AI Paper Atlas

Research map / 3D vision / Depth and stereo

Efficient and High-Quality Depth Estimation via Pixel-Space Diffusion with Linear Attention

Bingde Liu, Wu Ran, Jinglei Zhang, Huanhuan Yuan, Chao Ma

ECCV 2026 · 3D vision › Depth and stereo · approach: Self-supervised monocular depth · 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 Global PCM (DINOv2 semantic alignment) (ablation)Lapis · zero-shot depth avgAbsRel: 19.8 -> 4.8Improved
add Local PCM (ablation)Lapis · zero-shot depth avgAbsRel: 5.1 -> 4.8Improved
add Pixel-level Refinement Module (ablation)Lapis · zero-shot depth avgAbsRel: 4.9 -> 4.8No clear effect
use ELU+1 linear attention instead of softmax (ablation)Lapis · zero-shot depth avgAbsRel: 5.0 -> 4.8No clear effect
use AdaLN/MLP conditioning instead of linear cross-attention (ablation)Lapis · zero-shot depth avgAbsRel: 10.8 -> 4.8Improved
use x-prediction instead of v-prediction (ablation)Lapis · zero-shot depthAbsRelImproved
use more sampling steps than one (ablation)Lapis · zero-shot depthAbsRelHurt
use Lapis instead of Pixel-Perfect Depth at 1080PLapis · 1080P zero-shot depth avglatency (ms): 905.5 -> 119.0Improved
use Lapis vs Pixel-Perfect Depth at native resolutionLapis · native zero-shot depth avgAbsRel: 4.2 -> 4.1Improved
use Lapis vs MoGe-2 for speed at 1080PLapis · 1080P runtimelatency (ms): 115.3 -> 119.0Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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