DepthAnything3
The latest iteration in the DepthAnything series of monocular depth estimation foundation models. It is trained on large-scale, diverse image data and further improves multi-view consistency and depth accuracy.
Timeline (last 90 days)
LiFi's geometric branch adopts a reverse sampling algorithm and incorporates an uncertainty-aware geometric encoder that integrates the depth estimation capability of DepthAnything3.
DepthAnything3 is the latest iteration of the DepthAnything series, further optimized in multi-view consistency and depth accuracy.
All Facts (2)
LiFi's geometric branch adopts a reverse sampling algorithm and incorporates an uncertainty-aware geometric encoder that integrates the depth estimation capability of DepthAnything3.
50%UnverifiedDepthAnything3 is the latest iteration of the DepthAnything series, further optimized in multi-view consistency and depth accuracy.
50%