In this work, we investigate the problem of creating high-fidelity 3D content from only a single
image. This is inherently challenging: it essentially involves estimating the underlying 3D …

We present MVSNeRF, a novel neural rendering approach that can efficiently reconstruct
neural radiance fields for view synthesis. Unlike prior works on neural radiance fields that …

We present a practical and robust deep learning solution for capturing and rendering novel
views of complex real world scenes for virtual exploration. Previous approaches either …

The view synthesis problem--generating novel views of a scene from known imagery--has
garnered recent attention due in part to compelling applications in virtual and augmented …

Novel view synthesis from a single image has been a cornerstone problem for many Virtual
Reality applications that provide immersive experiences. However, most existing techniques …

We present NeX, a new approach to novel view synthesis based on enhancements of
multiplane image (MPI) that can reproduce next-level view-dependent effects--in real time …

We present an information-theoretic regularization technique for few-shot novel view
synthesis based on neural implicit representation. The proposed approach minimizes …

View synthesis allows for the generation of new views of a scene given one or more images.
This is challenging; it requires comprehensively understanding the 3D scene from images …

Classical light field rendering for novel view synthesis can accurately reproduce view-
dependent effects such as reflection, refraction, and translucency, but requires a dense view …

A recent strand of work in view synthesis uses deep learning to generate multiplane images--
a camera-centric, layered 3D representation--given two or more input images at known …