This paper reviews the current state of the art in artificial intelligence (AI) technologies and
applications in the context of the creative industries. A brief background of AI, and …

Representing and rendering dynamic scenes has been an important but challenging task.
Especially to accurately model complex motions high efficiency is usually hard to guarantee …

We present a diffusion-based model for 3D-aware generative novel view synthesis from as
few as a single input image. Our model samples from the distribution of possible renderings …

Neural radiance fields enable state-of-the-art photorealistic view synthesis. However,
existing radiance field representations are either too compute-intensive for real-time …

Abstract Neural Radiance Fields (NeRFs) have demonstrated amazing ability to synthesize
images of 3D scenes from novel views. However, they rely upon specialized volumetric …

We address the problem of synthesizing novel views from a monocular video depicting a
complex dynamic scene. State-of-the-art methods based on temporally varying Neural …

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 …

We present a super-fast convergence approach to reconstructing the per-scene radiance
field from a set of images that capture the scene with known poses. This task, which is often …

Being data-driven is one of the most iconic properties of deep learning algorithms. The birth
of ImageNet drives a remarkable trend of" learning from large-scale data" in computer vision …

Dynamic radiance field reconstruction methods aim to model the time-varying structure and
appearance of a dynamic scene. Existing methods, however, assume that accurate camera …