Gaze-contingent efficient hologram compression for foveated near-eye holographic displays

Dong, Zhenxing; Ling, Yuye; Xu, Chao; Li, Yan; Su, Yikai

doi:10.1016/j.displa.2023.102464

Cited by 4 publications

(1 citation statement)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Specifically, we utilized the pixel-shuffle layer and the lightweight super-resolution (SR) network to alleviate the excessive GPU memory requirements during the hologram generation process. Furthermore, inspired by foveated rendering, 16 we adopted low compression ratio transmission for the foveal region to maintain high image quality, while employing reduced resolution and ultra-high compression ratio transmission for the peripheral regions. To our knowledge, it is the first time that 4K definition holograms have been generated and compressed with a compression ratio of 40 on a consumer-grade GPU.…”

Section: Introductionmentioning

confidence: 99%

Deep learning-based approach for efficient generation and transmission of high-definition computer-generated holography

Jia,

Dong,

Ling

et al. 2024

Advances in Display Technologies XIV

Self Cite

View full text Add to dashboard Cite

Deep learning-based computer-generated holography (CGH) has recently demonstrated tremendous potential in three-dimensional (3D) displays and yielded impressive display quality. However, current CGH techniques are mostly limited on generating and transmitting holograms with a resolution of 1080p, which is far from the ultra-high resolution (16K+) required for practical virtual reality (VR) and augmented reality (AR) applications to support a wide field o f v iew a nd l arge e ye b ox. O ne o f t he m ajor o bstacles i n c urrent C GH f rameworks lies in the limited memory available on consumer-grade GPUs which could not facilitate the generation of highdefinition h olograms. M oreover, t he e xisting h ologram c ompression r ate c an h ardly p ermit t he transmission of high-resolution holograms over a 5G communication network, which is crucial for mobile application. To overcome the aforementioned challenges, we proposed an efficient jo int fr amework fo r ho logram ge neration and transmission to drive the development of consumer-grade high-definition h olographic d isplays. S pecifically, for hologram generation, we proposed a plug-and-play module that includes a pixel shuffle la yer an d a lightweight holographic super-resolution network, enabling the current CGH networks to generate high-definition holograms. For hologram transmission, we presented an efficient ho lographic tr ansmission fr amework ba sed on foveated rendering. In simulations, we have successfully achieved the generation and transmission of holograms with a 4K resolution for the first t ime o n a n N VIDIA G eForce R TX 3 090 G PU. W e b elieve t he p roposed framework could be a viable approach for the evergrowing data issue in holographic displays.

show abstract

Section: Introductionmentioning

confidence: 99%