AI Paper Atlas

Research map / 3D vision / Depth and stereo

Physically Grounded Monocular Depth via Nanophotonic Wavefront Encoding

Bingxuan Li, Jiahao Wu, Yuan Xu, Zezheng Zhu, Yunxiang Zhang, Kenneth Chen, Yanqi Liang, Nanfang Yu, Qi Sun

ECCV 2026 · 3D vision › Depth and stereo · approach: Depth from light field and defocus · 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 pretrained depth prior (initialize from pretrained ViT) (ablation)Ours-Small with metalens · FlyingThings3DMAE: 0.061 -> 0.022Improved
use metalens design instead of DeepDfD optics (ablation)Ours-Small · FlyingThings3DMAE: 0.035 -> 0.022Improved
use ViT instead of U-Net backbone (no prior) (ablation)Ours-Small with metalens · FlyingThings3DMAE: 0.063 -> 0.061No clear effect
fine-tune pretrained ViT with DeepDfD optics instead of U-Net from scratch (ablation)DeepDfD baseline · FlyingThings3DMAE: 0.089 -> 0.035Improved
add decoder-side fusion module to input adaptation (ablation)Ours-Base · Physical experimentAbsRel: 0.055 -> 0.058Hurt
use input adaptation instead of fusion only (ablation)Ours-Base · Physical experimentAbsRel: 0.109 -> 0.055Improved
add disocclusion-aware forward model (ablation)Ours-Base · Physical experiment (real data included)AbsRel: 0.074 -> 0.055Improved
add polarization-aware augmentation (ablation)Ours-Base · Physical experiment (real data included)AbsRel: 0.066 -> 0.055Improved
add polarization-aware augmentation (ablation)Ours-Base · Physical experiment (synthetic only)delta_0.5: 0.240 -> 0.546Improved
add light imbalance augmentation (ablation)Ours-Base · Physical experiment (synthetic only)delta_0.5: 0.451 -> 0.546Improved
add noise augmentation (ablation)Ours-Base · Physical experiment (real data included)delta_0.5: 0.907 -> 0.895Hurt
fine-tune Depth Anything v2 on our dataset without depth encodingDepthAny. v2 · NYU Depth V2 (simulated)AbsRelNo clear effect

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