Deep Foundation Model
A model pretrained on large-scale depth data that can estimate high-quality depth maps from monocular images or videos, with strong generalization ability in in-the-wild scenarios.
Timeline (last 90 days)
Depth foundation models refer to models pretrained on large-scale depth data that can estimate high-quality depth maps from monocular images or video.
In DePoser, the depth foundation model is used to generate 3D geometric supervision signals for local data, automatically producing pseudo-annotations of human meshes combined with human priors or 2D keypoints.
DePoser relies on depth foundation models for annotation, so the quality ceiling of its pseudo-ground truth is determined by the depth foundation model, and errors propagate into subsequent fine-tuning.
All Facts (3)
Depth foundation models refer to models pretrained on large-scale depth data that can estimate high-quality depth maps from monocular images or video.
50%UnverifiedIn DePoser, the depth foundation model is used to generate 3D geometric supervision signals for local data, automatically producing pseudo-annotations of human meshes combined with human priors or 2D keypoints.
50%UnverifiedDePoser relies on depth foundation models for annotation, so the quality ceiling of its pseudo-ground truth is determined by the depth foundation model, and errors propagate into subsequent fine-tuning.
50%