Adaptive surface splatting for facial rendering

Kim, Hyeon-Joong; Öztireli, A. Cengiz; Groß, Markus; Choi, Soo-Mi

doi:10.1002/cav.1463

Cited by 6 publications

(4 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, they returned to splat primitives and, thus, needed screen space hole and occlusion filling as well as edge-aware smoothing and anti-aliasing for consistent results. Another application area for the splat primitive was the detailed rendering of facial scans [62]. The authors adaptively distributed the splats depending on detail level and adjusted the splat sizes accordingly with screen space hole filling applied accordingly.…”

Section: ) Modern Point Cloud Rasterization Pipelines In the 2010smentioning

confidence: 99%

“…Real-time surface point cloud rasterization methods provide only hard shadows [56], [62], [64] or soft shadows [61] with Phong shading as their photorealistic effects. This means that even though rasterization methods are computationally more efficient compared to ray tracing, the supported photorealistic effects for point cloud rendering are very limited.…”

Section: ) Supported Photorealismmentioning

confidence: 99%

See 1 more Smart Citation

Real-Time Rendering of Point Clouds With Photorealistic Effects: A Survey

et al. 2022

View full text Add to dashboard Cite

Readily available RGB-D cameras in smart phones and improving 3D scanning technologies have made it possible to produce detailed point cloud and point-based models of real world objects even in real time. Rendering such models in high quality and at satisfactory frame rates is needed for realistic extended reality (XR) applications. This publication reviews real-time photorealistic point cloud rendering methods which directly ray trace or rasterize point cloud models, with an emphasis on ray tracing and realtime performance. We found that real-time direct point cloud ray tracing research has been focused on static non-animated content, and thus, open research possibilities include adapting modern dedicated ray tracing hardware for increased performance for animated and live captured scenes, and adding path tracing techniques to increase photorealistic effects in the rendering result. A categorization and discussion on the capabilities of state-of-the-art photorealistic point cloud rendering methods is presented by surveying both real-time and offline methods, which are assumed to become real-time capable with the advances in near-future hardware. Challenges and future trends are derived by comparing different rasterization and ray tracing methods as well as acceleration structures for point clouds in terms of produced rendering effects and speed.

show abstract

Section: ) Modern Point Cloud Rasterization Pipelines In the 2010smentioning

confidence: 99%

Section: ) Supported Photorealismmentioning

confidence: 99%

Real-Time Rendering of Point Clouds With Photorealistic Effects: A Survey

et al. 2022

View full text Add to dashboard Cite

show abstract

“…To render the point set, we generate splats with elliptical shapes [3]. To control the extent to which geometric features are preserved, we use the parameter .…”

Section: Point Includes 3d Position Information and Normal Vectormentioning

confidence: 99%

“…Öztireli et al [2] presented a spectral sampling method to simplify high resolution models. Kim et al [3] developed a method for adaptive surface splatting to efficiently render 3D face scans, considering facial features such as eyes, eyebrows, lips, and wrinkles. Then the method was extended and combined with automatic facial feature detection in [4].…”

Section: Introductionmentioning

confidence: 99%

Efficient stereo rendering of large 3D datasets based on binocular suppression

Shin

Kim

Choi

et al. 2015

2015 International Conference on Big Data and Smart Computing (BIGCOMP)

Self Cite

View full text Add to dashboard Cite

As the demand for stereo 3D content increases in the various fields, many types of devices for displaying stereo contents have been developed such as TVs, laptops, and mobile devices. Thus, efficient rendering methods that can process massive stereo data on those devices are becoming more important as well as reducing a feeling of visual discomfort of the viewer. In this paper, we analyze binocular suppression in an aspect of human visual perception, and present a point-based stereo rendering method to process high-resolution 3D data based on binocular suppression. To reduce visual discomfort which occurs in the process of the stereo rendering, we develop a simplification method by extending spectral sampling. Using the adaptive sampling, we can improve the rendering quality, especially in the visually sensitive areas as well as reducing the size of datasets.

show abstract