Midas v3. 1--a model zoo for robust monocular relative depth estimation
We release MiDaS v3. 1 for monocular depth estimation, offering a variety of new models
based on different encoder backbones. This release is motivated by the success of …
based on different encoder backbones. This release is motivated by the success of …
SC-NeRF: Self-Correcting Neural Radiance Field with Sparse Views
In recent studies, the generalization of neural radiance fields for novel view synthesis task
has been widely explored. However, existing methods are limited to objects and indoor …
has been widely explored. However, existing methods are limited to objects and indoor …
NeRF-SDP: Efficient Generalizable Neural Radiance Field with Scene Depth Perception
In recent years, neural radiance fields have exhibited impressive performance in novel view
synthesis. However, exploiting complex network structures to achieve generalizable NeRF …
synthesis. However, exploiting complex network structures to achieve generalizable NeRF …