AI Paper Atlas

Research map / 3D vision / Depth and stereo

NVDS+: Towards Efficient and Versatile Neural Stabilizer for Video Depth Estimation

Yiran Wang, Min Shi, Jiaqi Li, Chaoyi Hong, Zihao Huang, Juewen Peng, Zhiguo Cao, Jianming Zhang, Ke Xian, Guosheng Lin

TPAMI 2024 · 3D vision › Depth and stereo · approach: Dense depth prediction and completion · 18 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 bidirectional averaging over forward-only inference (ablation)NVDS+ Large (DPT-Large) · VDW testOPW: 0.165 -> 0.147Improved
add flow-guided consistency fusion on top of averaging (ablation)NVDS+ Large (DPT-Large) · VDW testOPW: 0.147 -> 0.129Improved
add flow-guided consistency fusion on top of averaging (ablation)NVDS+ Large (MiDaS-v2.1-Large) · VDW testOPW: 0.180 -> 0.148Improved
add temporal loss during training (ablation)NVDS+ Large · VDW subsetOPW: 0.303 -> 0.216Improved
add temporal loss during training (ablation)NVDS+ Large · VDW subsetdelta1: 0.627 -> 0.625No clear effect
use three reference frames instead of one (ablation)NVDS+ Large · VDW subsetOPW: 0.272 -> 0.216Improved
use four reference frames instead of three (ablation)NVDS+ Large · VDW subsetOPW: 0.216 -> 0.224No clear effect
increase inter-frame interval from 1 to 5 (ablation)NVDS+ Large · VDW subsetOPW: 0.216 -> 0.246Hurt
add the stabilization network instead of a multi-frame baseline (ablation)DPT-Large · VDW subsetOPW: 0.471 -> 0.216Improved
train on VDW instead of NYUDV2 (ablation)NVDS+ · Sintel (zero-shot)delta1: 0.527 -> 0.591Improved
train on VDW instead of IRS+TartanAir (ablation)NVDS+ · Sintel (zero-shot)OPW: 0.489 -> 0.424Improved
pretrain on VDW before finetuning on NYUDV2 (ablation)NVDS+ Large (DPT-Large) · NYUDV2delta1: 0.931 -> 0.950Improved

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