AI Paper Atlas

Research map / 3D vision / Depth and stereo

BridgeDepth: Bridging Monocular and Stereo Reasoning with Latent Alignment

Tongfan Guan, Jiaxin Guo, Chen Wang, Yun-Hui Liu

ICCV 2025 · 3D vision › Depth and stereo · approach: Self-supervised monocular depth · 14 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 monocular-readout cross-attention (monocular priors into stereo aggregation) (ablation)NMRF-s baseline · ETH3D zero-shotBP-1: 3.7 -> 2.3Improved
add monocular-update (stereo evidence back into monocular stream) (ablation)BridgeDepth · ETH3D zero-shotBP-1: 2.3 -> 2.1Improved
add fine-grained 1/4 resolution alignment (ablation)BridgeDepth · ETH3D zero-shotBP-1: 2.1 -> 1.6Improved
add monocular loss supervision (ablation)BridgeDepth · ETH3D zero-shotBP-1: 1.6 -> 1.3Improved
add all monocular components (cost: slower inference) (ablation)NMRF-s baseline · Inference time 960x540time (s): 0.044 -> 0.147Hurt
use iterative bidirectional alignment instead of post-hoc fusion (ablation)BridgeDepth (DAv2-B) · ETH3D zero-shotBP-1: 3.2 -> 1.4Improved
swap monocular backbone from DAv2-L to UniDepthV2 (ablation)BridgeDepth · ETH3D zero-shotBP-1: 1.3 -> 1.8Hurt
use BridgeDepth instead of NMRF in zero-shot evaluationNMRF · Middlebury (Q) zero-shotBP-2: 7.5 -> 4.3Improved
BridgeDepth versus FoundationStereo on KITTI-12 zero-shotBridgeDepth · KITTI-12 zero-shotD1: 3.6 vs 3.2 (FoundationStereo)Hurt
enlarge stereo feature network (ConvNeXt-Tiny based BridgeDepth-L)BridgeDepth · Scene Flow testBP-1: 3.67 -> 3.25Improved

Later papers that compared with this method

1 later accepted paper reports BridgeDepth as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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