Radiance fields have demonstrated impressive performance in synthesizing novel views
from sparse input views yet prevailing methods suffer from high training costs and slow …

Abstract 3D Gaussian Splatting (3DGS) creates a radiance field consisting of 3D Gaussians
to represent a scene. With sparse training views, 3DGS easily suffers from overfitting …

Large scale 3D scene reconstruction is important for applications such as virtual reality and
simulation. Existing neural rendering approaches (eg, NeRF, 3DGS) have achieved realistic …

Recent developments in differentiable and neural rendering have made impressive
breakthroughs in a variety of 2D and 3D tasks, eg novel view synthesis, 3D reconstruction …

Generalizable NeRF can directly synthesize novel views across new scenes eliminating the
need for scene-specific retraining in vanilla NeRF. A critical enabling factor in these …

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

Generalizability and few-shot learning are key challenges in Neural Radiance Fields
(NeRF), often due to the lack of a holistic understanding in pixel-level rendering. We …

In recent years there has been an explosion of 2D vision models for numerous tasks such as
semantic segmentation style transfer or scene editing enabled by large-scale 2D image …

Cross-scene generalizable NeRF models which could directly synthesize novel views using
several source views of unseen scenes are gaining prominence in the NeRF field …

In recent years, there has been an explosion of 2D vision models for numerous tasks such
as semantic segmentation, style transfer or scene editing, enabled by large-scale 2D image …