Work with @mert-o.bsky.social and @visionbernie.bsky.social at @cogcovi.bsky.social @unifau.bsky.social, where we have two year fully-funded postdoc positions open on related topics. (5/5)

We handle occlusions by employing amodal completion for each instance. The completed instance is then reconstructed using existing models that perform well for single objects. However, we first address the object crop domain shift (e.g., focal length) through reprojection. (4/5)

First, we parse the image of the scene by identifying the composing entities and estimating the depth and camera parameters. Each instance is then processed individually. The unprojected depth serves as a layout reference for composing the scene in 3D space. (3/5)

Most single-image scene-level reconstruction methods require 3D supervised end-to-end training and suffer from poor generalization capabilities. We propose a modular approach where each component performs well by focusing on specific tasks that are easier to supervise. (2/5)