AI Paper Atlas

Research map / 3D vision / 3D generation

MUVA: A New Large-Scale Benchmark for Multi-View Amodal Instance Segmentation in the Shopping Scenario

Zhixuan Li, Weining Ye, Juan Terven, Zachary Bennett, Ying Zheng, Tingting Jiang, Tiejun Huang

ICCV 2023 · 3D vision › 3D generation · approach: Learning 3D reconstruction from images · 16 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
train with six views instead of one view (same training data) (ablation)MASFormer · MUVA testAP: 25.6 -> 39.4Improved
train with six views instead of one view (ablation)Baseline (FES only) · MUVA testAP: 17.8 -> 22.9Improved
add view-level attention (ablation)MASFormer baseline · MUVA testAP: 22.9 -> 28.7Improved
add instance-level attention (ablation)MASFormer baseline · MUVA testAP: 22.9 -> 34.1Improved
combine view-level and instance-level attention (ablation)MASFormer · MUVA testAP: 34.1 -> 39.4Improved
increase number of input views from 1 to 6 (random order) (ablation)MASFormer · MUVA testAP: 25.6 -> 39.4Improved
randomize order of input views instead of fixed order (ablation)MASFormer (6 views) · MUVA testAP: 37.9 -> 39.4Improved
use stronger backbone (ResNeXt-101 vs ResNet-50) (ablation)MASFormer (6 views) · MUVA testAP: 39.4 -> 43.0Improved
add synthetic MUVA data to real D2SA training dataMASFormer · D2SA val (overlapping categories)AP: 63.5 -> 68.4Improved
train on synthetic MUVA only and test on real D2SAMASFormer · D2SA val (overlapping categories)AP: 63.5 -> 41.9Hurt
use Transformer multi-view model instead of BCNetMASFormer · MUVA testcomputational cost: GPU memory 4G -> 13G; FPS 8.3 -> 3.7Hurt

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