Natural Scenes Datasets for Exploration In 6DOF Navigation

Schenkel, Arnaud; Bonatto, Daniele; Fachada, Sarah; Guillaume, Henry-Louis; Lafruit, Gauthier

doi:10.1109/ic3d.2018.8657865

Cited by 14 publications

(13 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3D content with perfect depth maps (eg: Classroom), real scenery with Kinect depth map (eg: ULB Unicorn) and stereomatching estimated depth maps (eg: ULB BabyUnicorn) were used. A review of the different datasets is out of the scope of this paper and can be found in [41].…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

RaViS: Real-time accelerated View Synthesizer for immersive video 6DoF VR

Bonatto¹,

Fachada²,

Lafruit³

2020

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Resultsmentioning

confidence: 99%

“…However, the depth sensor is usually not aligned with the RGB sensor and the output resolution is often far less than the RGB resolution. Depth scaling and inpainting need to be performed to obtain high quality images as in [41].…”

Section: Depth Mapsmentioning

confidence: 99%

RaViS: Real-time accelerated View Synthesizer for immersive video 6DoF VR

Bonatto¹,

Fachada²,

Lafruit³

2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…For testing GoRG in YUV, a set of eight multiview sequences from MPEG-I is used [37,38]. Their identifiers and features are introduced in Table 1.…”

Section: Yuv Materialsmentioning

confidence: 99%

GoRG: Towards a GPU-Accelerated Multiview Hyperspectral Depth Estimation Tool for Medical Applications

Sancho

Sutradhar

Rosa

et al. 2021

Sensors

View full text Add to dashboard Cite

HyperSpectral (HS) images have been successfully used for brain tumor boundary detection during resection operations. Nowadays, these classification maps coexist with other technologies such as MRI or IOUS that improve a neurosurgeon’s action, with their incorporation being a neurosurgeon’s task. The project in which this work is framed generates an unified and more accurate 3D immersive model using HS, MRI, and IOUS information. To do so, the HS images need to include 3D information and it needs to be generated in real-time operating room conditions, around a few seconds. This work presents Graph cuts Reference depth estimation in GPU (GoRG), a GPU-accelerated multiview depth estimation tool for HS images also able to process YUV images in less than 5.5 s on average. Compared to a high-quality SoA algorithm, MPEG DERS, GoRG YUV obtain quality losses of −0.93 dB, −0.6 dB, and −1.96% for WS-PSNR, IV-PSNR, and VMAF, respectively, using a video synthesis processing chain. For HS test images, GoRG obtains an average RMSE of 7.5 cm, with most of its errors in the background, needing around 850 ms to process one frame and view. These results demonstrate the feasibility of using GoRG during a tumor resection operation.

show abstract

“…1 (B), and (ii) a depth-based view synthesis, aka RVS (Reference View Synthesis). The latter is applied in the present paper for synthesizing a holographic stereogram from the ULB_Unicorn data set [4], a test scene with various objects on a table of 2.30 m wide and 1m deep, cf. Fig.…”

Section: State Of the Artmentioning

confidence: 99%