Streamable Neural Video Compression: A Mixed Precision Approach for Cross-Platform Deployment

Neural Video Codecs (NVCs) offer unprecedented rate-distortion performance, making them highly attractive for bandwidth-constrained environments like 5G cellular networks and emerging satellite direct-to-cell (D2C) links. However, deploying NVCs in real-world streaming applications is severely hindered by cross-platform floating-point non-determinism, which causes arithmetic entropy coders to desynchronize and crash across different GPU architectures. While recent integer-based quantization methods address this, they incur either massive degradation in compression efficiency (INT8) or severe computational bottlenecks by bypassing hardware acceleration (INT16). In this paper, we propose a streamable, client-server NVC architecture featuring a novel Mixed Precision (FP16/FP32) strategy. By strategically executing P-frames in hardware-accelerated FP16 for real-time throughput, while forcing I-frames and periodic feature-adapter resets to IEEE-754 compliant FP32, we guarantee deterministic synchronization at critical boundaries. Through extensive cross-encode/decode evaluations across 12 GPUs spanning four architectural generations, we demonstrate that our approach successfully eliminates intra-generation fragmentation and substantially broadens cross-die interoperability, achieving seamless cross-generation decodability for recent architectures at 1080p. Crucially, this is achieved with a negligible impact on compression efficiency. Furthermore, we evaluate the system's end-to-end latency across diverse real-world networks, including Wi-Fi 6, 5G NR (FDD/TDD), and Starlink D2C, proving the practical viability of streamable learned video compression while highlighting unique challenges in Non-Terrestrial Networks.

Wavefront Parallelization for Efficient Learned Image Compression

Autoregressive context models are foundational for learned image compression,but they suffer from slow serial inference. Existing acceleration methods such as checkerboard context require architectural changes and retraining, thus are inapplicable to pre-trained models. We propose a completely training-free inference-time acceleration algorithm inspired by wavefront parallelism in video coding standards. Our method reorganizes inference into an optimal ``staggered'' wavefront order, minimizing sequential steps while maintaining exact autoregressive dependencies. Experimental results show our approach accelerates pre-trained autoregressive models (e.g., Cheng et al.) by more than $13\times$ while preserving the original rate-distortion performance. We also demonstrate that faster decoding is possible by trading off precise context dependencies. Source code will be available at https://github.com/tokkiwa/compressai-wavefront.

Performance Analysis of Hardware-Accelerated 10-Bit 4:2:2 Encoding with Split-Frame Encoding for High-Fidelity V-PCC Streaming

Video-based Point Cloud Compression (V-PCC) encodes volumetric data by projecting 3D geometry and texture onto 2D video frames. To prevent spatial distortion and color bleeding during 3D reconstruction, this process requires 10-bit color depth and 4:2:2 chroma subsampling, rather than the standard 8-bit 4:2:0 format. Additionally, capturing high-density dynamic point clouds requires demanding encoding parameters, such as 8K resolution at framerates up to 120 fps. Historically, the lack of 4:2:2 chroma support in older GPU hardware encoders restricted real-time V-PCC to custom Application-Specific Integrated Circuits (ASICs). However, the recent introduction of NVIDIA's Blackwell GPU architecture, featuring on-chip hardware encoders with 10-bit 4:2:2 support, presents an opportunity to shift this workload to general-purpose hardware. This paper investigates the feasibility of such an approach. Using a commercially available Blackwell GPU equipped with four parallel on-die hardware encoders as a testbed, we evaluate the throughput, rate-distortion (RD) performance, and power consumption of 8K 10-bit 4:2:2 HEVC across various Split-Frame Encoding (SFE) configurations. Our results demonstrate that 4-way SFE achieves an encoding throughput of 122 fps, successfully meeting the strict real-time constraints of high-density V-PCC. Although the inability to exploit spatial redundancies across slice boundaries results in a BD-Rate penalty of up to 5%, the measured throughput and power efficiency establish standard, commercial off-the-shelf GPUs as a highly viable baseline for real-time volumetric video streaming.

Dual-Constrained Diffusion Image Compression for Operational Rate-Distortion-Perception Optimization

The rate-distortion-perception (RDP) trade-off extends classical rate--distortion theory by imposing a distributional constraint on reconstructions, providing a unified framework for neural image compression that jointly governs fidelity and perceptual realism. While prior work achieves near-optimal rate--perception trade-offs, practical frameworks explicitly realizing the full RDP surface remain scarce, primarily due to the difficulty of introducing common randomness at the decoder. We propose DCIC (Dual-Constrained Diffusion Image Compression), which integrates a learned codec with a diffusion-based decoder governed by joint distortion and idempotence constraints. The distortion constraint bounds reconstruction fidelity relative to the base codec output; the idempotence constraint -- requiring that re-encoding the restored image recovers the base codec reconstruction -- serves as a tractable surrogate for the distributional perception requirement. Together, they steer the reverse denoising process via iterative optimization with consistent noise injection, realizing common randomness without additional rate overhead. At fixed rate, dual attenuation factors $(K_D, K_P)$ jointly navigate the Pareto frontier of the distortion-perception plane, enabling continuously adjustable fidelity-realism trade-offs from a single bitstream. DCIC$_{RD}$ ($K_P{=}0$) and DCIC$_{RP}$ ($K_D{=}0$) arise as boundary curves, with DCIC$_{RDP}$ ($K_D = K_P=1$) realizing the optimal interior operating point. Experiments on CelebA-HQ, CLIC2020, and ImageNet-1K across CNN, Transformer, and hybrid architectures confirm that DCIC$_{RDP}$ achieves superior BD-PSNR over all perceptual codecs, while DCIC$_{RP}$ matches dedicated perception-oriented methods in BD-FID, validating the practical value of full RDP surface navigation.

Real-time Video Prediction With Fast Video Interpolation Model and Prediction Training

Transmission latency significantly affects users' quality of experience in real-time interaction and actuation. As latency is principally inevitable, video prediction can be utilized to mitigate the latency and ultimately enable zero-latency transmission. However, most of the existing video prediction methods are computationally expensive and impractical for real-time applications. In this work, we therefore propose real-time video prediction towards the zero-latency interaction over networks, called IFRVP (Intermediate Feature Refinement Video Prediction). Firstly, we propose three training methods for video prediction that extend frame interpolation models, where we utilize a simple convolution-only frame interpolation network based on IFRNet. Secondly, we introduce ELAN-based residual blocks into the prediction models to improve both inference speed and accuracy. Our evaluations show that our proposed models perform efficiently and achieve the best trade-off between prediction accuracy and computational speed among the existing video prediction methods. A demonstration movie is also provided at http://bit.ly/IFRVPDemo.

Performance Analysis of 5G FR2 (mmWave) Downlink 256QAM on Commercial 5G Networks

The 5G New Radio (NR) standard introduces new frequency bands allocated in Frequency Range 2 (FR2) to support enhanced Mobile Broadband (eMBB) in congested environments and enables new use cases such as Ultra-Reliable Low Latency Communication (URLLC). The 3GPP introduced 256QAM support for FR2 frequency bands to further enhance downlink capacity. However, sustaining 256QAM on FR2 in practical environments is challenging due to strong path loss and susceptibility to distortion. While 256QAM can improve theoretical throughput by 33%, compared to 64QAM, and is widely adopted in FR1, its real-world impact when utilized in FR2 is questionable, given the significant path loss and distortions experienced in the FR2 range. Additionally, using higher modulation correlates to higher BLER, increased instability, and retransmission. Moreover, 256QAM also utilizes a different MCS table defining the modulation and code rate at different Channel Quality Indexes (CQI), affecting the UE's link adaptation behavior. This paper investigates the real-world performance of 256QAM utilization on FR2 bands in two countries, across three RAN manufacturers, and in both NSA (EN-DC) and SA (NR-DC) configurations, under various scenarios, including open-air plazas, city centers, footbridges, train station platforms, and stationary environments. The results show that 256QAM provides a reasonable throughput gain when stationary but marginal improvements when there is UE mobility while increasing the probability of NACK responses, increasing BLER, and the number of retransmissions. Finally, MATLAB simulations are run to validate the findings as well as explore the effect of the recently introduced 1024QAM on FR2.

Lightweight Stochastic Video Prediction via Hybrid Warping

Accurate video prediction by deep neural networks, especially for dynamic regions, is a challenging task in computer vision for critical applications such as autonomous driving, remote working, and telemedicine. Due to inherent uncertainties, existing prediction models often struggle with the complexity of motion dynamics and occlusions. In this paper, we propose a novel stochastic long-term video prediction model that focuses on dynamic regions by employing a hybrid warping strategy. By integrating frames generated through forward and backward warpings, our approach effectively compensates for the weaknesses of each technique, improving the prediction accuracy and realism of moving regions in videos while also addressing uncertainty by making stochastic predictions that account for various motions. Furthermore, considering real-time predictions, we introduce a MobileNet-based lightweight architecture into our model. Our model, called SVPHW, achieves state-of-the-art performance on two benchmark datasets.

LMM-driven Semantic Image-Text Coding for Ultra Low-bitrate Learned Image Compression

Supported by powerful generative models, low-bitrate learned image compression (LIC) models utilizing perceptual metrics have become feasible. Some of the most advanced models achieve high compression rates and superior perceptual quality by using image captions as sub-information. This paper demonstrates that using a large multi-modal model (LMM), it is possible to generate captions and compress them within a single model. We also propose a novel semantic-perceptual-oriented fine-tuning method applicable to any LIC network, resulting in a 41.58\% improvement in LPIPS BD-rate compared to existing methods. Our implementation and pre-trained weights are available at https://github.com/tokkiwa/ImageTextCoding.

SCP: Spherical-Coordinate-based Learned Point Cloud Compression

In recent years, the task of learned point cloud compression has gained prominence. An important type of point cloud, the spinning LiDAR point cloud, is generated by spinning LiDAR on vehicles. This process results in numerous circular shapes and azimuthal angle invariance features within the point clouds. However, these two features have been largely overlooked by previous methodologies. In this paper, we introduce a model-agnostic method called Spherical-Coordinate-based learned Point cloud compression (SCP), designed to leverage the aforementioned features fully. Additionally, we propose a multi-level Octree for SCP to mitigate the reconstruction error for distant areas within the Spherical-coordinate-based Octree. SCP exhibits excellent universality, making it applicable to various learned point cloud compression techniques. Experimental results demonstrate that SCP surpasses previous state-of-the-art methods by up to 29.14% in point-to-point PSNR BD-Rate.

Practical Commercial 5G Standalone (SA) Uplink Throughput Prediction

While the 5G New Radio (NR) network promises a huge uplift of the uplink throughput, the improvement can only be seen when the User Equipment (UE) is connected to the high-frequency millimeter wave (mmWave) band. With the rise of uplink-intensive smartphone applications such as the real-time transmission of UHD 4K/8K videos, and Virtual Reality (VR)/Augmented Reality (AR) contents, uplink throughput prediction plays a huge role in maximizing the users' quality of experience (QoE). In this paper, we propose using a ConvLSTM-based neural network to predict the future uplink throughput based on past uplink throughput and RF parameters. The network is trained using the data from real-world drive tests on commercial 5G SA networks while riding commuter trains, which accounted for various frequency bands, handover, and blind spots. To make sure our model can be practically implemented, we then limited our model to only use the information available via Android API, then evaluate our model using the data from both commuter trains and other methods of transportation. The results show that our model reaches an average prediction accuracy of 98.9\% with an average RMSE of 1.80 Mbps across all unseen evaluation scenarios.