A new pipeline using canonical LoRAs for view synthesis, deformable 3D Gaussian splatting anchored on D-SMAL, and generative repair to produce animatable 3D dogs from single wild images without 3D supervision.
DogMo: A Large-Scale Multi-View RGB-D Dataset for 4D Canine Motion Recovery.arXiv preprint arXiv:2510.24117, 2025
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Uni-Mo generates 7,488 language-annotated quadruped motions via LLM prompts and video diffusion, lifts them to 3D trajectories, and trains policies achieving 96.7% real-robot success on 392 sampled motions.
citing papers explorer
No citing papers match the current filters.