AI Paper Atlas

Research map / 3D vision / Depth and stereo

Learning Depth Estimation for Transparent and Mirror Surfaces

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

ICCV 2023 · 3D vision › Depth and stereo · approach: Dense depth prediction and completion · 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
in-paint ToM regions with uniform colors to get virtual depth labels (no fine-tuning)DPT · Booster train (ToM pixels)MAE (mm): 113.14 -> 57.19Improved
use N=5 colors with median instead of N=1 (ablation)DPT virtual depth · Booster train (ToM pixels)MAE (mm): 65.58 -> 57.19Improved
fine-tune on virtual depth labels from in-painted imagesMiDaS · Booster train (ToM pixels)MAE (mm): 122.33 -> 93.66Improved
fine-tune on virtual depth labels from in-painted imagesDPT · Booster train (ToM pixels)MAE (mm): 113.14 -> 70.68Improved
self-train on own predictions without in-painting (ablation)MiDaS and DPT · Booster train (ToM pixels)MAE (mm): 122.33 -> 126.71 (MiDaS); 113.14 -> 118.84 (DPT)No clear effect
in-paint at inference with proxy-segmentation masks instead of fine-tuning (ablation)DPT · Booster train (All pixels)delta<1.25: 96.79 -> 93.23Hurt
use proxy segmentation masks (Trans2Seg/MirrorNet) instead of GT for fine-tuning (ablation)DPT fine-tuning · Booster train (ToM pixels)MAE (mm): 67.95 -> 70.67Mixed
naively extend in-painting to stereo by masking both images (ablation)RAFT-Stereo · Booster test (ToM pixels)bad-2 (%): 56.77 -> 57.08No clear effect
merge stereo disparities with DPT virtual depth on ToM regionsRAFT-Stereo · Booster test (ToM pixels)bad-2 (%): 56.77 -> 47.54Improved
merge stereo disparities with DPT virtual depth on ToM regionsCREStereo · Booster test (ToM pixels)bad-2 (%): 51.83 -> 36.90Improved
self-train stereo network on own predictions (ablation)RAFT-Stereo · Booster test (All pixels)bad-2 (%): 17.42 -> 18.42Hurt
use proxy masks instead of GT masks for merged stereo labels (ablation)RAFT-Stereo · Booster test (All pixels)bad-2 (%): 17.42 -> 19.56Mixed

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