Dngaussian: Optimizing sparse-view 3d gaussian radiance fields with global-local depth normalization
Radiance fields have demonstrated impressive performance in synthesizing novel views
from sparse input views yet prevailing methods suffer from high training costs and slow …
from sparse input views yet prevailing methods suffer from high training costs and slow …
CoR-GS: sparse-view 3D Gaussian splatting via co-regularization
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 …
to represent a scene. With sparse training views, 3DGS easily suffers from overfitting …
G3r: Gradient guided generalizable reconstruction
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 …
simulation. Existing neural rendering approaches (eg, NeRF, 3DGS) have achieved realistic …
AIM 2024 sparse neural rendering challenge: Dataset and benchmark
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 …
breakthroughs in a variety of 2D and 3D tasks, eg novel view synthesis, 3D reconstruction …
Entangled View-Epipolar Information Aggregation for Generalizable Neural Radiance Fields
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 …
need for scene-specific retraining in vanilla NeRF. A critical enabling factor in these …
SlotLifter: Slot-guided Feature Lifting for Learning Object-centric Radiance Fields
The ability to distill object-centric abstractions from intricate visual scenes underpins human-
level generalization. Despite the significant progress in object-centric learning methods …
level generalization. Despite the significant progress in object-centric learning methods …
Caesarnerf: Calibrated semantic representation for few-shot generalizable neural rendering
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 …
(NeRF), often due to the lack of a holistic understanding in pixel-level rendering. We …
Lift3D: Zero-Shot Lifting of Any 2D Vision Model to 3D
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 …
semantic segmentation style transfer or scene editing enabled by large-scale 2D image …
NeRF as Pretraining at Scale: Generalizable 3D-Aware Semantic Representation Learning from View Prediction
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 …
several source views of unseen scenes are gaining prominence in the NeRF field …
Lift3D: Zero-Shot Lifting of Any 2D Vision Model to 3D
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 …
as semantic segmentation, style transfer or scene editing, enabled by large-scale 2D image …