2 papers
cs.CV2025
Learning Dynamic Scene Reconstruction with Sinusoidal Geometric Priors
Tian Guo, Hui Yuan, Philip Xu +1
We propose SirenPose, a novel loss function that combines the periodic activation properties of sinusoidal representation networks with geometric priors derived from keypoint struc…
cs.CV2025
A Three-Level Alignment Framework for Large-Scale 3D Retrieval and Controlled 4D Generation
Philip Xu
We introduce Uni4D, a unified framework for large scale open vocabulary 3D retrieval and controlled 4D generation based on structured three level alignment across text, 3D models,…