AI Paper Atlas

Research map / 3D vision / Depth and stereo

Seeing and Seeing Through the Glass: Real and Synthetic Data for Multi-Layer Depth Estimation

Hongyu Wen, Yiming Zuo, Venkat Subramanian, Patrick Chen, Jia Deng

ICCV 2025 · 3D vision › Depth and stereo · approach: Depth from light field and defocus · 8 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
fine-tune on the synthetic LayeredDepth-Syn dataMetric3D V2 · LayeredDepth real benchmark (Layer 1)quadruplet accuracy: 55.14 -> 75.20Improved
fine-tune on the synthetic dataMetric3D V2 · LayeredDepth real benchmark (Layer 1)pair accuracy: 80.31 -> 89.53Improved
fine-tune on the synthetic dataMetric3D V2 · LayeredDepth real benchmark (Layer 1)triplet accuracy: 65.43 -> 81.71Improved
use Layer Index Concatenation instead of Multi-head outputNeWCRFs multi-layer baseline · LayeredDepth real benchmark (all tuples)quadruplet accuracy: 25.97 -> 26.00Improved
use Recurrent instead of Multi-head outputNeWCRFs multi-layer baseline · LayeredDepth real benchmark (all tuples)quadruplet accuracy: 25.97 -> 24.64Hurt
use Recurrent instead of Multi-head outputNeWCRFs multi-layer baseline · LayeredDepth real benchmark (Layer 7)quadruplet accuracy: 33.10 -> 27.59Hurt
use Recurrent instead of Multi-head outputNeWCRFs multi-layer baseline · LayeredDepth real benchmark (Layer 1)quadruplet accuracy: 24.21 -> 26.12Improved
replace NeWCRFs backbone with Depth Anything V2 backbone (multi-head)Multi-head baseline · LayeredDepth real benchmark (all tuples)quadruplet accuracy: 25.97 -> 61.68Improved
replace NeWCRFs backbone with Depth Anything V2 backbone (multi-head)Multi-head baseline · LayeredDepth synthetic validation (Layer 1)AbsRel (x100): 17.97 -> 8.24Improved
evaluate with Adapted Layer instead of First Layer strategyMetric3D V2 (metric) · LayeredDepth synthetic validation (transparent regions)AbsRel: 0.31 -> 0.16Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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