We introduce SceneScript, a method that directly produces full scene models as a sequence
of structured language commands using an autoregressive, token-based approach. Our …

Semantic 2D maps are commonly used by humans and machines for navigation purposes,
whether it's walking or driving. However, these maps have limitations: they lack detail, often …

We present PARQ-a multi-view 3D object detector with transformer and pixel-aligned
recurrent queries. Unlike previous works that use learnable features or only encode 3D point …

The success of the transformer architecture in natural language processing has recently
triggered attention in the computer vision field. The transformer has been used as a …

We propose a method for annotating videos of complex multi-object scenes with a globally-
consistent 3D representation of the objects. We annotate each object with a CAD model from …

Orthodontic treatment monitoring involves using current images and previous 3D models to
estimate the relative position of individual teeth before and after orthodontic treatment. This …

The image matching field has been witnessing a continuous emergence of novel learnable
feature matching techniques with ever-improving performance on conventional benchmarks …

We propose an end-to-end trainable, cross-category method for reconstructing multiple man-
made articulated objects from a single RGBD image, focusing on part-level shape …

Instance shape reconstruction from a 3D scene involves recovering the full geometries of
multiple objects at the semantic instance level. Many methods leverage data-driven learning …

Achieving precise 6 degrees of freedom (6D) pose estimation of rigid objects from color
images is a critical challenge with wide-ranging applications in robotics and close-contact …