SceneNN: A Scene Meshes Dataset with aNNotations

By Binh-Son Hua, Quang-Hieu Pham, Dinh C. Nguyen, Minh-Khoi Tran, Lap-Fai Craig Yu, Sai-Kit Yeung. 2016

406 citations recorded by the source corpus.

Several RGB-D datasets have been publicized over the past few years for facilitating research in computer vision and robotics. However, the lack of comprehensive and fine-grained annotation in these RGB-D datasets has posed challenges to their widespread usage. In this paper, we introduce SceneNN, an RGB-D scene dataset consisting of 100 scenes. All scenes are reconstructed into triangle meshes and have per-vertex and per-pixel annotation. We further enriched the dataset with fine-grained information such as axis-aligned bounding boxes, oriented bounding boxes, and object poses. We used the dataset as a benchmark to evaluate the state-of-the-art methods on relevant research problems such as intrinsic decomposition and shape completion. Our dataset and annotation tools are available at http://www.scenenn.net.

Subfields: Aerospace Engineering, Computational Mechanics, Computer Vision and Pattern Recognition, Evaluation & Benchmarks, 3D Vision & Pose

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computational Mechanics

In Computer Vision and Pattern Recognition

In Evaluation & Benchmarks

In 3D Vision & Pose

Citations in the corpus

Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding (2020, background): “SceneNN [31] X S+I Stanford 2D-3D-S [8, 9, 75] X X S+I Matterport3D [6, 14, 57, 58, 75] X X S+I ScanNet [17] X X S+I Gibson [58, 75] X”
Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data (2019, methodology): “RGB-D and 3D scene meshes datasets [19, 9, 1, 37, 34] have more objects that are reconstructed along with the scenes, but such objects are often considered in a scene segmentation or object detection task, and not under an object classiﬁcation setup.”
ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes (2017, methodology): “However, what makes it particularly valuable for research in scene understanding is its annotation with estimated calibration parameters, camera poses, 3D surface reconstructions, textured meshes, dense object-level semantic segmentations, and aligned CAD models (see Fig.”
Matterport3D: Learning from RGB-D Data in Indoor Environments (2017, background): “Existing work on curation of RGB-D datasets has focused mostly on scans of individual objects [5], stand-alone rooms [20, 28], views of a room [32, 35], spaces from academic buildings and small apartments [7], and small collections of rooms or public spaces [44, 1, 22].”
Joint 2D-3D-Semantic Data for Indoor Scene Understanding (2017, background): “Although several RGB-D [6, 7, 16, 15] and a few 3D datasets [12, 13, 14, 1] have been developed to date, the majority of them are limited in the scale, diversity, and/or the number of modalities they provide.”
3D-FRONT: 3D Furnished Rooms with layOuts and semaNTics (2020, methodology): “Over the past years, a large number of RGB-D benchmarks have been constructed and made publicly available [21, 3, 27, 36, 43, 33, 19, 6, 9, 18, 26, 23, 49, 24, 4, 32, 35, 42, 11, 17, 47, 38, 2].”
Configurable 3D Scene Synthesis and 2D Image Rendering with Per-pixel Ground Truth Using Stochastic Grammars (2017, background): “To address this problem, researchers have started collecting RGB-D imagery using Kinect-like sensors and preparing the associated ground truth data [71, 34].”
Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI (2021, background): “Early efforts on 3D scene datasets such as SceneNN [1] and ScanNet [2] collected reconstructions of regions of rooms, and individual rooms.”
Self-Supervised Pretraining of 3D Features on any Point-Cloud (2021, background): “Scene-centric datasets can be broadly divided into indoor scens [5, 10, 18, 39, 58, 63, 75, 81, 84, 104], and outdoor (self-driving focussed) scenes [26, 71, 88].”
OpenRooms: An End-to-End Open Framework for Photorealistic Indoor Scene Datasets (2020, methodology): “However, our pipeline can be extended, using existing tools, to other datasets [41][21] of 3D scans of indoor scenes, as demonstrated in the supplementary.”
The Hessigheim 3D (H3D) Benchmark on Semantic Segmentation of High-Resolution 3D Point Clouds and Textured Meshes from UAV LiDAR and Multi-View-Stereo (2021, background): “For better interpretability, often multi-modality is realized in the sense that acquired point clouds are meshed to obtain a well-deﬁned closed surface representation (Hua et al., 2016). ii) Outdoor terrestrial data.”
SEGCloud: Semantic Segmentation of 3D Point Clouds (2017, background): “Several 3D Scene datasets have been made available to the research community [56, 4, 5, 31, 59, 72, 52, 16, 24, 74].”
Rotation Invariant Convolutions for 3D Point Clouds Deep Learning (2019, background): “The availability of 3D object and scene datasets [36, 41, 2, 11, 6] has made scene understanding in 3D feasible.”
SceneNet RGB-D: 5M Photorealistic Images of Synthetic Indoor Trajectories with Ground Truth (2016, background): “Section 5 provides a detailed explanation on random scene generation, and Section 6 talks about generating random trajectories.”
OccuSeg: Occupancy-Aware 3D Instance Segmentation (2020, methodology): “For all the datasets including ScanNetV2 [4], Stanford3D [1] and SceneNN [18] as shown in the experiments of Sec.”
ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data (2021, background): “There are several other datasets which have focused on long indoor RGB-D captures [9, 14, 23, 24] to address the view-point diversity.”
A Robust 3D-2D Interactive Tool for Scene Segmentation and Annotation (2016, methodology): “lly segments and annotates repetitive objects deﬁned by users. We create a dataset with more than hundred scenes. All the scenes are fully segmented and annotated using our tool. We refer readers to [15] for more details and proofof-concept applications using the dataset. Compared with existing work”
Pointwise Convolutional Neural Networks (2017, methodology): “Figure 4: Semantic segmentation on SceneNN dataset [13].”