AI Paper Atlas

Research map / 3D vision / Depth and stereo

Deep End-to-End Alignment and Refinement for Time-of-Flight RGB-D Module

Di Qiu, Jiahao Pang, Wenxiu Sun, Chengxi Yang

ICCV 2019 · 3D vision › Depth and stereo · approach: Learned stereo with specialized sensors · 32 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 flow refinement with camera-parameter depth-to-flow conversion and fusion network (ablation)cross-modal flow alignment · Synthetic data, sigma 6AEPE: 2.70 -> 2.45Improved
add flow refinement with camera-parameter depth-to-flow conversion and fusion network (ablation)cross-modal flow alignment · Real data, sigma 6AEPE: 1.59 -> 1.36Improved
feed raw ToF depth directly to the fusion network instead of converting it to flow (ablation)cross-modal flow alignment · Synthetic data, sigma 6AEPE: 2.70 -> 2.79Hurt
direct depth fusion versus no refinement (ablation)cross-modal flow alignment · Real data, sigma 2AEPE: 1.28 -> 1.29No clear effect
add gradient loss term (ablation)ToF-KPN · ToF-FlyingThings3DMAE (cm): 2.43 -> 1.51Improved
add kernel normalization (ablation)ToF-KPN · ToF-FlyingThings3DMAE (cm): 1.73 -> 1.51Improved
apply the bias before the kernel instead of after (ablation)ToF-KPN · ToF-FlyingThings3DMAE (cm): 1.62 -> 1.51Improved
add bias term when kernel normalization is absent (ablation)NoNorm KPN · ToF-FlyingThings3DMAE (cm): 1.74 -> 1.73No clear effect
use kernel normalization or early bias over vanilla KPN (ablation)vanilla KPN (NoNormAftBias) · ToF-FlyingThings3DMAE (cm): 1.76 -> 1.62Improved
use kernel prediction (ToF-KPN) instead of direct regression U-Net (ablation)depth refinement backbone · ToF-FlyingThings3DMAE (cm): 1.79 -> 1.51Improved
jointly fine-tune alignment and refinement end to endDEAR · ToF-FlyingThings3D misaligned testMAE (cm): 2.90 -> 2.81Improved
ToF-KPN versus multi-reflection module on FLATToF-KPN · FLAT static testMAE (cm): 3.88 -> 0.68Improved

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