AI Paper Atlas

Research map / 3D vision / Depth and stereo

G2-MonoDepth: A General Framework of Generalized Depth Inference From Monocular RGB+X Data

Haotian Wang, Meng Yang, Nanning Zheng

TPAMI 2023 · 3D vision › Depth and stereo · approach: Self-supervised monocular depth · 25 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
use ReZero blocks instead of BN (ablation)G2-MonoDepth · KITTI synthetic (0.1% sparsity)RMSE: 16.46 -> 12.03Improved
use ReZero blocks instead of BN (ablation)G2-MonoDepth · NYUv2 synthetic (0.1% sparsity)RMSE: 6.49 -> 6.02Improved
use Sobel operator instead of differential operator (ablation)G2-MonoDepth · KITTI synthetic (0.1% sparsity)RMSE: 29.66 -> 31.32Hurt
use Sobel operator instead of differential operator (ablation)G2-MonoDepth · KITTI synthetic (10% sparsity)RMSE: 5.46 -> 5.18Improved
use mean/mean deviation (G2S) instead of median standardization (MS) (ablation)G2-MonoDepth loss · KITTI synthetic (100% sparsity)RMSE: 18.98 -> 7.49Improved
use mean/mean deviation (G2S) instead of median standardization (MS) (ablation)G2-MonoDepth loss · NYUv2 synthetic (10% sparsity)RMSE: 15.75 -> 4.28Improved
use mean/mean deviation (G2S) instead of z-score (ZS) standardization (ablation)G2-MonoDepth loss · NYUv2 synthetic (10% sparsity)RMSE: 4.02 -> 4.28Hurt
use mean/mean deviation (G2S) instead of z-score (ZS) standardization (ablation)G2-MonoDepth loss · Ibims synthetic (0% sparsity)SRMSE: 0.92 -> 0.83Improved
use G2-MonoDepth over MiDas with fewer training data (0.23 million vs 19 million) and 18M vs 105M parameters (ablation)MiDas · Depth estimation, real-world (6 datasets)average rank on SRMSE: 2.3 -> 1.7Improved
add sparse depth input (0% to 0.1% valid pixels)G2-MonoDepth · synthetic dataRMSEImproved
use unified G2-MonoDepth instead of JIFFJIFF · NYUv2 depth enhancement (real)RMSE: 3.06 -> 3.87Hurt
use G2-MonoDepth instead of GuideNetGuideNet · KITTI depth completion 64-line (real)RMSE: 3.17 -> 4.23Hurt

Later papers that compared with this method

3 later accepted papers report G2-MonoDepth as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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