AI Paper Atlas

Research map / 3D vision / Depth and stereo

UniDAC: Universal Metric Depth Estimation for Any Camera

Girish Chandar Ganesan, Yuliang Guo, Liu Ren, Xiaoming Liu

CVPR 2026 · 3D vision › Depth and stereo · approach: Self-supervised monocular depth · 3 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 relative/scale decoupling with scale map instead of direct metric depth (ablation)UniDAC · KITTI-360delta1: 0.563 -> 0.622Improved
add relative/scale decoupling with scale map instead of direct metric depth (ablation)UniDAC · ScanNet++delta1: 0.782 -> 0.792Improved
use scale map S instead of single scalar scale (ablation)UniDAC · KITTI-360delta1: 0.601 -> 0.622Improved
use scale map S instead of single scalar scale (ablation)UniDAC · ScanNet++delta1: 0.773 -> 0.792Improved
single scalar scale vs direct metric depth (ablation)UniDAC · ScanNet++delta1: 0.782 -> 0.773Hurt
replace 2D RoPE with RoPE-phi (ablation)UniDAC · ScanNet++delta1: 0.750 -> 0.792Improved
replace 2D RoPE with RoPE-phi (ablation)UniDAC · KITTI-360delta1: 0.592 -> 0.622Improved
use depth-guided shift map T instead of scalar shift (ablation)UniDAC · KITTI-360delta1: 0.622 -> 0.630Improved
initialize encoder with DINOv3 instead of DINOv2 (ablation)UniDAC · KITTI-360delta1: 0.445 -> 0.622Improved
initialize encoder with DINOv3 instead of DINOv2 (ablation)DAC_U · KITTI-360delta1: 0.334 -> 0.428Improved
add A2D2 to training data (ablation)UniDAC (GT intrinsics) · KITTI-360delta1: 0.757 -> 0.836Improved
use predicted (AnyCalib) instead of ground-truth intrinsics (ablation)UniDAC · KITTI-360delta1: 0.836 -> 0.815Hurt

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