View Synthesis: LiDAR Camera versus Depth Estimation
Autor: | Gauthier Lafruit, Yupeng Xie, Daniele Bonatto, Mehrdad Teratani, Sarah Fachada |
---|---|
Přispěvatelé: | Skala, Václav |
Rok vydání: | 2021 |
Předmět: |
Reference software
LiDAR RVS Computer science syntéza pohledu odhad hloubky Depth-Image-Based Rendering ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Sciences de l'ingénieur Rendering (computer graphics) Set (abstract data type) Depth map depth estimation Calibration Computer vision business.industry Frame (networking) Reference View Synthesizer DIBR Virtual Reality Depth sensor View synthesis View synthesis view synthesis Lidar vykreslování založené na hloubce obrazu DERS Artificial intelligence kalibrace kamery camera calibration business |
Zdroj: | International Conference on Computer Graphics, Visualization and Computer Vision 2021 (WSCG) |
ISSN: | 2464-4617 |
DOI: | 10.24132/csrn.2021.3101.35 |
Popis: | Depth-Image-Based Rendering (DIBR) can synthesize a virtual view image from a set of multiview images and corresponding depth maps. However, this requires an accurate depth map estimation that incurs a high compu- tational cost over several minutes per frame in DERS (MPEG-I’s Depth Estimation Reference Software) even by using a high-class computer. LiDAR cameras can thus be an alternative solution to DERS in real-time DIBR ap- plications. We compare the quality of a low-cost LiDAR camera, the Intel Realsense LiDAR L515 calibrated and configured adequately, with DERS using MPEG-I’s Reference View Synthesizer (RVS). In IV-PSNR, the LiDAR camera reaches 32.2dB view synthesis quality with a 15cm camera baseline and 40.3dB with a 2cm baseline. Though DERS outperforms the LiDAR camera with 4.2dB, the latter provides a better quality-performance trade- off. However, visual inspection demonstrates that LiDAR’s virtual views have even slightly higher quality than with DERS in most tested low-texture scene areas, except for object borders. Overall, we highly recommend using LiDAR cameras over advanced depth estimation methods (like DERS) in real-time DIBR applications. Neverthe- less, this requires delicate calibration with multiple tools further exposed in the paper. |
Databáze: | OpenAIRE |
Externí odkaz: |