Related papers: Fast-Vid2Vid: Spatial-Temporal Compression for Vid…
Recent research has revealed that reducing the temporal and spatial redundancy are both effective approaches towards efficient video recognition, e.g., allocating the majority of computation to a task-relevant subset of frames or the most…
We introduce FSVideo, a fast speed transformer-based image-to-video (I2V) diffusion framework. We build our framework on the following key components: 1.) a new video autoencoder with highly-compressed latent space ($64\times64\times4$…
Image-to-Video generation (I2V) animates a static image into a temporally coherent video sequence following textual instructions, yet preserving fine-grained object identity under changing viewpoints remains a persistent challenge. Unlike…
Demand for 2K video synthesis is rising with increasing consumer expectations for ultra-clear visuals. While diffusion transformers (DiTs) have demonstrated remarkable capabilities in high-quality video generation, scaling them to 2K…
Generating videos predicting the future of a given sequence has been an area of active research in recent years. However, an essential problem remains unsolved: most of the methods require large computational cost and memory usage for…
Most text-video retrieval methods utilize the text-image pre-trained models like CLIP as a backbone. These methods process each sampled frame independently by the image encoder, resulting in high computational overhead and limiting…
Conditional image-to-video (cI2V) generation aims to synthesize a new plausible video starting from an image (e.g., a person's face) and a condition (e.g., an action class label like smile). The key challenge of the cI2V task lies in the…
Text-to-video diffusion models enable the generation of high-quality videos that follow text instructions, making it easy to create diverse and individual content. However, existing approaches mostly focus on high-quality short video…
Masked-based autoregressive models have demonstrated promising image generation capability in continuous space. However, their potential for video generation remains under-explored. In this paper, we propose \textbf{VideoMAR}, a concise and…
Learned video compression (LVC) has witnessed remarkable advancements in recent years. Similar as the traditional video coding, LVC inherits motion estimation/compensation, residual coding and other modules, all of which are implemented…
We propose Latent-Shift -- an efficient text-to-video generation method based on a pretrained text-to-image generation model that consists of an autoencoder and a U-Net diffusion model. Learning a video diffusion model in the latent space…
Contemporary models for generating images show remarkable quality and versatility. Swayed by these advantages, the research community repurposes them to generate videos. Since video content is highly redundant, we argue that naively…
We study the compression of spatial and temporal features in fluid flow data using multimedia compression techniques. The efficacy of spatial compression techniques, including JPEG and JPEG2000 (JP2), and spatio-temporal video compression…
With the rapid growth of large-scale video analytics applications, edge-cloud collaborative systems have become the dominant paradigm for real-time inference. However, existing approaches often fail to dynamically adapt to heterogeneous…
Video generation requires synthesizing consistent and persistent frames with dynamic content over time. This work investigates modeling the temporal relations for composing video with arbitrary length, from a few frames to even infinite,…
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…
Training robust deep video representations has proven to be computationally challenging due to substantial decoding overheads, the enormous size of raw video streams, and their inherent high temporal redundancy. Different from existing…
Image-to-video (I2V) generation aims to use the initial frame (alongside a text prompt) to create a video sequence. A grand challenge in I2V generation is to maintain visual consistency throughout the video: existing methods often struggle…
Compared to images, videos better reflect real-world acquisition and possess valuable temporal cues. However, existing multi-sensor fusion research predominantly integrates complementary context from multiple images rather than videos due…
Generating synthetic multi-view images from a text prompt is an essential bridge to generating synthetic 3D assets. In this work, we introduce RapidMV, a novel text-to-multi-view generative model that can produce 32 multi-view synthetic…