SOTAVerified

Foreground Segmentation

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 84 papers

TitleStatusHype
FOCUS: Towards Universal Foreground SegmentationCode2
PartSTAD: 2D-to-3D Part Segmentation Task AdaptationCode2
Seg-R1: Segmentation Can Be Surprisingly Simple with Reinforcement LearningCode2
Explicit Visual Prompting for Low-Level Structure SegmentationsCode2
Explicit Visual Prompting for Universal Foreground SegmentationsCode2
Visual Prompting via Image InpaintingCode2
Exploring the Interactive Guidance for Unified and Effective Image MattingCode1
PraNet-V2: Dual-Supervised Reverse Attention for Medical Image SegmentationCode1
ZBS: Zero-shot Background Subtraction via Instance-level Background Modeling and Foreground SelectionCode1
Foreground Segmentation Using a Triplet Convolutional Neural Network for Multiscale Feature EncodingCode1
"What's This?" -- Learning to Segment Unknown Objects from Manipulation SequencesCode1
Autoencoder-based background reconstruction and foreground segmentation with background noise estimationCode1
E-InMeMo: Enhanced Prompting for Visual In-Context LearningCode1
A De-raining semantic segmentation network for real-time foreground segmentationCode1
Neural Head Reenactment with Latent Pose DescriptorsCode1
Instruct Me More! Random Prompting for Visual In-Context LearningCode1
Real-time Instance Segmentation with Discriminative Orientation MapsCode1
One-Shot Video Object SegmentationCode1
Semantic-guided Automatic Natural Image Matting with Trimap Generation Network and Light-weight Non-local Attention—0
Illumination-Aware Multi-Task GANs for Foreground Segmentation—0
Illumination Invariant Foreground Object Segmentation using ForeGANs—0
Image Decomposition Using a Robust Regression Approach—0
3D Shape Reconstruction from a Single 2D Image via 2D-3D Self-Consistency—0
IMProv: Inpainting-based Multimodal Prompting for Computer Vision Tasks—0
Joint Background Reconstruction and Foreground Segmentation via A Two-stage Convolutional Neural Network—0
Kernel Adaptive Convolution for Scene Text Detection via Distance Map Prediction—0
Learning Segmentation Masks with the Independence Prior—0
Learning Transferrable Knowledge for Semantic Segmentation with Deep Convolutional Neural Network—0
LIME: Live Intrinsic Material Estimation—0
Markerless Camera-to-Robot Pose Estimation via Self-supervised Sim-to-Real Transfer—0
Modelling depth for nonparametric foreground segmentation using RGBD devices—0
Monocular 3D Object Detection via Feature Domain Adaptation—0
MRI Breast tissue segmentation using nnU-Net for biomechanical modeling—0
MUSTAN: Multi-scale Temporal Context as Attention for Robust Video Foreground Segmentation—0
OneGAN: Simultaneous Unsupervised Learning of Conditional Image Generation, Foreground Segmentation, and Fine-Grained Clustering—0
On guiding video object segmentation—0
OpenIllumination: A Multi-Illumination Dataset for Inverse Rendering Evaluation on Real Objects—0
Optical flow-based branch segmentation for complex orchard environments—0
Performance Analysis of a Foreground Segmentation Neural Network Model—0
Person Count Localization in Videos From Noisy Foreground and Detections—0
Pixel Objectness—0
Pixel Objectness: Learning to Segment Generic Objects Automatically in Images and Videos—0
Improved Anomaly Detection in Crowded Scenes via Cell-based Analysis of Foreground Speed, Size and Texture—0
A Robust Pose Transformational GAN for Pose Guided Person Image Synthesis—0
A Robust Regression Approach for Background/Foreground Segmentation—0
Automatic Video Object Segmentation via Motion-Appearance-Stream Fusion and Instance-aware Segmentation—0
Background-Foreground Segmentation for Interior Sensing in Automotive Industry—0
Background Subtraction via Generalized Fused Lasso Foreground Modeling—0
Background Subtraction with Real-time Semantic Segmentation—0
BEVControl: Accurately Controlling Street-view Elements with Multi-perspective Consistency via BEV Sketch Layout—0
Show:102550
← PrevPage 1 of 2Next →

No leaderboard results yet.