Lattice AI Research

Research focus

Computer Vision (2)Multimodal Models (2)Architecture Design (Transformers, SSMs, MoE) (1)

Frequent co-authors

Peter Wonka (2)Aymen Mir (1)Riza Alp Guler (1)Gerard Pons-Moll (1)

Papers (2)

Mar 18, 2026

Mar 18, 2026·also D geometry and aspect ratio of the subject., D map that represents a distortion-free, Imperial, KAUST

AHOY! Animatable Humans under Occlusion from YouTube Videos with Gaussian Splatting and Video Diffusion Priors

Reconstructing complete, animatable 3D avatars from heavily occluded YouTube videos is now possible, thanks to a hallucination-as-supervision pipeline using diffusion models.

Aymen Mir, Riza Alp Guler, Xiangjun Tang +2

Computer Vision Multimodal Models

Mar 3, 2026

Any Resolution Any Geometry: From Multi-View To Multi-Patch

Key contribution not extracted.

Wenqing Cui, Mykola Lavreniuk, Ramzi Idoughi +2

Architecture Design (Transformers, SSMs, MoE)Computer Vision Multimodal Models

Search

Xiangjun Tang

Research focus

Frequent co-authors

Papers (2)