Recent history has seen a tremendous growth of work exploring implicit representations of
geometry and radiance, popularized through Neural Radiance Fields (NeRF). Such works …

Existing image editing tools, while powerful, typically disregard the underlying 3D geometry
from which the image is projected. As a result, edits made using these tools may become …

This review thoroughly examines the role of semantically-aware Neural Radiance Fields
(NeRFs) in visual scene understanding, covering an analysis of over 250 scholarly papers. It …

Partial convolution weights convolutions with binary masks and renormalizes on valid pixels.
It was originally proposed for image inpainting task because a corrupted image processed …

Abstract Neural Radiance Fields (NeRF) coupled with GANs represent a promising direction
in the area of 3D reconstruction from a single view, owing to their ability to efficiently model …

Abstract Generative Adversarial Networks (GANs) produce impressive results on
unconditional image generation when powered with large-scale image datasets. Yet …

In this paper, we address the problem of texture representation for 3D shapes for the
challenging and underexplored tasks of texture transfer and synthesis. Previous works either …

ABSTRACT Three-dimensional (3D) point clouds (PCs) and meshes have increasingly
become available and indispensable for diversified applications in work and life. In addition …

This paper presents TexRO, a novel method for generating delicate textures of a known 3D
mesh by optimizing its UV texture. The key contributions are two-fold. We propose an …

This paper presents a method to reconstruct high-quality textured 3D models from single
images. Current methods rely on datasets with expensive annotations; multi-view images …