Video editing with diffusion models presents significant challenges, especially under real-time constraints. Current methods either enhance temporal consistency at the cost of slow processing or rely on frame-by-frame editing, leading to flickering and temporal artifacts. To address both challenges, we propose SmoothDiffusion-VE, a streaming-based editing approach that improves temporal consistency and processing speed through our proposed Adaptive Feature Cache (AFC) and motion-guided attention. The AFC dynamically adjusts the caching behavior based on perceptual similarity (LPIPS) between frames, i.e., shifting to a mini-cache mode for similar frames to reduce computational load. Conversely, significant frame changes trigger deeper caching to maintain robust temporal coherence. Our motion-guided attention selectively focuses on dynamic regions using optical flow, reducing unnecessary computations in static areas and accelerating processing. SmoothDiffusion-VE can run 28 FPS on one RTX 4090 GPU, achieving a 1564× speedup over Plug-and-Play Diffusion (PNP) and a 1916× speedup over Diffusion Motion Transfer (DMT), delivering a powerful solution for fast and consistent video editing.

Abstract Even with the advent of hardware‐accelerated ray tracing in modern GPUs, only a small number of rays can be traced at each pixel in real‐time applications. This presents a significant challenge for path tracing, even when augmented with state‐of‐the art denoising algorithms. While the recently‐developed ReSTIR algorithm [BWP∗20] enables high‐quality renderings of scenes with millions of light sources using just a few shadow rays at each pixel, there remains a need for effective algorithms to sample indirect illumination. We introduce an effective path sampling algorithm for indirect lighting that is suitable to highly parallel GPU architectures. Building on the screen‐space spatio‐temporal resampling principles of ReSTIR, our approach resamples multi‐bounce indirect lighting paths obtained by path tracing. Doing so allows sharing information about important paths that contribute to lighting both across time and pixels in the image. The resulting algorithm achieves a substantial error reduction compared to path tracing: at a single sample per pixel every frame, our algorithm achieves MSE improvements ranging from 9.3× to 166× in our test scenes. In conjunction with a denoiser, it leads to high‐quality path traced global illumination at real‐time frame rates on modern GPUs.

Abstract Real‐time ray tracing (RTRT) is being pervasively applied. The key to RTRT is a reliable denoising scheme that reconstructs clean images from significantly undersampled noisy inputs, usually at 1 sample per pixel as limited by current hardware's computing power. The state of the art reconstruction methods all rely on temporal filtering to find correspondences of current pixels in the previous frame, described using per‐pixel screen‐space motion vectors. While these approaches are demonstrated powerful, they suffer from a common issue that the temporal information cannot be used when the motion vectors are not valid, i.e. when temporal correspondences are not obviously available or do not exist in theory. We introduce temporally reliable motion vectors that aim at deeper exploration of temporal coherence, especially for the generally‐believed difficult applications on shadows, glossy reflections and occlusions, with the key idea to detect and track the cause of each effect. We show that our temporally reliable motion vectors produce significantly better temporal results on a variety of dynamic scenes when compared to the state of the art methods, but with negligible performance overhead.

Both the frame rate and the latency are crucial to the performance of realtime rendering applications such as video games. Spatial supersampling methods, such as the Deep Learning SuperSampling (DLSS), have been proven successful at decreasing the rendering time of each frame by rendering at a lower resolution. But temporal supersampling methods that directly aim at producing more frames on the fly are still not practically available. This is mainly due to both its own computational cost and the latency introduced by interpolating frames from the future. In this paper, we present ExtraNet, an efficient neural network that predicts accurate shading results on an extrapolated frame, to minimize both the performance overhead and the latency. With the help of the rendered auxiliary geometry buffers of the extrapolated frame, and the temporally reliable motion vectors, we train our ExtraNet to perform two tasks simultaneously: irradiance in-painting for regions that cannot find historical correspondences, and accurate ghosting-free shading prediction for regions where temporal information is available. We present a robust hole-marking strategy to automate the classification of these tasks, as well as the data generation from a series of high-quality production-ready scenes. Finally, we use lightweight gated convolutions to enable fast inference. As a result, our ExtraNet is able to produce plausibly extrapolated frames without easily noticeable artifacts, delivering a 1.5× to near 2× increase in frame rates with minimized latency in practice.

With the explosive development of big data, it is necessary to sort the data according to their importance or priorities. The sources with different importance levels can be modeled by the multilevel diversity coding systems (MDCS). Another trend in future communication networks, say 5G wireless networks and Internet of Things, is that users may obtain their data from all available sources, even from devices belonging to other users. Then, the privacy of data becomes a crucial issue. In a recent work by Li et al., the secure asymmetric MDCS (S-AMDCS) with wiretap channels was investigated, where the wiretapped messages do not leak any information about the sources (i.e. perfect secrecy). It was shown that superposition (source-separate coding) is not optimal for the general S-AMDCS and the exact full secure rate region was proved for a class of S-AMDCS. In addition, a bound on the key size of the secure rate region was provided as well. As a further step on the SAMDCS problem, this paper mainly focuses on the key size characterization. Specifically, the constraints on the key size of superposition secure rate region are proved and a counterexample is found to show that the bound on the key size of the exact secure rate region provided by Li et al. is not tight. In contrast, tight necessary and sufficient constraints on the secrecy key size of the counterexample, which is the four-encoder S-AMDCS, are proved.

Synthesizing larger texture images from a smaller exemplar is an important task in graphics and vision. The conventional CNNs, recently adopted for synthesis, require to train and test on the same set of images and fail to generalize to unseen images. This is mainly because those CNNs fully rely on convolutional and upsampling layers that operate locally and not suitable for a task as global as texture synthesis. In this work, inspired by the repetitive nature of texture patterns, we find that texture synthesis can be viewed as (local) \textit{upsampling} in the Fast Fourier Transform (FFT) domain. However, FFT of natural images exhibits high dynamic range and lacks local correlations. Therefore, to train CNNs we design a framework to perform FFT upsampling in feature space using deformable convolutions. Such design allows our framework to generalize to unseen images, and synthesize textures in a single pass. Extensive evaluations confirm that our method achieves state-of-the-art performance both quantitatively and qualitatively.

Abstract Temporal Antialiasing (TAA), formally defined as temporally‐amortized supersampling, is the most widely used antialiasing technique in today's real‐time renderers and game engines. This survey provides a systematic overview of this technique. We first review the history of TAA, its development path and related work. We then identify the two main sub‐components of TAA, sample accumulation and history validation, and discuss algorithmic and implementation options. As temporal upsampling is becoming increasingly relevant to today's game engines, we propose an extension of our TAA formulation to cover a variety of temporal upsampling techniques. Despite the popularity of TAA, there are still significant unresolved technical challenges that affect image quality in many scenarios. We provide an in‐depth analysis of these challenges, and review existing techniques for improvements. Finally, we summarize popular algorithms and topics that are closely related to TAA. We believe the rapid advances in those areas may either benefit from or feedback into TAA research and development.

The partially collaborative repair of multiple node failures in distributed storage systems is investigated. An exact-repair code is constructed using a bilinear form, which achieves the minimum-bandwidth partially collaborative repair (MBPCR) point. When the storage capacity is minimum, the problem of repairing multi-node failures using a Maximum Distance Separable (MDS) array code is also investigated. The minimum-storage partially collaborative repair (MSPCR) problem with same number of repairing and reconstruction nodes has been studied before. In this paper, the scenario where the number of repairing nodes is greater than that of reconstruction nodes and the storage capacity is already minimal for partial collaboration is considered. An MDS array code is constructed, which asymptotically achieves the MSPCR point. Further, we show that the given code construction could not always have a regular collaborative structure.

The problem of exact-repair regenerating codes against eavesdropping attack is studied. The eavesdropping model we consider is that the eavesdropper has the capability to observe the data involved in the repair of a subset of I nodes. An (n, k, d, I) secure exact-repair regenerating code is an (n, k, d) exact-repair regenerating code that is secure under this eavesdropping model. It has been shown that for some parameters (n, k, d, I), the associated optimal storage-bandwidth tradeoff curve, which has one corner point, can be determined. The focus of this paper is on characterizing such parameters. We establish a lower bound ℓ̂ on the number of wiretap nodes, and show that this bound is tight for the case k = d = n - 1.

The problem of exact-repair regenerating codes against eavesdropping attack is studied. The eavesdropping model we consider is that the eavesdropper has the capability to observe the data involved in the repair of a subset of l nodes. Under this security constraint, it has been shown that the optimal tradeoff curve has a single corner point for some (n, k, d, l). The focus of this paper is on finding parameters (n, k, d, l) whose associated tradeoff curve has this behavior. For k=d=n-1, we prove that the tradeoff curve has a single corner point if and only if l ≥ [[1/4](d-1)]. Previously, it was known that the tradeoff curve has a single corner point if l ≥ [(√d-1)2].

Plesiosaurians are an extinct group of highly derived Mesozoic marine reptiles with a global distribution that spans 135 million years from the Early Jurassic to the Late Cretaceous. During their long evolutionary history they maintained a unique body plan with two pairs of large wing-like flippers, but their locomotion has been a topic of debate for almost 200 years. Key areas of controversy have concerned the most efficient biologically possible limb stroke, e.g. whether it consisted of rowing, underwater flight, or modified underwater flight, and how the four limbs moved in relation to each other: did they move in or out of phase? Previous studies have investigated plesiosaur swimming using a variety of methods, including skeletal analysis, human swimmers, and robotics. We adopt a novel approach using a digital, three-dimensional, articulated, free-swimming plesiosaur in a simulated fluid. We generated a large number of simulations under various joint degrees of freedom to investigate how the locomotory repertoire changes under different parameters. Within the biologically possible range of limb motion, the simulated plesiosaur swims primarily with its forelimbs using an unmodified underwater flight stroke, essentially the same as turtles and penguins. In contrast, the hindlimbs provide relatively weak thrust in all simulations. We conclude that plesiosaurs were forelimb-dominated swimmers that used their hind limbs mainly for maneuverability and stability.

We consider the design of codes for distributed storage systems that are amenable to repair. We introduce the notion of partial collaboration to capture the property that nodes participating in a repair process may collaborate to different extents, bringing more nuances to the known cases: no collaboration or full collaboration during repair. We compute for this scenario the storage (per node) when the repair bandwidth (per node) is minimal, and conversely the repair bandwidth when the storage is minimal. We provide a generic code construction that enables repair of several failures through partial collaboration.