Emerging neural radiance fields (NeRF) are a promising scene representation for computer
graphics, enabling high-quality 3D reconstruction and novel view synthesis from image …

Although an object may appear in numerous contexts, we often describe it in a limited
number of ways. Language allows us to abstract away visual variation to represent and …

Recent works on generalizable NeRFs have shown promising results on novel view
synthesis from single or few images. However, such models have rarely been applied on …

We consider the visual disambiguation task of determining whether a pair of visually similar
images depict the same or distinct 3D surfaces (eg, the same or opposite sides of a …

Scene-level novel view synthesis (NVS) is fundamental to many vision and graphics
applications. Recently, pose-conditioned diffusion models have led to significant progress …

We introduce PartGlot, a neural framework and associated architectures for learning
semantic part segmentation of 3D shape geometry, based solely on part referential …

Numerous digital media repositories have been set up during recent decades, each
containing plenty of data about historic cityscapes. In contrast, digital 3D reconstructions of …

Recent work on dense captioning and visual grounding in 3D have achieved impressive
results. Despite developments in both areas, the limited amount of available 3D vision …

Internet image collections containing photos captured by crowds of photographers show
promise for enabling digital exploration of large‐scale tourist landmarks. However, prior …

Text-to-shape retrieval is an increasingly relevant problem with the growth of 3D shape data.
Recent work on contrastive losses for learning joint embeddings over multimodal data has …