AI Paper Atlas

Research map / 3D vision / Depth and stereo

Large Depth Completion Model from Sparse Observations

Zhu Yu, zhengyi zhao, Runmin Zhang, Lingteng Qiu, Kejie Qiu, Yisheng He, Siyu Zhu, Zilong Dong, Si-Yuan Cao, Hui-liang Shen

ICLR 2026 · 3D vision › Depth and stereo · approach: Dense depth prediction and completion · 1 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 Poisson-based coarse depth instead of global alignment (ablation)LDCM · Estimated depth averageREL: 0.024 -> 0.022Improved
use Poisson-based coarse depth instead of LWLR (ablation)LDCM · Estimated depth averageREL: 0.025 -> 0.022Improved
add Poisson coarse depth versus sparse input only (ablation)LDCM · Estimated depth averageREL: 0.029 -> 0.022Improved
add global alignment to Poisson coarse depth (ablation)Poisson coarse depth · Coarse depth averageREL: 0.147 -> 0.059Improved
use Poisson instead of global alignment for coarse map (ablation)coarse depth · Coarse depth averageREL: 0.087 -> 0.059Improved
replace SI-Log depth head with point map head (ablation)LDCM · Depth completion averageREL: 0.026 -> 0.022Improved
replace depth + ray map with point map (ablation)LDCM · Depth completion averageREL: 0.026 -> 0.022Improved
replace depth + ray map with point map (ablation)LDCM · Point map estimation averageREL^p: 0.067 -> 0.045Improved
apply Poisson alignment to DepthAnythingV2DepthAnythingV2 · Average of 5 datasetsREL: 0.071 -> 0.039Improved
apply Poisson alignment to VGGTVGGT · Average of 5 datasetsREL: 0.121 -> 0.047Improved
apply Poisson alignment to MoGe V1MoGe V1 · Average of 5 datasetsREL: 0.142 -> 0.035Improved
add extra real data (DrivingStereo) to training (ablation)LDCM · Depth completion averageREL: 0.022 -> 0.022No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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