Hugging Face Daily Papers·· 2026-10-15AI score17
Gen4P: The Video Generator Is a 4D Perceiver
Gen4P: Video Generators are 4D Perceivers
AI briefing
Gen4P proposes a unified framework that can turn a pretrained video generator into a feed-forward 4D perceiver; without iterative denoising, a single encoder forward pass can process clean video latents and predict the required 4D attributes. Its on-demand querying supports flexible spatial sampling, continuous-time queries provide temporal flexibility, and a pretrained video-depth LoRA can be plugged in as a frozen geometric prior. Gen4P achieves SOTA or competitive performance on 3D point tracking, video depth, and camera pose estimation tasks.
Open original arxiv.org