AI Paper Atlas

Research map / Detection and segmentation / 3D detection and driving

MVSalNet:Multi-View Augmentation for RGB-D Salient Object Detection

Jiayuan Zhou, Lijun Wang, Huchuan Lu, Kaining Huang, Xinchu Shi, Bocong Liu

ECCV 2022 · Detection and segmentation › 3D detection and driving · approach: Multi-camera BEV detection · 44 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 multi-view augmentation with three encoder-decoder branches (original plus two rotated views) (ablation)MVSalNet · NLPRadaptive F-measure: 0.860 -> 0.901Improved
use novel views as extra training data only (ablation)single encoder-decoder · NLPRadaptive F-measure: 0.860 -> 0.874Improved
use rendered novel views instead of three branches with identical RGB (ablation)MVSalNet · NLPRadaptive F-measure: 0.891 -> 0.901Improved
use two novel views instead of one (ablation)MVSalNet · NLPRadaptive F-measure: 0.882 -> 0.901Improved
use rendered views instead of concatenating depth with RGB (ablation)MVSalNet · NLPRadaptive F-measure: 0.895 -> 0.901Improved
add two more views at ±60 degrees (4 views) (ablation)MVSalNet · NLPRadaptive F-measure: 0.901 -> 0.899No clear effect
change rotation angle from ±30 to ±60 degrees (ablation)MVSalNet · NLPRadaptive F-measure: 0.901 -> 0.889Hurt
add Transformer dynamic filtering (TDF) instead of plain skip connection (ablation)MVSalNet · NLPRadaptive F-measure: 0.886 -> 0.901Improved
use multi-dilation SW-MSA heads instead of single head (ablation)TDF · NLPRadaptive F-measure: 0.892 -> 0.901Improved
use TDF instead of CNN dynamic filtering (DDPM) (ablation)MVSalNet · NLPRadaptive F-measure: 389M -> 83M parameters; 0.896 -> 0.901Improved
use learned fusion module instead of adding the saliency maps (ablation)MVSalNet · NLPRadaptive F-measure: 0.883 -> 0.901Improved
fuse into original view instead of supervising two synthesized maps separately (ablation)MVSalNet · NLPRadaptive F-measure: 0.896 -> 0.901Improved

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