AI Paper Atlas

Research map / 3D vision / Depth and stereo

Physics to the Rescue: Deep Non-Line-of-Sight Reconstruction for High-Speed Imaging

Fangzhou Mu, Sicheng Mo, Jiayong Peng, Xiaochun Liu, Ji Hyun Nam, Siddeshwar Raghavan, Andreas U. Velten, Yin Li

TPAMI 2022 · 3D vision › Depth and stereo · approach: Non-line-of-sight imaging · 58 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 supervised physics-embedded model instead of LFEOurs (sup) · Alphanumerics unseen posesPSNR: 22.42 -> 24.60Improved
add unsupervised training (Poisson loss on transients) to supervised training (ablation)Ours (joint) · Alphanumerics unseen posesPSNR: 24.60 -> 25.05Improved
add supervised loss to unsupervised training (ablation)Ours (unsup) · Alphanumerics unseen posesSSIM: 0.709 -> 0.861Improved
use unsupervised transient training only vs RSDOurs (unsup) · Alphanumerics unseen posesPSNR: 20.83 -> 20.97No clear effect
joint training instead of supervised only (ablation)Ours (joint) · CMU out-of-distributionPSNR: 22.46 -> 22.11Hurt
unsupervised-only training instead of supervised for out-of-distribution (ablation)Ours (unsup) · CMU out-of-distributionPSNR: 22.46 -> 23.18Improved
replace NeTF rendering with proposed transient rendering recipe (NeTF++)NeTF · CMU out-of-distributionPSNR: 20.31 -> 23.26Improved
feed-forward learned scene priors instead of per-scene NeTF++Ours (sup) · CMU out-of-distributionPSNR: 23.26 -> 22.46Hurt
use ConvNet-free volume renderer instead of LFE on motorbikesOurs (sup) · Motorbikes unseen posesPSNR: 21.09 -> 24.05Improved
use our encoder features instead of RSD features for classificationOurs (sup) · Alphanumerics classificationaccuracy: 82.2% -> 85.4%Improved
add joint training for classification features (ablation)Ours (joint) · Alphanumerics classificationaccuracy: 85.4% -> 85.2%No clear effect
add total variation prior (ablation)Ours · NLOS intensity renderingqualitativeImproved

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