Tag
Holo4D is a video reshooting framework that uses reconstructed 3D trajectory scaffolds to guide a pretrained video diffusion model for novel-view video synthesis, preserving scene geometry and motion while generatively completing unseen regions without retraining the generator.
3D HAMSTER enhances robot manipulation by using a vision-language model with depth encoding to generate 3D trajectories for point cloud-based control, outperforming 2D-guided baselines.