Research map / 3D vision / Human pose estimation

Mouse Total Capture: A multi-view Dataset for 3D Motion and Expression Capture of Freely Moving Mouse

NeurIPS 2026 · 3D vision › Human pose estimation · approach: Transformer-based multi-view 3D pose

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Introduces Mouse Total Capture, a multi-view dataset for simultaneous 3D whole-body motion and facial expression capture of freely moving mice.

Problem

Existing mouse capture work covers either body pose of freely moving mice or facial expression under head-fixed conditions; no dataset supports joint whole-body motion and expression capture in freely moving mice.

Approach

A multi-view capture dataset that records whole-body motion and facial expression together for freely moving mice, filling the gap between body-pose and head-fixed face datasets.

Closest papers by meaning

• Pose Splatter: A 3D Gaussian Splatting Model for Quantifying Animal Pose and Appearance (NeurIPS 2025 · similarity 0.87)
• BEAST3D: animal behavioral analysis and neural encoding from multi-view video via Gaussian splatting (NeurIPS 2026 · similarity 0.86)
• Retrospective for the Dynamic Sensorium Competition for predicting large-scale mouse primary visual cortex activity from videos (NeurIPS 2024 · similarity 0.85)
• Animal-Bench: Benchmarking Multimodal Video Models for Animal-centric Video Understanding (NeurIPS 2024 · similarity 0.83)
• Inpainting the Neural Picture: Inferring Unrecorded Brain Area Dynamics from Multi-Animal Datasets (NeurIPS 2025 · similarity 0.83)
• The PanAf-FGBG Dataset: Understanding the Impact of Backgrounds in Wildlife Behaviour Recognition (CVPR 2025 · similarity 0.83)