AI Paper Atlas

Research map / 3D vision / Depth and stereo

Booster: A Benchmark for Depth From Images of Specular and Transparent Surfaces

Pierluigi Zama Ramirez, Alex Costanzino, Fabio Tosi, Matteo Poggi, Samuele Salti, Stefano Mattoccia, Luigi Di Stefano

TPAMI 2023 · 3D vision › Depth and stereo · approach: Depth from light field and defocus · 39 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 fine-tuning on the Booster training split (ablation)CREStereo · Booster Balanced (full-res GT, all pixels)bad-2: 33.07 -> 29.48Improved
add fine-tuning on the Booster training split (ablation)RAFT-Stereo · Booster Balanced (quarter-res GT, all pixels)bad-2: 17.43 -> 10.72Improved
add fine-tuning on the Booster training split (ablation)CFNet · Booster Balanced (full-res GT, all pixels)bad-2 and MAE: bad-2 61.34 -> 66.94; MAE 27.60 -> 19.65Mixed
add fine-tuning on the Booster training split (ablation)RAFT-Stereo · Booster Balanced (full-res GT, material Class 0)bad-2: 28.14 -> 30.94Hurt
add fine-tuning on the Booster training split (ablation)CREStereo · Booster Balanced (full-res GT, material Class 3)bad-2: 79.50 -> 67.40Improved
add fine-tuning on the Booster training split (ablation)CREStereo · Booster Unbalanced (material Class 3)bad-2: 86.39 -> 63.37Improved
add fine-tuning on the Booster training split (ablation)RAFT-Stereo · Booster Unbalanced (full-res GT, all pixels)bad-2 and MAE: bad-2 54.47 -> 58.55; MAE 9.52 -> 5.68Mixed
add fine-tuning on the Booster training split (ablation)CREStereo · Booster Unbalanced (full-res GT, all pixels)bad-2: 56.00 -> 53.52Improved
add fine-tuning on the Booster training split (ablation)DPT · Booster Mono (all pixels)Abs Rel: 0.069 -> 0.065Improved
add fine-tuning on the Booster training split (ablation)MiDaS · Booster Mono (all pixels)Abs Rel: 0.073 -> 0.073No clear effect
add Boosting multi-resolution mergingMiDaS · Booster Mono (all pixels)Abs Rel: 0.073 -> 0.072No clear effect
add Boosting multi-resolution mergingLeRes · Booster Mono (all pixels)Abs Rel: 0.077 -> 0.078No clear effect

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