AI Paper Atlas

Research map / 3D vision / Depth and stereo

Virtual Occlusions Through Implicit Depth

Jamie Watson, Mohamed Sayed, Zawar Qureshi, Gabriel J. Brostow, Sara Vicente, Oisin Mac Aodha, Michael Firman

CVPR 2023 · 3D vision › Depth and stereo · approach: Depth from light field and defocus · 7 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
reframe occlusion as direct binary mask prediction (implicit depth) instead of depth regression then thresholdSimpleRecon backbone · ScanNetv2 test keyframesIoU All: +2.09 (60.52 to 62.61)Improved
reframe occlusion as direct binary mask prediction instead of depth regressionSimpleRecon (ResNet) backbone · ScanNetv2 test keyframesIoU All: +1.23 (58.91 to 60.14)Improved
implicit depth occlusion on MonoDepth2 backboneMonoDepth2 · ScanNetv2 test keyframesIoU All: +2.29 (46.06 to 48.35)Improved
implicit depth occlusion on ManyDepth backboneManyDepth · ScanNetv2 test keyframesIoU All: +0.87 (55.68 to 56.55)Improved
implicit depth occlusion on SimpleRecon backboneSimpleRecon · ScanNetv2 test keyframesIoU Surface: +3.04 (32.44 to 35.48)Improved
implicit depth occlusion on SimpleRecon backboneSimpleRecon · ScanNetv2 test keyframesAbs Rel (depth, via binary search): 0.0436 vs 0.0429 (slightly worse)Mixed
remove edge-based regularization near depth discontinuities (ablation)SimpleRecon (ResNet) + Ours · ScanNetv2 test keyframesIoU All: adding it: 59.79 to 60.14Improved
remove high-resolution supervision (ablation)SimpleRecon (ResNet) + Ours · ScanNetv2 test keyframesIoU All: adding it: 59.94 to 60.14 (small)Improved
replace multi-view backbone with monocular backbone (ablation)implicit depth model · ScanNetv2 test keyframesIoU All: 48.24 vs 60.14 without MVSHurt
replace implicit binary output with DORN-style 80-bin classification (ablation)SimpleRecon (ResNet) backbone · ScanNetv2 test keyframesIoU All: 56.81 vs 60.14Hurt
uniform training depth sampling instead of near-surface biased sampling (ablation)implicit depth model · ScanNetv2 test keyframesIoU All: 60.28 vs 60.14 overall, but IoU Surface 33.18 vs 33.29 and Boundary 36.16 vs 36.54Mixed
add warped previous prediction temporal input (with training-time noise and flip) (ablation)implicit depth model · ScanNetv2 test keyframesTemporal Score (lower is better): 235.1 to 164.5 (about 30% fewer flickers)Improved

Earlier methods this paper compares with

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