Related papers: Flexible Architecture for Real-time Processing of …
Video diffusion models have rapidly become the dominant paradigm for high-fidelity generative video synthesis, but their practical deployment remains constrained by severe inference costs. Compared with image generation, video synthesis…
All-optical image processing provides a fast and energy-efficient alternative to conventional electronic systems by directly manipulating optical wavefronts. However, metasurface-based optical processors reported to date are often limited…
Motion-based video frame interpolation commonly relies on optical flow to warp pixels from the inputs to the desired interpolation instant. Yet due to the inherent challenges of motion estimation (e.g. occlusions and discontinuities), most…
Multi-camera systems have been shown to improve the accuracy and robustness of SLAM estimates, yet state-of-the-art SLAM systems predominantly support monocular or stereo setups. This paper presents a generic sparse visual SLAM framework…
Heterogeneous many-cores are now an integral part of modern computing systems ranging from embedding systems to supercomputers. While heterogeneous many-core design offers the potential for energy-efficient high-performance, such potential…
We study the problem of determining whether a given temporal specification can be implemented by a symmetric system, i.e., a system composed from identical components. Symmetry is an important goal in the design of distributed systems,…
In this work, we first propose a fully differentiable Many-to-Many (M2M) splatting framework to interpolate frames efficiently. Given a frame pair, we estimate multiple bidirectional flows to directly forward warp the pixels to the desired…
Multi-modal learning from video data has seen increased attention recently as it allows to train semantically meaningful embeddings without human annotation enabling tasks like zero-shot retrieval and classification. In this work, we…
Video frame interpolation is a challenging problem because there are different scenarios for each video depending on the variety of foreground and background motion, frame rate, and occlusion. It is therefore difficult for a single network…
We present Vchitect-2.0, a parallel transformer architecture designed to scale up video diffusion models for large-scale text-to-video generation. The overall Vchitect-2.0 system has several key designs. (1) By introducing a novel…
Video diffusion models have made substantial progress in various video generation applications. However, training models for long video generation tasks require significant computational and data resources, posing a challenge to developing…
Volumetric video relighting is essential for bringing captured performances into virtual worlds, but current approaches struggle to deliver temporally stable, production-ready results. Diffusion-based intrinsic decomposition methods show…
This paper presents a cross-layer video delivery scheme, StreamOptix, and proposes a joint optimization algorithm for video delivery that leverages the characteristics of the physical (PHY), medium access control (MAC), and application…
Despite its significant achievements in large-scale scene reconstruction, 3D Gaussian Splatting still faces substantial challenges, including slow processing, high computational costs, and limited geometric accuracy. These core issues arise…
MIMO (multiple input, multiple output) approaches are a recent trend in neural network architectures for video restoration problems, where each network evaluation produces multiple output frames. The video is split into non-overlapping…
Region proposal is critical for object detection while it usually poses a bottleneck in improving the computation efficiency on traditional control-flow architectures. We have observed region proposal tasks are potentially suitable for…
This paper presents a reconfigurable parallel data flow architecture. This architecture uses the concepts of multi-agent paradigm in reconfigurable hardware systems. The utilization of this new paradigm has the potential to greatly increase…
We present a polarization-insensitive metasurface processor to perform spatial asymmetric filtering of an incident optical beam, thereby allowing for real-time parallel optical processing. To enable massive parallel processing, we introduce…
In embedded vision systems, parallel computation of the integral image presents several design challenges in terms of hardware resources, speed and power consumption. Although recursive equations significantly reduce the number of…
The development of composable systems architecture marks a significant shift in resource allocation and utilization within data centers. This paper presents a composable architecture scaling up to 32 GPUs on a single node, addressing the…