Laser: Latent Set Representations for 3D Generative Modeling
NeRF provides unparalleled fidelity of novel view synthesis: rendering a 3D scene from an arbitrary viewpoint. NeRF requires training on a large number of views that fully cover a scene, which limits its applicability. While these issues can be addressed by learning a prior over scenes in various fo...
Saved in:
Main Authors | , , , , , , , , |
---|---|
Format | Journal Article |
Language | English |
Published |
13.01.2023
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | NeRF provides unparalleled fidelity of novel view synthesis: rendering a 3D
scene from an arbitrary viewpoint. NeRF requires training on a large number of
views that fully cover a scene, which limits its applicability. While these
issues can be addressed by learning a prior over scenes in various forms,
previous approaches have been either applied to overly simple scenes or
struggling to render unobserved parts. We introduce Laser-NV: a generative
model which achieves high modelling capacity, and which is based on a
set-valued latent representation modelled by normalizing flows. Similarly to
previous amortized approaches, Laser-NV learns structure from multiple scenes
and is capable of fast, feed-forward inference from few views. To encourage
higher rendering fidelity and consistency with observed views, Laser-NV further
incorporates a geometry-informed attention mechanism over the observed views.
Laser-NV further produces diverse and plausible completions of occluded parts
of a scene while remaining consistent with observations. Laser-NV shows
state-of-the-art novel-view synthesis quality when evaluated on ShapeNet and on
a novel simulated City dataset, which features high uncertainty in the
unobserved regions of the scene. |
---|---|
DOI: | 10.48550/arxiv.2301.05747 |