SS3D pretrains an end-to-end feed-forward 3D estimator on filtered YouTube-8M videos via SfM self-supervision, MVS filtering, and expert distillation, delivering stronger zero-shot transfer and fine-tuning than prior self-supervised baselines.
arXiv preprint arXiv:2106.03505 (2021)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
baseline 1
citation-polarity summary
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
CoopNet improves co-training of depth, odometry, and optical flow networks via a hybrid loss that rebalances gradients by modeling photometric error disagreements to identify and ignore moving objects.
citing papers explorer
-
SS3D: End2End Self-Supervised 3D from Web Videos
SS3D pretrains an end-to-end feed-forward 3D estimator on filtered YouTube-8M videos via SfM self-supervision, MVS filtering, and expert distillation, delivering stronger zero-shot transfer and fine-tuning than prior self-supervised baselines.
-
Rebalancing gradient to improve self-supervised co-training of depth, odometry and optical flow predictions
CoopNet improves co-training of depth, odometry, and optical flow networks via a hybrid loss that rebalances gradients by modeling photometric error disagreements to identify and ignore moving objects.