AI Paper Atlas

Research map / 3D vision / Depth and stereo

Hybrid-grained Feature Aggregation with Coarse-to-fine Language Guidance for Self-supervised Monocular Depth Estimation

Wenyao Zhang, Hongsi Liu, Bohan Li, Jiawei He, Zekun Qi, Yunnan Wang, Shengyang Zhao, Xinqiang Yu, Wenjun Zeng, Xin Jin

ICCV 2025 · 3D vision › Depth and stereo · approach: Self-supervised monocular depth · 5 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
plug Hybrid-depth encoder into Monodepth2Monodepth2 · KITTI Eigen splitAbs Rel: 0.115 -> 0.093Improved
plug Hybrid-depth encoder into ManydepthManydepth · KITTI Eigen splitAbs Rel: 0.098 -> 0.096Improved
plug Hybrid-depth encoder into Mono-ViFIMono-ViFI · KITTI Eigen splitAbs Rel: 0.105 -> 0.094Improved
add coarse depth sensing stage (vs stronger backbone alone) (ablation)Monodepth2 · KITTI Eigen splitAbs Rel: 0.105 -> 0.093Improved
add coarse depth sensing stage (vs stronger backbone alone) (ablation)Manydepth · KITTI Eigen splitAbs Rel: 0.096 -> 0.096No clear effect
add language-guided contrastive loss on top of intramodal loss (ablation)Monodepth2 + Hybrid-depth · KITTI Eigen splitAbs Rel: 0.098 -> 0.093Improved
add intramodal contrastive loss on top of language-guided loss (ablation)Monodepth2 + Hybrid-depth · KITTI Eigen splitAbs Rel: 0.095 -> 0.093Improved
add depth-instruction language alignment (granularity calibrator) in coarse stage (ablation)Monodepth2 + Hybrid-depth · KITTI Eigen splitAbs Rel: 0.098 -> 0.093Improved
add depth-instruction language alignment in fine stage (ablation)Monodepth2 + Hybrid-depth · KITTI Eigen splitAbs Rel: 0.100 -> 0.093Improved
combine CLIP and DINO instead of using only one (ablation)Monodepth2 + Hybrid-depth · KITTI Eigen splitAbs Rel: 0.102 -> 0.093 (CLIP only); 0.104 -> 0.093 (DINO only)Improved
increase learnable depth tokens beyond 256 (ablation)Monodepth2 + Hybrid-depth · KITTI Eigen splitAbs Rel: 0.093 -> 0.097 (512 tokens)Hurt
plug Hybrid-depth into BEV detectorsBEVDet and FB-BEV · nuScenes valmAP / NDS: BEVDet mAP 0.283 -> 0.325; FB-BEV NDS 0.406 -> 0.439Improved

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