AI Paper Atlas

Research map / Detection and segmentation / 3D detection and driving

Map-Det3D: Metric Feed-Forward 3D Reconstruction Prior for Multi-view 3D Object Detection from Streaming Inputs

Yung-Hsu Yang, Luigi Piccinelli, Samuel Rota Bulò, Sunghwan Hong, Denys Rozumnyi, Johannes Schönberger, Zuria Bauer, Hermann Blum, Peter Kontschieder, Marc Pollefeys

ECCV 2026 · Detection and segmentation › 3D detection and driving · approach: Multi-camera BEV detection · 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
Add multi-view input with frozen backbone (ablation)Map-Det3D · CA-1M valAP15: 11.7 -> 11.8No clear effect
Unfreeze scale head only (ablation)Map-Det3D · CA-1M valAP15: 11.8 -> 11.9No clear effect
Unfreeze multi-view transformer (and scale head) (ablation)Map-Det3D · CA-1M valAP15: 11.9 -> 14.5Improved
Add multi-view input after unfreezing (ablation)Map-Det3D · CA-1M valAP15: 14.5 -> 17.2Improved
Condition on camera intrinsics (ablation)Map-Det3D · CA-1M valAP15: 11.8 -> 12.6Improved
Add camera poses to conditioning (ablation)Map-Det3D · CA-1M valAP15: 12.6 -> 17.3Improved
Enable all components (full model) (ablation)Map-Det3D · CA-1M valAP15: 11.7 -> 21.2Improved
Add direct up-to-scale 3D box head instead of 2D-to-3D lifting (ablation)Map-Det3D · CA-1M valAP15: 15.6 -> 17.3Improved
Add direct up-to-scale 3D box head instead of 2D-to-3D lifting (ablation)Map-Det3D · ScanNet (zero-shot)AP15: 10.8 -> 12.6Improved
Increase window from T=1 to T=5 (ablation)Map-Det3D · CA-1M valAP15: 14.0 -> 21.2Improved
Test with T=7 instead of trained T=5 (ablation)Map-Det3D · CA-1M valAP15: 21.2 -> 21.1No clear effect
Offline few-view setting (strides=5) instead of online sliding window (ablation)Map-Det3D · CA-1M valAP15: 21.2 -> 22.2Improved

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