Related papers: On the Content Bias in Fr\'echet Video Distance
Fr\'echet Inception Distance (FID) is the primary metric for ranking models in data-driven generative modeling. While remarkably successful, the metric is known to sometimes disagree with human judgement. We investigate a root cause of…
In last decade, ever growing internet technologies provided platform to share the multimedia data among different communities. As the ultimate users are human subjects who are concerned about quality of visual information, it is often…
In this article, we highlight what appears to be major issue of Variational Autoencoders, evinced from an extensive experimentation with different network architectures and datasets: the variance of generated data is significantly lower…
Technological advances in sensors have paved the way for digital cameras to become increasingly ubiquitous, which, in turn, led to the popularity of the self-recording culture. As a result, the amount of visual data on the Internet is…
How can we tell whether a video has been sped up or slowed down? How can we generate videos at different speeds? Although videos have been central to modern computer vision research, little attention has been paid to perceiving and…
High frame rates have been known to enhance the perceived visual quality of specific video content. However, the lack of investigation of high frame rates has restricted the expansion of this research field particularly in the context of…
Although several 2D quality metrics have been proposed for images and videos, in the case of 3D efforts are only at the initial stages. In this paper, we propose a new full-reference quality metric for 3D content. Our method is modeled…
Most existing real-time deep models trained with each frame independently may produce inconsistent results across the temporal axis when tested on a video sequence. A few methods take the correlations in the video sequence into…
Video generation models have achieved notable progress in static scenarios, yet their performance in motion video generation remains limited, with quality degrading under drastic dynamic changes. This is due to noise disrupting temporal…
Neural style transfer models have been used to stylize an ordinary video to specific styles. To ensure temporal inconsistency between the frames of the stylized video, a common approach is to estimate the optic flow of the pixels in the…
While video compression algorithms effectively reduce bitrate, aggressive quantization often compromises temporal coherence, introducing artifacts such as flicker, motion inconsistency, and unstable textures. Although spatial quality…
Recent advancements in video generation have substantially improved visual quality and temporal coherence, making these models increasingly appealing for applications such as autonomous driving, particularly in the context of driving…
Diffusion models have revolutionized image generation, and their extension to video generation has shown promise. However, current video diffusion models~(VDMs) rely on a scalar timestep variable applied at the clip level, which limits…
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…
Virtual Reality is regaining attention due to recent advancements in hardware technology. Immersive images / videos are becoming widely adopted to carry omnidirectional visual information. However, due to the requirements for higher spatial…
Generating temporally coherent high fidelity video is an important milestone in generative modeling research. We make progress towards this milestone by proposing a diffusion model for video generation that shows very promising initial…
Modern metrics for generative learning like Fr\'echet Inception Distance (FID) and DINOv2-Fr\'echet Distance (FD-DINOv2) demonstrate impressive performance. However, they suffer from various shortcomings, like a bias towards specific…
The growth of Social Networks has fueled the habit of people logging their day-to-day activities, and long First-Person Videos (FPVs) are one of the main tools in this new habit. Semantic-aware fast-forward methods are able to decrease the…
Dataset distillation aims to synthesize compact yet informative datasets that allow models trained on them to achieve performance comparable to training on the full dataset. While this approach has shown promising results for image data,…
Video diffusion models have recently made great progress in generation quality, but are still limited by the high memory and computational requirements. This is because current video diffusion models often attempt to process…