BEAST3D learns viewpoint-invariant 3D features from calibrated multi-view animal videos via Gaussian splatting for novel view synthesis, pose estimation, and neural encoding across four species.
Domain-adaptive pretraining improves primate behavior recognition.arXiv preprint arXiv:2509.12193, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
q-bio.NC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
BEAST3D: Animal behavioral analysis and neural encoding from multi-view video via Gaussian splatting
BEAST3D learns viewpoint-invariant 3D features from calibrated multi-view animal videos via Gaussian splatting for novel view synthesis, pose estimation, and neural encoding across four species.