 43.18 -> 43.22No clear effect
add joint pose self-calibration at moderate pose noise (ablation)R2-Gaussian · Beetle, pose noise rot 0.02 trans 1.0PSNR (dB): 33.90 -> 40.65Improved
add joint pose self-calibration at the strongest pose noise (ablation)R2-Gaussian · Beetle, pose noise rot 0.10 trans 5.0PSNR (dB): 30.80 -> 32.32Improved
add joint pose self-calibration at the strongest pose noise (ablation)R2-Gaussian · Head, pose noise rot 0.10 trans 5.0PSNR (dB): 26.41 -> 28.17Improved
add joint pose self-calibration with 75 viewsR2-Gaussian · Synthetic CT with pose noise, 75 viewsPSNR (dB): 28.50 -> 33.42Improved
add joint pose self-calibration with 25 viewsR2-Gaussian · Synthetic CT with pose noise, 25 viewsPSNR (dB): 26.44 -> 29.02Improved
reduce input views from 75 to 25Ours (self-calibrating splat CT) · Synthetic CT with pose noise, 25 viewsPSNR (dB): 33.42 -> 29.02Hurt
self-calibration instead of NeAT for pose estimationOurs (self-calibrating splat CT) · Synthetic CT, 15 scenes mean (rot 0.03, trans 1.0)translation RMSE (AU): 1.437 -> 0.726Improved
self-calibration instead of Thies et al. for pose estimationOurs (self-calibrating splat CT) · Synthetic CT, 15 scenes mean (rot 0.03, trans 1.0)orientation RMSE (deg): 4.076 -> 0.627Improved
remove TV regularization and add pose calibrationOurs (self-calibrating splat CT) · Synthetic CT, mean computation timecomputation time (min): 23.19 -> 20.89Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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