相关论文: VDOT: Efficient Unified Video Creation via Optimal…

Dataset distillation provides an effective approach to reduce memory and computational costs by optimizing a compact dataset that achieves performance comparable to the full original. However, for large-scale datasets and complex deep…

Text-to-video diffusion models have advanced video generation significantly. However, customizing these models to generate videos with tailored motions presents a substantial challenge. In specific, they encounter hurdles in (a) accurately…

Recently, a series of diffusion-aware distillation algorithms have emerged to alleviate the computational overhead associated with the multi-step inference process of Diffusion Models (DMs). Current distillation techniques often dichotomize…

We present FloVD, a novel video diffusion model for camera-controllable video generation. FloVD leverages optical flow to represent the motions of the camera and moving objects. This approach offers two key benefits. Since optical flow can…

Dataset distillation compresses large datasets into compact synthetic ones to reduce storage and computational costs. Among various approaches, distribution matching (DM)-based methods have attracted attention for their high efficiency.…

High-quality computer vision models typically address the problem of understanding the general distribution of real-world images. However, most cameras observe only a very small fraction of this distribution. This offers the possibility of…

Discrete diffusion models are a new class of text generators that offer advantages such as bidirectional context use, parallelizable generation, and flexible prompting compared to autoregressive models. However, a critical limitation of…

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…

We present a new method for making diffusion models faster to sample. The method distills many-step diffusion models into few-step models by matching conditional expectations of the clean data given noisy data along the sampling trajectory.…

Video generation requires modeling a vast spatiotemporal space, which demands significant computational resources and data usage. To reduce the complexity, the prevailing approaches employ a cascaded architecture to avoid direct training…

Diffusion models achieve high-quality sample generation at the cost of a lengthy multistep inference procedure. To overcome this, diffusion distillation techniques produce student generators capable of matching or surpassing the teacher in…

Controllable video generation has attracted significant attention, largely due to advances in video diffusion models. In domains such as autonomous driving, it is essential to develop highly accurate predictions for object motions. This…

Real-time video generation via diffusion is essential for building general-purpose multimodal interactive AI systems. However, the simultaneous denoising of all video frames with bidirectional attention via an iterative process in diffusion…

The recent large-scale vision-language pre-training (VLP) of dual-stream architectures (e.g., CLIP) with a tremendous amount of image-text pair data, has shown its superiority on various multimodal alignment tasks. Despite its success, the…

Diffusion Transformer(DiT)-based generation models have achieved remarkable success in video generation. However, their inherent computational demands pose significant efficiency challenges. In this paper, we exploit the inherent temporal…

Motion Object Segmentation (MOS) is crucial for autonomous driving, as it enhances localization, path planning, map construction, scene flow estimation, and future state prediction. While existing methods achieve strong performance,…

Diffusion models have revolutionized video generation, becoming essential tools in creative content generation and physical simulation. Transformer-based architectures (DiTs) and classifier-free guidance (CFG) are two cornerstones of this…

Knowledge distillation as an efficient knowledge transfer technique, has achieved remarkable success in unimodal scenarios. However, in cross-modal settings, conventional distillation methods encounter significant challenges due to data and…

Diffusion Transformer (DiT), an emerging diffusion model for visual generation, has demonstrated superior performance but suffers from substantial computational costs. Our investigations reveal that these costs primarily stem from the…

Few-step video generation has been significantly advanced by consistency distillation. However, the performance of consistency-distilled models often degrades as more sampling steps are allocated at test time, limiting their effectiveness…