paper-with-me

Papers Object Segmentation

“Object Segmentation” 태그가 달린 논문 86편 · 필터 해제

Filtering-out poor-quality images for data preparation

2026-07-14 · Roopdeep Kaur, Gour Karmakar, Muhammad Imran arxiv

Filtering noise is a fundamental part of data preparation that enhances image quality for applications such as object segmentation, detection, and recognition. Various noise reduction techniques are proposed in the liter…

Image Quality AssessmentTraffic Sign RecognitionObject SegmentationAutonomous Vehicles

Evidence-Backed Video Question Answering

2026-07-13 · Shijie Wang, Honglu Zhou, Ziyang Wang, Ran Xu 외 hf

Current Video Large Language Models (Video LLMs) excel in question answering (QA) but largely operate as black boxes, providing textual answers without verifiable visual grounding. Existing explainability efforts rely on…

Video Question AnsweringObject SegmentationVisual Grounding

A Large-Scale Dataset and a New Method for RemoteSensing Traffic Object Segmentation

2026-07-04 · Zhigang Yang, Huiguang Yao, Linmao Tian, Qiang Li 외 arxiv

Remote sensing imagery plays a crucial role in evaluating regional transportation capacity. However, existing segmentation datasets often lack diversity in object categories and scenes, limiting the ability of models to …

Object Segmentation

SUMO: Segment and Track Any Motion with Nonlinear State Space Models

2026-06-29 · Kexin Tian, Sixu Li, Keshu Wu, Yang Zhou 외 arxiv

Visual Object Tracking (VOT) and Moving Object Segmentation (MOS) are two fundamental tasks in computer vision that involve both spatial and temporal object dynamics. Existing methods rely predominantly on visual cues an…

Visual Object TrackingObject Segmentation

DCSNet: Multiscale Feature Aggregation for Small Medical Object Segmentation with Detection-guided Hierarchical Cropping

2026-06-24 · Shanfeng Zhang, Bo Gou, Yue Cao, Lei Zhang 외 arxiv

Small object segmentation in medical imaging is primarily hindered by class imbalance and inherent boundary complexity. Consequently, conventional global networks frequently fail to detect sparse targets or suffer from s…

Object SegmentationLesion Segmentation

From Reconstruction to Decision: A Post-Encoder Plug-in Adapter for Curvilinear Segmentation

2026-06-22 · Qin Lei, Jiang Zhong, Xin Xiao, Yuming Yang 외 arxiv

Curvilinear object segmentation, including vessels and cracks, is challenging due to extreme spatial sparsity and topological fragility, where small local errors can cause severe structural disconnections. Meanwhile, mod…

Object Segmentation

ELDiff: When Evidential Learning Meets Text-to-Image Diffusion

2026-06-18 · Qingtao Pan, Kai Ye, Zhihao Dou, Bing Ji 외 arxiv

In multi-object text-to-image (T2I) diffusion, ensuring semantic consistency between textual prompts and generated visual content is crucial for image synthesis. However, such consistency constraint is often underemphasi…

Object Segmentation

DIMOS: Disentangling Instance-level Moving Object Segmentation

2026-06-11 · Hongxiang Huang, Hongwei Ren, Xiaopeng Lin, Yulong Huang 외 arxiv

Moving instance segmentation (MIS) attracts increasing attention due to its broad applications in traffic surveillance, autonomous driving, and animal tracking. Event cameras record asynchronous brightness changes, provi…

Instance SegmentationObject SegmentationAutonomous Driving

WorldOlympiad: Can Your World Model Survive a Triathlon?

2026-06-09 · Yuke Zhao, Wangbo Zhao, Weijie Wang, Zeyu Zhang 외 arxiv

We introduce WorldOlympiad, a benchmark for diagnosing video-based world models across physical faithfulness, geometric consistency, and interaction fidelity. While existing benchmarks often focus on visual quality, sema…

Object Segmentation

A Trajectory-Driven Spatio-Temporal Refinement Solution for CVPR 2026 8th UG2+ Challenge Track 3: DOST

2026-05-30 · Hongzhen Li, Miao Yu, Leilei Cao, Youwei Pan 외 arxiv

In this work, we present our solution for the 8th UG2+ Challenge (CVPR 2026) Track 3: Dynamic Object Segmentation in Turbulence (DOST). Our method is built upon the strong baseline framework Segment Any Motion (SegAnyMo)…

Object SegmentationDomain Adaptation

Turbulence-Robust Dynamic Object Segmentation with Multi-Signal Priors and SAM2 Refinement

2026-05-28 · Bolian Peng, Ying Tang, Xu Liu, Long Sun 외 arxiv

This technical report presents our solution for the CVPR 2026 UG2+ Challenge Track 3: Dynamic Object Segmentation in Turbulence (DOST). We design a training-free multi-signal segmentation pipeline that combines pretraine…

Object Segmentation

TrackRef3D: Multi-View Consistent Track-then-Label for Open-World Referring Segmentation in 3D Gaussian Splatting

2026-05-26 · Yuyang Tan, Renhe Zhang, Hang Zhang, Ao Li 외 arxiv

Referring 3D Gaussian Splatting (R3DGS), which utilizes natural language for 3D object segmentation, has emerged as a crucial capability for embodied AI. However, existing methods typically rely on expensive per-scene ma…

Object Segmentation

FoundObj: Self-supervised Foundation Models as Rewards for Label-free 3D Object Segmentation

2026-05-26 · Zihui Zhang, Zhixuan Sun, Yafei Yang, Jinxi Li 외 arxiv

We address the challenging task of 3D object segmentation in complex scene point clouds without relying on any scene-level human annotations during training. Existing methods are typically constrained to identifying simp…

Reinforcement LearningObject SegmentationPoint Clouds

RIDE: Retinex-Informed Decoupling for Exposing Concealed Objects

2026-05-14 · Chunming He, Rihan Zhang, Dingming Zhang, Chengyu Fang 외 arxiv

Concealed Object Segmentation (COS) encompasses a family of dense-prediction tasks, including camouflaged object detection, polyp segmentation, transparent object detection, and industrial defect inspection, where target…

Object SegmentationPolyp SegmentationObject Detection

EvObj: Learning Evolving Object-centric Representations for 3D Instance Segmentation without Scene Supervision

2026-05-13 · Jiahao Chen, Zihui Zhang, Yafei Yang, Jinxi Li 외 arxiv

We introduce EvObj for unsupervised 3D instance segmentation that bridges the geometric domain gap between synthetic pretraining data and real-world point clouds. Current methods suffer from structural discrepancies when…

3D Instance SegmentationObject SegmentationPoint Clouds

LEXI-SG: Monocular 3D Scene Graph Mapping with Room-Guided Feed-Forward Reconstruction

2026-05-13 · Christina Kassab, Hyeonjae Gil, Matías Mattamala, Ayoung Kim 외 arxiv

Scene graphs are becoming a standard representation for robot navigation, providing hierarchical geometric and semantic scene understanding. However, most scene graph mapping methods rely on depth cameras or LiDAR sensor…

Object SegmentationScene UnderstandingRobot Navigation

Premover: Fast Vision-Language-Action Control by Acting Before Instructions Are Complete

2026-05-12 · Joonha Park, Jiseung Jeong, Taesik Gong arxiv

Vision-Language-Action (VLA) policies are typically evaluated as if the user had finished typing or speaking before the robot begins acting. In real deployment, however, users take several seconds to enter a request, lea…

Object Segmentation

FlowDIS: Language-Guided Dichotomous Image Segmentation with Flow Matching

2026-05-06 · Andranik Sargsyan, Shant Navasardyan arxiv

Accurate image segmentation is essential for modern computer vision applications such as image editing, autonomous driving, and medical image analysis. In recent years, Dichotomous Image Segmentation (DIS) has become a s…

Dichotomous Image SegmentationObject SegmentationAutonomous DrivingImage Editing

UnGAP: Uncertainty-Guided Affine Prompting for Real-Time Crack Segmentation

2026-05-04 · Conghui Li, Huanyu He, Xin Wang, Weiyao Lin 외 arxiv

Real-time crack segmentation is vital for structural health monitoring but is plagued by aleatoric uncertainties arising from varying lighting, blur, and texture ambiguity. Current uncertainty-aware approaches typically …

Object SegmentationCrack Segmentation

Report of the 5th PVUW Challenge: Towards More Diverse Modalities in Pixel-Level Understanding

2026-04-28 · Chang Liu, Henghui Ding, Nikhila Ravi, Yunchao Wei 외 arxiv

This report summarizes the objectives, datasets, and top-performing methodologies of the 2026 Pixel-level Video Understanding in the Wild (PVUW) Challenge, hosted at CVPR 2026, which evaluates state-of-the-art models und…

Object Segmentation
1–20 / 86 다음 →