In this paper, we present a novel neural scene rendering system, which learns an object-compositional neural radiance field and produces realistic rendering with editing capability for a clustered and real-world scene.
Convolutional Neural Networks (CNNs) have achieved remarkable success in various computer vision tasks but rely on tremendous computational cost.
Meanwhile, the learned instance discrimination capability from the discriminator is in turn exploited to encourage the generator for diverse generation.
Ranked #1 on Image Generation on FFHQ 256 x 256
Generative Adversarial Networks (GANs) have made great success in synthesizing high-quality images.
To this end, we propose Neural Body, a new human body representation which assumes that the learned neural representations at different frames share the same set of latent codes anchored to a deformable mesh, so that the observations across frames can be naturally integrated.
Generative Adversarial Networks (GANs) have recently advanced image synthesis by learning the underlying distribution of the observed data.
Visual tempo, which describes how fast an action goes, has shown its potential in supervised action recognition.
Previous works often capture the visual tempo through sampling raw videos at multiple rates and constructing an input-level frame pyramid, which usually requires a costly multi-branch network to handle.
Ranked #41 on Action Recognition on Something-Something V2
We present a new object representation, called Dense RepPoints, that utilizes a large set of points to describe an object at multiple levels, including both box level and pixel level.
To reduce memory footprint and run-time latency, techniques such as neural net-work pruning and binarization have been explored separately.
To reduce memory footprint and run-time latency, techniques such as neural network pruning and binarization have been explored separately.