Multi-view stereo infers the 3D geometry from a set of images captured from several known
positions and viewpoints. It is one of the most important components of 3D reconstruction …

State-of-the-art automated image orientation (Structure from Motion) and dense image
matching (Multiple View Stereo) methods commonly used to produce 3D information from …

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 …

This paper addresses the challenge of reconstructing 3D indoor scenes from multi-view
images. Many previous works have shown impressive reconstruction results on textured …

We present a novel framework named NeuralRecon for real-time 3D scene reconstruction
from a monocular video. Unlike previous methods that estimate single-view depth maps …

We present PatchmatchNet, a novel and learnable cascade formulation of Patchmatch for
high-resolution multi-view stereo. With high computation speed and low memory …

While image diffusion models have made significant progress in text-driven 3D content
creation they often fail to accurately capture the intended meaning of text prompts especially …

This paper introduces a novel representation of volumetric videos for real-time view
synthesis of dynamic scenes. Recent advances in neural scene representations …

Neural implicit surfaces have become an important technique for multi-view 3D
reconstruction but their accuracy remains limited. In this paper, we argue that this comes …

Neural radiance-density field methods have become increasingly popular for the task of
novel-view rendering. Their recent extension to hash-based positional encoding ensures …