相关论文: RGBD-Net: Predicting color and depth images for no…

Synthesizing novel views from a single input image is a challenging task. It requires extrapolating the 3D structure of a scene while inferring details in occluded regions, and maintaining geometric consistency across viewpoints. Many…

We present a novel approach that converts partial and noisy RGB-D scans into high-quality 3D scene reconstructions by inferring unobserved scene geometry. Our approach is fully self-supervised and can hence be trained solely on real-world,…

Deep convolutional networks (CNN) can achieve impressive results on RGB scene recognition thanks to large datasets such as Places. In contrast, RGB-D scene recognition is still underdeveloped in comparison, due to two limitations of RGB-D…

Under good conditions, Neural Radiance Fields (NeRFs) have shown impressive results on novel view synthesis tasks. NeRFs learn a scene's color and density fields by minimizing the photometric discrepancy between training views and…

In this paper, we propose an end-to-end deep learning network named 3dDepthNet, which produces an accurate dense depth image from a single pair of sparse LiDAR depth and color image for robotics and autonomous driving tasks. Based on the…

Recent neural rendering and reconstruction techniques, such as NeRFs or Gaussian Splatting, have shown remarkable novel view synthesis capabilities but require hundreds of images of the scene from diverse viewpoints to render high-quality…

Current methods for 3D scene reconstruction from sparse posed images employ intermediate 3D representations such as neural fields, voxel grids, or 3D Gaussians, to achieve multi-view consistent scene appearance and geometry. In this paper…

Robust object recognition is a crucial ingredient of many, if not all, real-world robotics applications. This paper leverages recent progress on Convolutional Neural Networks (CNNs) and proposes a novel RGB-D architecture for object…

Ground-truth RGBD data are fundamental for a wide range of computer vision applications; however, those labeled samples are difficult to collect and time-consuming to produce. A common solution to overcome this lack of data is to employ…

In this study, we present a method for synthesizing novel views from a single 360-degree RGB-D image based on the neural radiance field (NeRF) . Prior studies relied on the neighborhood interpolation capability of multi-layer perceptrons to…

We present a machine learning algorithm that takes as input a 2D RGB image and synthesizes a 4D RGBD light field (color and depth of the scene in each ray direction). For training, we introduce the largest public light field dataset,…

The semantic synthesis of unseen scenes from multiple viewpoints is crucial for research in 3D scene understanding. Current methods are capable of rendering novel-view images and semantic maps by reconstructing generalizable Neural Radiance…

We introduce a novel geometry-guided online video view synthesis method with enhanced view and temporal consistency. Traditional approaches achieve high-quality synthesis from dense multi-view camera setups but require significant…

We present an approach that learns to synthesize high-quality, novel views of 3D objects or scenes, while providing fine-grained and precise control over the 6-DOF viewpoint. The approach is self-supervised and only requires 2D images and…

High dynamic range (HDR) novel view synthesis (NVS) aims to create photorealistic images from novel viewpoints using HDR imaging techniques. The rendered HDR images capture a wider range of brightness levels containing more details of the…

3D model generation from single 2D RGB images is a challenging and actively researched computer vision task. Various techniques using conventional network architectures have been proposed for the same. However, the body of research work is…

We propose a new deep learning architecture for the tasks of semantic segmentation and depth prediction from RGB-D images. We revise the state of art based on the RGB and depth feature fusion, where both modalities are assumed to be…

Compared to RGB semantic segmentation, RGBD semantic segmentation can achieve better performance by taking depth information into consideration. However, it is still problematic for contemporary segmenters to effectively exploit RGBD…

Deep learning approaches have achieved highly accurate face recognition by training the models with very large face image datasets. Unlike the availability of large 2D face image datasets, there is a lack of large 3D face datasets available…

Neural Radiance Fields (NeRF) have garnered remarkable success in novel view synthesis. Nonetheless, the task of generating high-quality images for novel views persists as a critical challenge. While the existing efforts have exhibited…