Related papers: Bayesian Monocular Depth Refinement via Neural Rad…

Neural networks have shown great abilities in estimating depth from a single image. However, the inferred depth maps are well below one-megapixel resolution and often lack fine-grained details, which limits their practicality. Our method…

Self-supervised learning for depth estimation uses geometry in image sequences for supervision and shows promising results. Like many computer vision tasks, depth network performance is determined by the capability to learn accurate spatial…

With the advent of Neural Radiance Fields (NeRF), neural networks can now render novel views of a 3D scene with quality that fools the human eye. Yet, generating these images is very computationally intensive, limiting their applicability…

Neural radiance fields (NeRFs) have shown impressive results for novel view synthesis. However, they depend on the repetitive use of a single-input single-output multilayer perceptron (SISO MLP) that maps 3D coordinates and view direction…

We present a robust and accurate depth refinement system, named GeoRefine, for geometrically-consistent dense mapping from monocular sequences. GeoRefine consists of three modules: a hybrid SLAM module using learning-based priors, an online…

Neural radiance fields (NeRF) bring a new wave for 3D interactive experiences. However, as an important part of the immersive experiences, the defocus effects have not been fully explored within NeRF. Some recent NeRF-based methods generate…

Monocular Depth Estimation (MDE) is a fundamental computer vision task with important applications in 3D vision. The current mainstream MDE methods employ an encoder-decoder architecture with multi-level/scale feature processing. However,…

A commonly observed failure mode of Neural Radiance Field (NeRF) is fitting incorrect geometries when given an insufficient number of input views. One potential reason is that standard volumetric rendering does not enforce the constraint…

While Neural Radiance Fields (NeRFs) had achieved unprecedented novel view synthesis results, they have been struggling in dealing with large-scale cluttered scenes with sparse input views and highly view-dependent appearances.…

Neural rendering has garnered substantial attention owing to its capacity for creating realistic 3D scenes. However, its applicability to extensive scenes remains challenging, with limitations in effectiveness. In this work, we propose the…

Monocular depth estimation and defocus estimation are two fundamental tasks in computer vision. Most existing methods treat depth estimation and defocus estimation as two separate tasks, ignoring the strong connection between them. In this…

Neural Radiance Fields (NeRF) methods excel at 3D reconstruction from multiple 2D images, even those taken with unknown camera poses. However, they still miss the fine-detailed structures that matter in industrial inspection, e.g.,…

Recently, convolutional neural networks (CNNs) have shown great success on the task of monocular depth estimation. A fundamental yet unanswered question is: how CNNs can infer depth from a single image. Toward answering this question, we…

Dense and accurate 3D mapping from a monocular sequence is a key technology for several applications and still an open research area. This paper leverages recent results on single-view CNN-based depth estimation and fuses them with…

Monocular depth estimation aims at predicting depth from a single image or video. Recently, self-supervised methods draw much attention since they are free of depth annotations and achieve impressive performance on several daytime…

In this paper, we propose MINE to perform novel view synthesis and depth estimation via dense 3D reconstruction from a single image. Our approach is a continuous depth generalization of the Multiplane Images (MPI) by introducing the NEural…

We present a Bayesian Neural Radiance Field (NeRF), which explicitly quantifies uncertainty in the volume density by modeling uncertainty in the occupancy, without the need for additional networks, making it particularly suited for…

The ability to accurately estimate depth information is crucial for many autonomous applications to recognize the surrounded environment and predict the depth of important objects. One of the most recently used techniques is monocular depth…

In the current monocular depth research, the dominant approach is to employ unsupervised training on large datasets, driven by warped photometric consistency. Such approaches lack robustness and are unable to generalize to challenging…

Neural radiance fields (NeRFs) produce state-of-the-art view synthesis results. However, they are slow to render, requiring hundreds of network evaluations per pixel to approximate a volume rendering integral. Baking NeRFs into explicit…