Video Multi-method Assessment Fusion (VMAF) is a widely used objective evaluation metric that has shown a stronger correlation with human visual system than other metrics. Some studies have already integrated VMAF as a measure of perceptual quality in the rate-distortion optimization of hybrid codecs. However, VMAF has long been considered non-differentiable, limiting its application in learning-based video compression. In this work, we successfully achieve a differentiable VMAF through mathematical approximations. Our implementation of differentiable VMAF maintains the performance of the original VMAF while ensuring accurate gradient calculations. By integrating it into the loss function for optimizing learning-based video compression, our experimental results demonstrate that this approach significantly enhances VMAF performance and improves perceptual quality at all bitrates.

Dynamic scene reconstruction poses a persistent challenge in 3D vision. Deformable 3D Gaussian Splatting has emerged as an effective method for this task, offering real-time rendering and high visual fidelity. This approach decomposes a dynamic scene into a static representation in a canonical space and time-varying scene motion. Scene motion is defined as the collective movement of all Gaussian points, and for compactness, existing approaches commonly adopt implicit neural fields or sparse control points. However, these methods predominantly rely on gradient-based optimization for all motion information. Due to the high degree of freedom, they struggle to converge on real-world datasets exhibiting complex motion. To preserve the compactness of motion representation and address convergence challenges, this paper proposes heterogeneous 3D control points, termed \textbf{H3D control points}, whose attributes are obtained using a hybrid strategy combining optical flow back-projection and gradient-based methods. This design decouples directly observable motion components from those that are geometrically occluded. Specifically, components of 3D motion that project onto the image plane are directly acquired via optical flow back projection, while unobservable portions are refined through gradient-based optimization. Experiments on the Neu3DV and CMU-Panoptic datasets demonstrate that our method achieves superior performance over state-of-the-art deformable 3D Gaussian splatting techniques. Remarkably, our method converges within just 100 iterations and achieves a per-frame processing speed of 2 seconds on a single NVIDIA RTX 4070 GPU.

This report presents the VCIP 2025 Grand Challenge on Ultra Low-Bitrate Video Compression, which aims to promote research progress in perceptually optimized and computationally efficient video compression under extreme bandwidth constraints. The challenge focuses on scenarios such as emergency communication, remote monitoring, and low-power transmission, where conventional codecs like HEVC and AV1 struggle to maintain acceptable perceptual quality. Two benchmark tracks are introduced to assess the trade-off between compression ratio, visual quality, and complexity: Track 1 (50 kbps) targets extreme low-bitrate conditions, while Track 2 (200 kbps) allows moderately higher bitrates under real-time constraints. Participants were required to satisfy strict limits on encoding and decoding complexity, evaluated in kMac per pixel and per-frame runtime. The evaluation combined both objective metrics (PSNR, SSIM, VMAF, LPIPS) and subjective human perception scoring to comprehensively assess quality and efficiency. The results reveal two complementary trends for the future of video compression: (1) efficiency-oriented codec architecture design enabling low-latency deployment on edge devices, and (2) perceptual enhancement through post-decoding restoration guided by temporal and semantic priors. Together, these directions signal a paradigm shift from traditional rate–distortion optimization toward a broader rate–perception–complexity trade-off. The insights gained from this challenge are expected to inspire future standards and generative compression models for perceptually-driven, adaptive, and bandwidth-efficient video communication.

The learning-based video compression method has made significant progress in recent years, exhibiting promising compression performance compared with traditional video codecs. However, prior works have primarily focused on advanced compression architectures while neglecting the rate control technique. Rate control can precisely control the coding bitrate with optimal compression performance, which is a critical technique in practical deployment. To address this issue, we present a fully neural network-based rate control system for learned video compression methods. Our system accurately encodes videos at a given bitrate while enhancing the rate-distortion performance. Specifically, we first design a rate allocation model to assign optimal bitrates to each frame based on their varying spatial and temporal characteristics. Then, we propose a deep learning-based rate implementation network to perform the rate-parameter mapping, precisely predicting coding parameters for a given rate. Our proposed rate control system can be easily integrated into existing learning-based video compression methods. The extensive experimental results show that the proposed method achieves accurate rate control on several baseline methods while also improving overall rate-distortion performance.

In this paper, we focus on mean-field variational Bayesian Neural Networks (BNNs) and explore the representation capacity of such BNNs by investigating which types of concepts are less likely to be encoded by the BNN. It has been observed and studied that a relatively small set of interactive concepts usually emerge in the knowledge representation of a sufficiently-trained neural network, and such concepts can faithfully explain the network output. Based on this, our study proves that compared to standard deep neural networks (DNNs), it is less likely for BNNs to encode complex concepts. Experiments verify our theoretical proofs. Note that the tendency to encode less complex concepts does not necessarily imply weak representation power, considering that complex concepts exhibit low generalization power and high adversarial vulnerability. The code is available at https://github.com/sjtu-xai-lab/BNN-concepts.