Related papers: USV: Unified Sparsification for Accelerating Video…
Despite the remarkable progress in deep generative models, synthesizing high-resolution and temporally coherent videos still remains a challenge due to their high-dimensionality and complex temporal dynamics along with large spatial…
Diffusion based video generation has received extensive attention and achieved considerable success within both the academic and industrial communities. However, current efforts are mainly concentrated on single-objective or single-task…
Diffusion models have recently advanced video restoration, but applying them to real-world video super-resolution (VSR) remains challenging due to high latency, prohibitive computation, and poor generalization to ultra-high resolutions. Our…
The efficiency of large vision-language models (LVLMs) is constrained by the computational bottleneck of the attention mechanism during the prefill phase and the memory bottleneck of fetching the key-value (KV) cache in the decoding phase,…
Diffusion Transformers are fundamental for video and image generation, but their efficiency is bottlenecked by the quadratic complexity of attention. While block sparse attention accelerates computation by attending only critical key-value…
This paper explores the innovative application of Stable Video Diffusion (SVD), a diffusion model that revolutionizes the creation of dynamic video content from static images. As digital media and design industries accelerate, SVD emerges…
Generating visual instructions in a given context is essential for developing interactive world simulators. While prior works address this problem through either text-guided image manipulation or video prediction, these tasks are typically…
Contemporary Video Object Segmentation (VOS) approaches typically consist stages of feature extraction, matching, memory management, and multiple objects aggregation. Recent advanced models either employ a discrete modeling for these…
Diffusion-based video super-resolution (VSR) has recently achieved remarkable fidelity but still suffers from prohibitive sampling costs. While distribution matching distillation (DMD) can accelerate diffusion models toward one-step…
Diffusion transformers exhibit remarkable video generation capability, yet their prohibitive computational and memory costs hinder practical deployment. Model quantization and attention sparsification are two promising directions for…
Standard Latent Diffusion Models rely on a complex, three-part architecture consisting of a separate encoder, decoder, and diffusion network, which are trained in multiple stages. This modular design is computationally inefficient, leads to…
In visual generation, the quadratic complexity of attention mechanisms results in high memory and computational costs, especially for longer token sequences required in high-resolution image or multi-frame video generation. To address this,…
The rapid development of large-scale deep learning models questions the affordability of hardware platforms, which necessitates the pruning to reduce their computational and memory footprints. Sparse neural networks as the product, have…
Do video-text transformers learn to model temporal relationships across frames? Despite their immense capacity and the abundance of multimodal training data, recent work has revealed the strong tendency of video-text models towards…
Diffusion models have demonstrated exceptional success in video super-resolution (VSR), exhibiting powerful capabilities for generating fine-grained details. However, their potential for space-time video super-resolution (STVSR), which…
Diffusion Transformers have demonstrated remarkable performance in video generation. However, their long input sequences incur substantial latency due to the quadratic complexity of full attention. Various sparse attention mechanisms have…
Image diffusion distillation achieves high-fidelity generation with very few sampling steps. However, applying these techniques directly to video diffusion often results in unsatisfactory frame quality due to the limited visual quality in…
Vision-language models (VLMs) have recently expanded from static image understanding to video reasoning, but their scalability is fundamentally limited by the quadratic cost of processing dense frame sequences. Long videos often exceed the…
Recent studies have highlighted the interplay between diffusion models and representation learning. Intermediate representations from diffusion models can be leveraged for downstream visual tasks, while self-supervised vision models can…
Recent video foundation models such as SAM2 excel at prompted video segmentation by treating masks as a general-purpose primitive. However, many real-world settings require unprompted segmentation that aims to detect and track all objects…