'Feature Learning in Finite-Width Bayesian Deep Linear Networks with Multiple Outputs and Convolutional Layers', by Federico Bassetti, Marco Gherardi, Alessandro Ingrosso, Mauro Pastore, Pietro Rotondo.
http://jmlr.org/papers/v26/24-1158.html
#gaussian #gaussians #convol
3D Gaussian Splatting (3DGS) is an emerging technique for photorealistic 3D scene rendering. However, rendering city-scale 3DGS scenes on mobile devices, e.g., your smartphones, remains a significant challenge due to the limited resources on mobile devices. A natural solution is to offload computation to the cloud; however, naively streaming rendered frames from the cloud to the client introduces high latency and requires bandwidth far beyond the capacity of current wireless networks. In this paper, we propose an effective solution to enable city-scale 3DGS rendering on mobile devices. Our key insight is that, under normal user motion, the number of newly visible Gaussians per second remains roughly constant. Leveraging this, we stream only the necessary Gaussians to the client. Specifically, on the cloud side, we propose asynchronous level-of-detail search to identify the necessary Gaussians for the client. On the client side, we accelerate rendering via a lookup table-based rasterization. Combined with holistic runtime optimizations, our system can deliver low-latency, city-scale 3DGS rendering on mobile devices. Compared to existing solutions, Voyager achieves over 100$\times$ reduction on data transfer and up to 8.9$\times$ speedup while retaining comparable rendering quality.
Voyager: Real-Time Splatting City-Scale 3D Gaussians on Your Phone
https://arxiv.org/abs/2506.02774
#HackerNews #Voyager #RealTime #Splatting #3D #Gaussians #Mobile #Technology
3D Gaussian Splatting (3DGS) is an emerging technique for photorealistic 3D scene rendering. However, rendering city-scale 3DGS scenes on mobile devices, e.g., your smartphones, remains a significant challenge due to the limited resources on mobile devices. A natural solution is to offload computation to the cloud; however, naively streaming rendered frames from the cloud to the client introduces high latency and requires bandwidth far beyond the capacity of current wireless networks. In this paper, we propose an effective solution to enable city-scale 3DGS rendering on mobile devices. Our key insight is that, under normal user motion, the number of newly visible Gaussians per second remains roughly constant. Leveraging this, we stream only the necessary Gaussians to the client. Specifically, on the cloud side, we propose asynchronous level-of-detail search to identify the necessary Gaussians for the client. On the client side, we accelerate rendering via a lookup table-based rasterization. Combined with holistic runtime optimizations, our system can deliver low-latency, city-scale 3DGS rendering on mobile devices. Compared to existing solutions, Voyager achieves over 100$\times$ reduction on data transfer and up to 8.9$\times$ speedup while retaining comparable rendering quality.
Evaluating CrowdSplat: Perceived Level of Detail for Gaussian Crowds
Xiaohan Sun, Yinghan Xu, John Dingliana, Carol O'Sullivan
https://arxiv.org/abs/2501.17085 https://arxiv.org/pdf/2501.17085 https://arxiv.org/html/2501.17085
arXiv:2501.17085v1 Announce Type: new
Abstract: Efficient and realistic crowd rendering is an important element of many real-time graphics applications such as Virtual Reality (VR) and games. To this end, Levels of Detail (LOD) avatar representations such as polygonal meshes, image-based impostors, and point clouds have been proposed and evaluated. More recently, 3D Gaussian Splatting has been explored as a potential method for real-time crowd rendering. In this paper, we present a two-alternative forced choice (2AFC) experiment that aims to determine the perceived quality of 3D Gaussian avatars. Three factors were explored: Motion, LOD (i.e., #Gaussians), and the avatar height in Pixels (corresponding to the viewing distance). Participants viewed pairs of animated 3D Gaussian avatars and were tasked with choosing the most detailed one. Our findings can inform the optimization of LOD strategies in Gaussian-based crowd rendering, thereby helping to achieve efficient rendering while maintaining visual quality in real-time applications.
Efficient and realistic crowd rendering is an important element of many real-time graphics applications such as Virtual Reality (VR) and games. To this end, Levels of Detail (LOD) avatar representations such as polygonal meshes, image-based impostors, and point clouds have been proposed and evaluated. More recently, 3D Gaussian Splatting has been explored as a potential method for real-time crowd rendering. In this paper, we present a two-alternative forced choice (2AFC) experiment that aims to determine the perceived quality of 3D Gaussian avatars. Three factors were explored: Motion, LOD (i.e., #Gaussians), and the avatar height in Pixels (corresponding to the viewing distance). Participants viewed pairs of animated 3D Gaussian avatars and were tasked with choosing the most detailed one. Our findings can inform the optimization of LOD strategies in Gaussian-based crowd rendering, thereby helping to achieve efficient rendering while maintaining visual quality in real-time applications.
JMLR
N-gated Hacker News
Hacker News
arXiv cs.CV bot
Hacker News