Yoni Kasten

Latest

• GSVisLoc: Generalizable Visual Localization for Gaussian Splatting Scene Representations
• Motion by Queries: Identity-Motion Trade-offs in Text-to-Video Generation
• TriTex: Learning Texture from a Single Mesh via Triplane Semantic Features
• Robust Equivariant Multiview Structure from Motion
• Fast Encoder-Based 3D from Casual Videos via Point Track Processing
• Point-Cloud Completion with Pretrained Text-to-image Diffusion Models
• CALM: Conditional Adversarial Latent Models for Directable Virtual Characters