This paper presents a novel grid-based NeRF called F^ 2-NeRF (Fast-Free-NeRF) for novel
view synthesis, which enables arbitrary input camera trajectories and only costs a few …

Abstract Existing Human NeRF methods for reconstructing 3D humans typically rely on
multiple 2D images from multi-view cameras or monocular videos captured from fixed …

We present Generalizable NeRF Transformer (GNT), a transformer-based architecture that
reconstructs Neural Radiance Fields (NeRFs) and learns to renders novel views on the fly …

The success of the Neural Radiance Fields (NeRF) in novel view synthesis has inspired
researchers to propose neural implicit scene reconstruction. However, most existing neural …

Learning-based multi-view stereo (MVS) has by far centered around 3D convolution on cost
volumes. Due to the high computation and memory consumption of 3D CNN, the resolution …

We have witnessed significant progress in deep learning-based 3D vision ranging from
neural radiance field (NeRF) based 3D representation learning to applications in novel view …

We present Generalizable NeRF Transformer (GNT), a transformer-based architecture that
reconstructs Neural Radiance Fields (NeRFs) and learns to render novel views on the fly …

Abstract Neural Radiance Field (NeRF) has achieved superior performance for novel view
synthesis by modeling the scene with a Multi-Layer Perception (MLP) and a volume …

Rendering scenes observed in a monocular video from novel viewpoints is a challenging
problem. For static scenes the community has studied both scene-specific optimization …

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 …