DIODE: A Dense Indoor and Outdoor DEpth Dataset

Igor, Vasiljevic,; Kolkin, Nick; Zhang, Shanyi; Luo, Ruotian; Wang, Haochen; Dai, Falcon Z.; Daniele, Andrea F.; Mostajabi, Mohammadreza; Basart, Steven; Walter, Matthew R.; Shakhnarovich, Gregory

doi:10.48550/arxiv.1908.00463

Cited by 20 publications

(35 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 2. Quantivate comparison of our reannotated NYU-v2 [39], Diode [41], ETH3D [36] datasets and our collected dataset, respectively. We highlight top two performers in each metric with pink and yellow background, respectively.…”

Section: Methodsmentioning

confidence: 99%

“…However, to our knowledge, there are no such datasets publicly available. To evaluate our method, we first present in Section 4.1 reannotating the commonly used depth datasets NYU-v2 [39] and Diode [41]. Then in Section 4.2 we relabel the ETH3D dataset [36], which includes sensor raw files.…”

Section: Dataset Preparationmentioning

confidence: 99%

“…NYU-v2 [39] is a classical RGB-D dataset, with hundreds of indoor scenes captured by Microsoft Kinect. Diode [41] is a latest RGB-D dataset released by Toyota Technological Institute at Chicago, this dataset contains more than 20 scenes include indoor and outdoor scenes. Affected by the illuminant and position, there are numbers of AWBbiased images in these datasets (See supplement material).…”

Section: Annotating Nyu-v2 and Diode Depth Datasetmentioning

confidence: 99%

“…• PCCC operates well on the sparse-sampled thumbnail point clouds, which allows over 500 frames per second (include time of building point cloud) on a Nvidia V100 GPU and is hardware friendly for a mobile SoC. • We annotated the illumination groundtruth labels for three popular RGB-D datasets (NYU-v2 dataset [39], Diode dataset [41] and ETH3D dataset [36]) and collected DepthAWB, a novel RGB-D dataset for the color constancy task.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Point Cloud Color Constancy

Xing¹,

Qian²,

Feng³

et al. 2021

Preprint

View full text Add to dashboard Cite

Section: Methodsmentioning

confidence: 99%

Section: Dataset Preparationmentioning

confidence: 99%

Section: Annotating Nyu-v2 and Diode Depth Datasetmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Point Cloud Color Constancy

Xing¹,

Qian²,

Feng³

et al. 2021

Preprint

View full text Add to dashboard Cite

“…• DIODE (Dense Indoor/Outdoor DEpth) [18] is the first public dataset that includes RGBD images from both indoor and outdoor scenes. It contains thousands of accurate, dense and long-range depth maps.…”

Section: Datasetsmentioning

confidence: 99%

End-to-end lossless compression of high precision depth maps guided by pseudo-residual

Wu¹,

Gao²

2022

Preprint

View full text Add to dashboard Cite

As a fundamental data format representing spatial information, depth map is widely used in signal processing and computer vision fields. Massive amount of high precision depth maps are produced with the rapid development of equipment like laser scanner or LiDAR. Therefore, it is urgent to explore a new compression method with better compression ratio for high precision depth maps. Utilizing the wide spread deep learning environment, we propose an end-to-end learning-based lossless compression method for high precision depth maps. The whole process is comprised of two sub-processes, named pre-processing of depth maps and deep lossless compression of processed depth maps. The deep lossless compression network consists of two sub-networks, named lossy compression network and lossless compression network. We leverage the concept of pseudo-residual to guide the generation of distribution for residual and avoid introducing context models. Our end-to-end lossless compression network achieves competitive performance over engineered codecs and has low computational cost.

show abstract

Learning Stereo from Single Images

Watson¹,

Aodha

Turmukhambetov³

et al. 2020

Computer Vision – ECCV 2020

View full text Add to dashboard Cite

Supervised deep networks are among the best methods for finding correspondences in stereo image pairs. Like all supervised approaches, these networks require ground truth data during training. However, collecting large quantities of accurate dense correspondence data is very challenging. We propose that it is unnecessary to have such a high reliance on ground truth depths or even corresponding stereo pairs. Inspired by recent progress in monocular depth estimation, we generate plausible disparity maps from single images. In turn, we use those flawed disparity maps in a carefully designed pipeline to generate stereo training pairs. Training in this manner makes it possible to convert any collection of single RGB images into stereo training data. This results in a significant reduction in human effort, with no need to collect real depths or to hand-design synthetic data. We can consequently train a stereo matching network from scratch on datasets like COCO, which were previously hard to exploit for stereo. Through extensive experiments we show that our approach outperforms stereo networks trained with standard synthetic datasets, when evaluated on KITTI, ETH3D, and Middlebury. Code to reproduce our results is available at https://github.com/nianticlabs/stereo-from-mono/.

show abstract

DIODE: A Dense Indoor and Outdoor DEpth Dataset

Cited by 20 publications

References 28 publications

Point Cloud Color Constancy

Point Cloud Color Constancy

End-to-end lossless compression of high precision depth maps guided by pseudo-residual

Learning Stereo from Single Images

Contact Info

Product

Resources

About