AI Paper Atlas

Research map / 3D vision / Depth and stereo

DENALI: A Dataset Enabling Non-Line-of-Sight Spatial Reasoning with Low-Cost LiDARs

Nikhil Behari, Diego Rivero, Luke Apostolides, Suman Ghosh, Paul Pu Liang, Ramesh Raskar

CVPR 2026 · 3D vision › Depth and stereo · approach: Non-line-of-sight imaging · 0 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 600 ps timing jitter blur (ablation)NLOS localization · DENALI localizationRMSE: 0.0804 -> 0.0819Hurt
add 50 ps or 100 ps timing jitter blur (ablation)NLOS localization · DENALI localizationRMSE: 0.0804 -> 0.0802No clear effect
add 600 ps timing jitter blur (ablation)NLOS size classification · DENALI size classificationAccuracy: 0.8616 -> 0.7944Hurt
add 600 ps timing jitter blur (ablation)NLOS object classification · DENALI object classificationTop-1: 0.1554 -> 0.1260Hurt
add 100 ps timing jitter blur (ablation)NLOS object classification · DENALI object classificationTop-1: 0.1554 -> 0.1684Improved
use 1D CNN instead of MLPhistogram model · DENALI localizationRMSE: 0.1045 -> 0.0456Improved
use 1D CNN instead of Transformerhistogram model · DENALI localizationRMSE: 0.0579 -> 0.0456Improved
use 3D CNN (spatiotemporal) instead of 1D CNNhistogram model · DENALI localizationRMSE: 0.0456 -> 0.0475No clear effect
use 3D CNN instead of 1D CNNhistogram model · DENALI object classificationTop-1: 0.3876 -> 0.3523Hurt
use 3D CNN instead of 1D CNNhistogram model · DENALI object classificationMacro-F1: 0.3832 -> 0.4377Improved
use 8 inch objects instead of 4 inch1D CNN · DENALI localizationRMSE: 0.0548 -> 0.0341Improved
use 8 inch objects instead of 4 inch1D CNN · DENALI object classificationTop-1: 0.3191 -> 0.4573Improved

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