CzechLynx: A Dataset for Individual Identification and Pose Estimation of the Eurasian Lynx

2025/06/05 by Lukas Picek, Lukáš Picek, Picek, Lukas +41 · 1 voice
Biochemistry, Genetics and Molecular Biology · Environmental Science · Psychology · #Human-Animal Interaction Studies #Primate Behavior and Ecology #Wildlife Ecology and Conservation #cs.AI #cs.CV

paper · pdf · doi:10.48550/arxiv.2506.04931

openalex publication_date 2025/06/05 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We introduce CzechLynx, the first large-scale, open-access dataset for individual identification, pose estimation, and instance segmentation of the Eurasian lynx (Lynx lynx). CzechLynx contains 39,760 camera trap images annotated with segmentation masks, identity labels, and 20-point skeletons and covers 319 unique individuals across 15 years of systematic monitoring in two geographically distinct regions: southwest Bohemia and the Western Carpathians. In addition to the real camera trap data, we provide a large complementary set of photorealistic synthetic images and a Unity-based generation pipeline with diffusion-based text-to-texture modeling, capable of producing arbitrarily large amounts of synthetic data spanning diverse environments, poses, and coat-pattern variations. To enable systematic testing across realistic ecological scenarios, we define three complementary evaluation protocols: (i) geo-aware, (ii) time-aware open-set, and (iii) time-aware closed-set, covering cross-regional and long-term monitoring settings. With the provided resources, CzechLynx offers a unique, flexible benchmark for robust evaluation of computer vision and machine learning models across realistic ecological scenarios.

Citations

• Animal Identification with Independent Foreground and Background Modeling
• Paint-it: Text-to-Texture Synthesis via Deep Convolutional Texture Map Optimization and Physically-Based Rendering
• WildlifeDatasets: An open-source toolkit for animal re-identification
• Synthetic Data from Diffusion Models Improves ImageNet Classification
• Micrograph segmentations for DDEVD
• Segment Anything
• Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation
• Text2Tex: Text-driven Texture Synthesis via Diffusion Models
• Prior-Aware Synthetic Data to the Rescue: Animal Pose Estimation with Very Limited Real Data
• High-Resolution Image Synthesis with Latent Diffusion Models
• High-Resolution Image Synthesis with Latent Diffusion Models
• SyDog: A Synthetic Dog Dataset for Improved 2D Pose Estimation
• Deep High-Resolution Representation Learning for Visual Recognition
• Deep High-Resolution Representation Learning for Visual Recognition
• Cross-Domain Adaptation for Animal Pose Estimation
• Efficient Pipeline for Camera Trap Image Review
• Past, Present, and Future Approaches Using Computer Vision for Animal Re-Identification from Camera Trap Data
• Where Is My Puppy? Retrieving Lost Dogs by Facial Features

Discussions

• CzechLynx: A Dataset for Individual Identification and Pose Estimation of the Eurasian Lynx Lukáš Picek et 16 al. tl;dr; pose estimation, but for Lynx. 39k labeled images from 2009 to 2025. Synthetic [bsky, 6 points, 0 comments]

Related

• Integrating animal tracking datasets at a continental scale for mapping Eurasian lynx habitat
• Citizen Science and Machine Learning for Research and Nature Conservation: The Case of Eurasian Lynx, Free-ranging Rodents and Insects
• Hunter‐engaged monitoring of the Eurasian lynx during the reinforcement process
• CNN‐Based Flank Predictor for Quadruped Animal Species
• A decade of monitoring the critically endangered Balkan lynx in its core area: Insights from spatial capture recapture models