Cover Image

ClimaOoD: Improving Anomaly Segmentation via Physically Realistic Synthetic Data

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Yuxing, Li, Zheng, Liang, Huanhuan, Zhang, Ji, Sun, Zeyu, Liu, Yong
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

OoDDINO:A Multi-level Framework for Anomaly Segmentation on Complex Road Scenes
by: Liu, Yuxing, et al.
Published: (2025)

OoDIS: Anomaly Instance Segmentation and Detection Benchmark
by: Nekrasov, Alexey, et al.
Published: (2024)

RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detection
by: Zhang, Ximiao, et al.
Published: (2024)

Safe and Robust Watermark Injection with a Single OoD Image
by: Yu, Shuyang, et al.
Published: (2023)

Objectomaly: Objectness-Aware Refinement for OoD Segmentation with Structural Consistency and Boundary Precision
by: Song, Jeonghoon, et al.
Published: (2025)

HOIDiffusion: Generating Realistic 3D Hand-Object Interaction Data
by: Zhang, Mengqi, et al.
Published: (2024)

Logit Disagreement: OoD Detection with Bayesian Neural Networks
by: Raina, Kevin
Published: (2025)

FrOoDo: Framework for Out-of-Distribution Detection
by: Stieber, Jonathan, et al.
Published: (2022)

BAM: Box Abstraction Monitors for Real-time OoD Detection in Object Detection
by: Wu, Changshun, et al.
Published: (2024)

SoftPatch+: Fully Unsupervised Anomaly Classification and Segmentation
by: Wang, Chengjie, et al.
Published: (2024)

Reflexive Guidance: Improving OoDD in Vision-Language Models via Self-Guided Image-Adaptive Concept Generation
by: Kim, Jihyo, et al.
Published: (2024)

A Conditional Generative Framework for Synthetic Data Augmentation in Segmenting Thin and Elongated Structures in Biological Images
by: Liu, Yi, et al.
Published: (2025)

Synthesis4AD: Synthetic Anomalies are All You Need for 3D Anomaly Detection
by: Sun, Yihan, et al.
Published: (2026)

AnomalyPainter: Vision-Language-Diffusion Synergy for Zero-Shot Realistic and Diverse Industrial Anomaly Synthesis
by: Lai, Zhangyu, et al.
Published: (2025)

Enhanced OoD Detection through Cross-Modal Alignment of Multi-Modal Representations
by: Kim, Jeonghyeon, et al.
Published: (2025)

SNN-Driven Multimodal Human Action Recognition via Sparse Spatial-Temporal Data Fusion
by: Zheng, Naichuan, et al.
Published: (2025)

Scaling Tumor Segmentation: Best Lessons from Real and Synthetic Data
by: Chen, Qi, et al.
Published: (2025)

Self-Supervised Likelihood Estimation with Energy Guidance for Anomaly Segmentation in Urban Scenes
by: Tu, Yuanpeng, et al.
Published: (2023)

R3ST: A Synthetic 3D Dataset With Realistic Trajectories
by: Teglia, Simone, et al.
Published: (2025)

Effective Training Data Synthesis for Improving MLLM Chart Understanding
by: Yang, Yuwei, et al.
Published: (2025)

Zero Shot Domain Adaptive Semantic Segmentation by Synthetic Data Generation and Progressive Adaptation
by: Luo, Jun, et al.
Published: (2025)

What Makes Synthetic Data Effective in Image Segmentation
by: Zhang, Jinjin, et al.
Published: (2026)

DMP-3DAD: Cross-Category 3D Anomaly Detection via Realistic Depth Map Projection with Few Normal Samples
by: Wang, Zi, et al.
Published: (2026)

Learning Implicit Features with Flow Infused Attention for Realistic Virtual Try-On
by: Zhang, Delong, et al.
Published: (2024)

Improved Multi-Task Brain Tumour Segmentation with Synthetic Data Augmentation
by: Ferreira, André, et al.
Published: (2024)

DVIS-DAQ: Improving Video Segmentation via Dynamic Anchor Queries
by: Zhou, Yikang, et al.
Published: (2024)

Pre-training with 3D Synthetic Data: Learning 3D Point Cloud Instance Segmentation from 3D Synthetic Scenes
by: Otsuka, Daichi, et al.
Published: (2025)

Neural Network Meta Classifier: Improving the Reliability of Anomaly Segmentation
by: Runtas, Jurica, et al.
Published: (2024)

3D-GRES: Generalized 3D Referring Expression Segmentation
by: Wu, Changli, et al.
Published: (2024)

MIRAGE: Model-agnostic Industrial Realistic Anomaly Generation and Evaluation for Visual Anomaly Detection
by: Hu, Jinwei, et al.
Published: (2026)

Segment Any Anomaly without Training via Hybrid Prompt Regularization
by: Cao, Yunkang, et al.
Published: (2023)

Auto-Generating Weak Labels for Real & Synthetic Data to Improve Label-Scarce Medical Image Segmentation
by: Deshpande, Tanvi, et al.
Published: (2024)

Towards Realistic Low-Light Image Enhancement via ISP Driven Data Modeling
by: Wang, Zhihua, et al.
Published: (2025)

Data Synthesis Improves 3D Myotube Instance Segmentation
by: Exler, David, et al.
Published: (2026)

GoodSAM++: Bridging Domain and Capacity Gaps via Segment Anything Model for Panoramic Semantic Segmentation
by: Zhang, Weiming, et al.
Published: (2024)

A Training-free Synthetic Data Selection Method for Semantic Segmentation
by: Tang, Hao, et al.
Published: (2025)

SimpleProc: Fully Procedural Synthetic Data from Simple Rules for Multi-View Stereo
by: Ma, Zeyu, et al.
Published: (2026)

CLIPS: An Enhanced CLIP Framework for Learning with Synthetic Captions
by: Liu, Yanqing, et al.
Published: (2024)

Hybrid Open-set Segmentation with Synthetic Negative Data
by: Grcić, Matej, et al.
Published: (2023)

Assessment of Using Synthetic Data in Brain Tumor Segmentation
by: Jahagirdar, Aditi, et al.
Published: (2025)