AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

Learning to Discriminate Scene Structures Makes Self-Supervised Depth Learning Scalable

Mengtan Zhang, Yuchuan Cui, Yu Ma, Zizhan Guo, Wei Ye, Rui Fan

NeurIPS 2026 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Pretext-task visual pre-training · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes MaSS, a self-supervised monocular depth framework that learns to discriminate scene structures so that depth learning scales across diverse training scenes.

Problem

Self-supervised monocular depth estimation often degrades when trained on diverse scenes, because models encode dataset-specific structural biases that cause cross-domain optimization conflicts.

Approach

Under self-supervision, models encode dataset-specific structural biases rather than transferable scene geometry; MaSS is designed to address this by learning to discriminate scene structures so that training scales across diverse data. Full method details are not available from the abstract.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add scene-structure contrastive learning objective (ablation)MaSS · Waymo zero-shotAbs Rel: 0.163 -> 0.123Improved
add decoupled structural pathway (representation decoupling) (ablation)MaSS · NYUv2 (mixed training)Abs Rel: 0.116 -> 0.104Improved
add bidirectional interaction architecture between depth encoder and VFM (ablation)MaSS · Waymo zero-shotAbs Rel: 0.190 -> 0.123Improved
use MaSS instead of frozen DINOv2 with DPT head (ablation)DINOv2 backbone · nuScenes (mixed training)Abs Rel: 0.186 -> 0.134Improved
fully fine-tune DINOv2 with DPT instead of freezing it (ablation)DINOv2 + DPT · 7-Scenes zero-shotdelta1: 0.839 -> 0.600Hurt
replace DINOv2 with stronger DINOv3 backbone (ablation)MaSS · Training sets and zero-shotAbs Rel: 0.134 -> 0.136 (nuScenes)No clear effect
train on mixed datasets instead of single datasetMaSS · KITTI, DDAD, NYUv2, nuScenesAbs Rel: 0.094 -> 0.092 (KITTI)Improved
train on mixed datasets instead of single datasetexisting SSMDE baselines (Lite-Mono, Dynamo-Depth, SC-DepthV3, DCPI-Depth) · NYUv2Abs Rel: 0.151 -> 0.331 (DCPI-Depth)Hurt
mixed-dataset training instead of KITTI-onlyMaSS · Waymo zero-shotAbs Rel: 0.141 -> 0.123Improved
add 50K TartanAir samples (150K to 200K)MaSS mixed · DIML and DIODE out-of-distributionAbs Rel, delta1: +4.3% Abs Rel, +3.0% delta1Improved
add 50K TartanAir samples (150K to 200K)MaSS mixed · training domainsAbs Rel, delta1: +1.5% Abs Rel, +0.2% delta1No clear effect

Earlier methods this paper compares with

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

Surprising findings

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