Nowadays, visual intelligence tools have become ubiquitous, offering all kinds of convenience and possibilities. However, these tools have high computational requirements that exceed the capabilities of resource-constrained mobile and wearable devices. While offloading visual data to the cloud is a common solution, it introduces significant privacy vulnerabilities during transmission and server-side computation. To address this, we propose a novel distributed, hierarchical offloading framework for Vision Transformers (ViTs) that addresses these privacy challenges by design. Our approach uses a local trusted edge device, such as a mobile phone or an Nvidia Jetson, as the edge orchestrator. This orchestrator partitions the user's visual data into smaller portions and distributes them across multiple independent cloud servers. By design, no single external server possesses the complete image, preventing comprehensive data reconstruction. The final data merging and aggregation computation occurs exclusively on the user's trusted edge device. We apply our framework to the Segment Anything Model (SAM) as a practical case study, which demonstrates that our method substantially enhances content privacy over traditional cloud-based approaches. Evaluations show our framework maintains near-baseline segmentation performance while substantially reducing the risk of content reconstruction and user data exposure. Our framework provides a scalable, privacy-preserving solution for vision tasks in the edge-cloud continuum.

3D Gaussian Splatting (3DGS) is an emerging media representation that reconstructs real-world 3D scenes in high fidelity, enabling 6-degrees-of-freedom (6-DoF) navigation in virtual reality (VR). However, developing and evaluating 3DGS-enabled applications and optimizing their rendering performance require realistic user navigation data. Such data is currently unavailable for photorealistic 3DGS reconstructions of real-world scenes. This paper introduces EyeNavGS, the first publicly available 6-DoF navigation dataset featuring traces from 46 participants exploring twelve diverse, real-world 3DGS scenes. The dataset was collected at two sites, using the Meta Quest Pro headsets, recording the head pose and eye gaze data for each rendered frame during free world standing 6-DoF navigation. For each of the twelve scenes, we performed careful scene initialization to correct for scene tilt and scale, ensuring a perceptually-comfortable VR experience. We also release our open-source SIBR viewer software fork with record-and-replay functionalities and a suite of utility tools for data processing, conversion, and visualization. The EyeNavGS dataset and its accompanying software tools provide valuable resources for advancing research in 6-DoF viewport prediction, adaptive streaming, 3D saliency, and foveated rendering for 3DGS scenes. The EyeNavGS dataset is available at: https://symmru.github.io/EyeNavGS/

3D scene modeling is essential for immersive experiences in Virtual, Augmented, and Mixed Reality (VR/AR/MR) applications. Neural Radiance Fields (NeRF) have emerged as a strong alternative to traditional representations such as meshes and point clouds for 6-DoF rendering. However, maintaining high visual quality while enabling efficient transmission in dynamic environments remains a significant challenge. In this paper, we propose NeRFCompressor, a novel compression framework for dynamic scene representation using NeRF-like models. Building on tensor decomposition-based 3D reconstruction, NeRFCompressor improves transmission efficiency by leveraging existing video codecs to exploit both intra-scene and inter-scene redundancies. It maintains high QoE with minimal degradation in reconstruction quality. Experiments show that NeRFCompressor outperforms state-of-the-art methods in compressing both static and dynamic scene representations.

We present a novel DASH-based streaming system for dynamic 3D Gaussian Splatting (3DGS) scenes, addressing the challenges of streaming large amounts of 3DGS data over diverse and dynamic networks. Our Layer, Tile, and Segment Adaptive streaming (LTS) system combines three key features: (i) multi-layer streaming, which adapts to diverse client capabilities while balancing visual quality and bandwidth usage, (ii) tiled streaming, which reduces unnecessary data transmission by focusing on the user's viewport, and (iii) segment streaming, which divides dynamic 3DGS scenes into segments, letting clients request them dynamically to handle network fluctuations. Our experimental results demonstrate that our LTS system achieves superior performance in both live and on-demand streaming of dynamic 3DGS scenes compared to the baselines. For example, in live streaming, LTS could achieve up to 99.70% reduction in missing frames on average and deliver a maximum PSNR (Peak Signal-to-Noise Ratio) improvement of 10.08 dB. In on-demand streaming, LTS could reduce the freeze time by up to 92.01%, and increase the synthesized view quality by up to 5.14 dB in PSNR and 0.11 in SSIM (Structural Similarity Index). Our source codes are available at: https://github.com/AIINS-NTHU/LTS-DASH-Streaming-System-for-3DGS.

3D Gaussian Splatting (3DGS) is an emerging approach for training and representing real-world 3D scenes. Due to its photorealistic novel view synthesis and fast rendering speed (e.g., over 100 FPS), it has the potential to transform how scenes that can be explored in 6 degrees-of-freedom (6-DoF) are represented. However, a limiting factor of 3DGS is its large size, which requires high network bandwidth for streaming reconstructed real-world 3D scenes.

Volumetric video streaming has become increasingly popular in recent years due to its support of 6 degrees-of-freedom (6-DoF) exploration. There is, however, a shortage of dynamic 6-DoF content suitable for comparing the performance among heterogeneous volumetric video representations. This paper introduces a software toolkit for creating both a dataset of dynamic 6-DoF content in point clouds and a dataset for training and testing neural-based representations such as neural radiance fields (NeRF). Starting with freely available 3D assets online, our software toolkit uses the Blender Python API to generate training and testing datasets for neural-based dynamic volumetric model training. The created datasets are compliant with existing neural-based model training and rendering frameworks. The software can also construct point cloud sequences derived from synthetic dynamic 3D meshes. This further facilitates comparing point clouds and neural-based methods for volumetric video representation. We release the software toolkit along with a rich set of sequence datasets generated in compliance with the permissions granted by the original 3D asset creators. With our toolkit and dataset, we aim to facilitate research from the multimedia systems community to support practical volumetric streaming. Our software toolkit and dataset are available at: https://6-dof-dynamic-content-software.github.io/.

Video-based Point Cloud Compression (V-PCC) is an emerging standard for encoding dynamic point cloud data. With V-PCC, point cloud data is segmented, projected, and packed on to 2D video frames, which can be compressed using existing video coding standards such as H.264, H.265 and AV1. This makes it possible to support point cloud streaming via reliable video transmission systems. On the other hand, despite recent advances, many issues still remain and prevent V-PCC from being used in low-latency point cloud streaming. For instance, point cloud registration and patch generation can take a long time.