Related papers: SCRREAM : SCan, Register, REnder And Map:A Framewo…

We propose a novel framework for creating large-scale photorealistic datasets of indoor scenes, with ground truth geometry, material, lighting and semantics. Our goal is to make the dataset creation process widely accessible, transforming…

Datasets have gained an enormous amount of popularity in the computer vision community, from training and evaluation of Deep Learning-based methods to benchmarking Simultaneous Localization and Mapping (SLAM). Without a doubt, synthetic…

3D understanding is a key capability for real-world AI assistance. High-quality data plays an important role in driving the development of the 3D understanding community. Current 3D scene understanding datasets often provide geometric and…

We present a novel dataset for training and benchmarking semantic SLAM methods. The dataset consists of 200 long sequences, each one containing 3000-5000 data frames. We generate the sequences using realistic home layouts. For that we…

Depth estimation is a core task in 3D computer vision. Recent methods investigate the task of monocular depth trained with various depth sensor modalities. Every sensor has its advantages and drawbacks caused by the nature of estimates. In…

For many fundamental scene understanding tasks, it is difficult or impossible to obtain per-pixel ground truth labels from real images. We address this challenge by introducing Hypersim, a photorealistic synthetic dataset for holistic…

In recent years, there have been significant advancements in 3D reconstruction and dense RGB-D SLAM systems. One notable development is the application of Neural Radiance Fields (NeRF) in these systems, which utilizes implicit neural…

Learning-based methods for 3D scene reconstruction and object completion require large datasets containing partial scans paired with complete ground-truth geometry. However, acquiring such datasets using real-world scanning systems is…

This paper proposes a new method for simultaneous 3D reconstruction and semantic segmentation of indoor scenes. Unlike existing methods that require recording a video using a color camera and/or a depth camera, our method only needs a small…

Recent developments in differentiable and neural rendering have made impressive breakthroughs in a variety of 2D and 3D tasks, e.g. novel view synthesis, 3D reconstruction. Typically, differentiable rendering relies on a dense viewpoint…

Dense simultaneous localization and mapping (SLAM) is crucial for robotics and augmented reality applications. However, current methods are often hampered by the non-volumetric or implicit way they represent a scene. This work introduces…

Reconstructing accurate 3D surfaces for street-view scenarios is crucial for applications such as digital entertainment and autonomous driving simulation. However, existing street-view datasets, including KITTI, Waymo, and nuScenes, only…

Neural implicit representations have recently shown promising progress in dense Simultaneous Localization And Mapping (SLAM). However, existing works have shortcomings in terms of reconstruction quality and real-time performance, mainly due…

We introduce SceneNet RGB-D, expanding the previous work of SceneNet to enable large scale photorealistic rendering of indoor scene trajectories. It provides pixel-perfect ground truth for scene understanding problems such as semantic…

A key requirement for leveraging supervised deep learning methods is the availability of large, labeled datasets. Unfortunately, in the context of RGB-D scene understanding, very little data is available -- current datasets cover a small…

The convergence of 3D geometric perception and video synthesis has created an unprecedented demand for large-scale video data that is rich in both semantic and spatio-temporal information. While existing datasets have advanced either 3D…

The recent development of online static map element (a.k.a. HD Map) construction algorithms has raised a vast demand for data with ground truth annotations. However, available public datasets currently cannot provide high-quality training…

Recently, there has been growing interest in developing learning-based methods to detect and utilize salient semi-global or global structures, such as junctions, lines, planes, cuboids, smooth surfaces, and all types of symmetries, for 3D…

3D alignment has become a very important part of 3D scanning technology. For instance, we can divide the alignment process into four steps: key point detection, key point description, initial pose estimation, and alignment refinement.…

3D point cloud understanding has made great progress in recent years. However, one major bottleneck is the scarcity of annotated real datasets, especially compared to 2D object detection tasks, since a large amount of labor is involved in…