AI Paper Atlas

Research map / 3D vision / Depth and stereo

CARD: A Multi-Modal Automotive Dataset for Dense 3D Reconstruction in Challenging Road Topography

Gasser Elazab, Frank Neuhaus, Tilman Koß, Malte Splietker, Aditya Date, Michael Unterreiner, Maximilian Jansen, Olaf Hellwich

CVPR 2026 · 3D vision › Depth and stereo · approach: Foundation models for monocular geometry · 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
fine-tune MoGe2L on CARD with affine-invariant loss plus L1 height-space lossMoGe2L · CARD full imageAbsRel: 0.045 -> 0.029Improved
fine-tune MoGe2L on CARD with affine-invariant loss plus L1 height-space lossMoGe2L · CARD bounding boxesHeight AbsDiff: 0.051 -> 0.034Improved
fine-tune MoGe2L on CARD with affine-invariant loss plus L1 height-space lossMoGe2L · CARD full imageHeight AbsDiff: 0.119 -> 0.051Improved
fine-tune UniDepthV2-L decoder on CARD with plain L1 depth lossUniDepthV2-L · CARD full imageRMSE: 1.825 -> 1.749Improved
fine-tune UniDepthV2-L decoder on CARD with plain L1 depth lossUniDepthV2-L · CARD bounding boxesAbsRel: 0.029 -> 0.027No clear effect
replace monocular teacher with FoundationStereo and use L1 metric loss in DMD3CDMD3C · CARD depth completion (full image)RMSE [m]: 0.7742 -> 0.7510Improved
replace monocular teacher with FoundationStereo and use L1 metric loss in DMD3CDMD3C · CARD depth completion (bounding boxes)delta1: 0.9900 -> 0.9984Improved
replace monocular teacher with FoundationStereo and use L1 metric loss in DMD3CDMD3C · CARD depth completion (full image)iMAE: 0.0050 -> 0.0057Hurt
use stereo (FoundationStereo) instead of best monocular modelMoGe2L · CARD bounding boxesHeight AbsDiff: 0.051 -> 0.025Improved
apply per-image median scaling to monocular predictionsDAV2 · CARD full imageAbsRel: 1.537 -> 0.096Improved
add LiDAR-only depth completion on top of stereo teacher (DMD3C+FS vs FoundationStereo)DMD3C+FS · CARD bounding boxesRMSE: 0.1918 -> 0.185Hurt
add voxel cleaning and baseline-adaptive voting to GT aggregation (ablation)LiDAR GT pipeline · CARD ground truth (qualitative)dynamic-point artifactsImproved

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