This review thoroughly examines the role of semantically-aware Neural Radiance Fields
(NeRFs) in visual scene understanding, covering an analysis of over 250 scholarly papers. It …

Neural volumetric representations have shown the potential that Multi-layer Perceptrons
(MLPs) can be optimized with multi-view calibrated images to represent scene geometry and …

Implicit neural representations have shown powerful capacity in modeling real-world 3D
scenes, offering superior performance in novel view synthesis. In this paper, we target a …

The recent success of transformer-based image generative models in object-centric learning
highlights the importance of powerful image generators for handling complex scenes …

The binding problem in human cognition, concerning how the brain represents and
connects objects within a fixed network of neural connections, remains a subject of intense …

We present radiance field propagation (RFP), a novel approach to segmenting objects in 3D
during reconstruction given only unlabeled multi-view images of a scene. RFP is derived …

Object-centric learning aims to represent visual data with a set of object entities (aka slots),
providing structured representations that enable systematic generalization. Leveraging …

A fully automated object reconstruction pipeline is crucial for digital content creation. While
the area of 3D reconstruction has witnessed profound developments, the removal of …

Learned visual dynamics models have proven effective for robotic manipulation tasks. Yet, it
remains unclear how best to represent scenes involving multi-object interactions. Current …

The ability to distill object-centric abstractions from intricate visual scenes underpins human-
level generalization. Despite the significant progress in object-centric learning methods …