
Qianqian Wang
@QianqianWang5 • 4,616 subscribers
Assistant Professor at Harvard University and Kempner Institute
Videos

Most multi-view reconstruction models need full supervision. We show they can self-improve without any ground truth labels. Introducing SelfEvo: Self-Improving 4D Perception via Self-Distillation. Up to +36.5% in video depth, +20.1% in camera estimation, zero annotation.
Qianqian Wang26,644 görüntüleme • 5 ay önce
Daha fazla içerik yok.