相关论文: DropletVideo: A Dataset and Approach to Explore In…
Video generation aims to produce temporally coherent sequences of visual frames, representing a pivotal advancement in Artificial Intelligence Generated Content (AIGC). Compared to static image generation, video generation poses unique…
Millions of surveillance cameras operate at 24x7 generating huge amount of visual data for processing. However, retrieval of important activities from such a large data can be time consuming. Thus, researchers are working on finding…
Scaling laws have validated the success and promise of large-data-trained models in creative generation across text, image, and video domains. However, this paradigm faces data scarcity in the 3D domain, as there is far less of it available…
We present a video generation model that accurately reproduces object motion, changes in camera viewpoint, and new content that arises over time. Existing video generation methods often fail to produce new content as a function of time…
Leveraging the generative ability of image diffusion models offers great potential for zero-shot video-to-video translation. The key lies in how to maintain temporal consistency across generated video frames by image diffusion models.…
Text-to-video generation is expensive, so only a few samples are typically produced per prompt. In this low-sample regime, maximizing the value of each batch requires high cross-video diversity. Recent methods improve diversity for image…
This work addresses the challenge of streamed video depth estimation, which expects not only per-frame accuracy but, more importantly, cross-frame consistency. We argue that sharing contextual information between frames or clips is pivotal…
Temporal consistency is critical in video prediction to ensure that outputs are coherent and free of artifacts. Traditional methods, such as temporal attention and 3D convolution, may struggle with significant object motion and may not…
Video generation has many unique challenges beyond those of image generation. The temporal dimension introduces extensive possible variations across frames, over which consistency and continuity may be violated. In this study, we move…
Subject-to-video generation has witnessed substantial progress in recent years. However, existing models still face significant challenges in faithfully following textual instructions. This limitation, commonly known as the copy-paste…
Video depth estimation has long been hindered by the scarcity of consistent and scalable ground truth data, leading to inconsistent and unreliable results. In this paper, we introduce Depth Any Video, a model that tackles the challenge…
With the explosive popularity of AI-generated content (AIGC), video generation has recently received a lot of attention. Generating videos guided by text instructions poses significant challenges, such as modeling the complex relationship…
Video content comprehension is essential for various applications, ranging from video analysis to interactive systems. Despite advancements in large-scale vision-language models (VLMs), these models often struggle to capture the nuanced,…
Generating long-form storytelling videos with consistent visual narratives remains a significant challenge in video synthesis. We present a novel framework, dataset, and a model that address three critical limitations: background…
Existing video generation models struggle to maintain long-term spatial and temporal consistency due to the dense, high-dimensional nature of video signals. To overcome this limitation, we propose Spatia, a spatial memory-aware video…
Spatially consistent long-horizon video generation aims to maintain temporal and spatial consistency along predefined camera trajectories. Existing methods mostly entangle memory modeling with video generation, leading to inconsistent…
High-quality video generation is crucial for many fields, including the film industry and autonomous driving. However, generating videos with spatiotemporal consistencies remains challenging. Current methods typically utilize attention…
We present a novel framework for compositional video synthesis that leverages temporally consistent object-centric representations, extending our previous work, SlotAdapt, from images to video. While existing object-centric approaches…
Video prediction is a pixel-wise dense prediction task to infer future frames based on past frames. Missing appearance details and motion blur are still two major problems for current predictive models, which lead to image distortion and…
We present the Moments in Time Dataset, a large-scale human-annotated collection of one million short videos corresponding to dynamic events unfolding within three seconds. Modeling the spatial-audio-temporal dynamics even for actions…