3 datasets found

Alpha-CLIP is an enhanced version of CLIP with an auxiliary alpha channel to suggest attentive regions and fine-tuned with constructed millions of RGBA region-text pairs.

The Deitke dataset contains 30 objects chosen by SyncDreamer [17] and rendered 16 views with uniformly distributed camera poses and environment lighting for each object.

The Objaverse dataset contains around 800k 3D objects. After adopting simple filter leveraging CLIP [27] to remove the objects whose rendered images are not relevant to its...