Related papers: Video Generation with Stable Transparency via Shif…

Scaling video diffusion transformers (DiTs) is limited by their quadratic 3D attention, even though most of the attention mass concentrates on a small subset of positions. We turn this observation into VSA, a trainable, hardware-efficient…

Achieving high-quality shadow removal with strong generalizability is challenging in scenes with complex global illumination. Due to the limited diversity in shadow removal datasets, current methods are prone to overfitting training data,…

Diffusion models have revolutionized image generation in recent years, yet they are still limited to a few sizes and aspect ratios. We propose ElasticDiffusion, a novel training-free decoding method that enables pretrained text-to-image…

Diffusion models generate new samples by progressively decreasing the noise from the initially provided random distribution. This inference procedure generally utilizes a trained neural network numerous times to obtain the final output,…

Stereo video generation has been gaining increasing attention with recent advancements in video diffusion models. However, most existing methods focus on generating 3D stereoscopic videos from monocular 2D videos. These approaches typically…

Generative models, particularly diffusion models, have made significant success in data synthesis across various modalities, including images, videos, and 3D assets. However, current diffusion models are computationally intensive, often…

Training generative adversarial networks is unstable in high-dimensions as the true data distribution tends to be concentrated in a small fraction of the ambient space. The discriminator is then quickly able to classify nearly all generated…

Successful forensic detectors can produce excellent results in supervised learning benchmarks but struggle to transfer to real-world applications. We believe this limitation is largely due to inadequate training data quality. While most…

Deep generative models have demonstrated the ability to create realistic audiovisual content, sometimes driven by domains of different nature. However, smooth temporal dynamics in video generation is a challenging problem. This work focuses…

Advancements in diffusion models have significantly improved video quality, directing attention to fine-grained controllability. However, many existing methods depend on fine-tuning large-scale video models for specific tasks, which becomes…

While recent years have witnessed great progress on using diffusion models for video generation, most of them are simple extensions of image generation frameworks, which fail to explicitly consider one of the key differences between videos…

Graph is a flexible and effective tool to represent complex structures in practice and graph neural networks (GNNs) have been shown to be effective on various graph tasks with randomly separated training and testing data. In real…

Talking face generation has historically struggled to produce head movements and natural facial expressions without guidance from additional reference videos. Recent developments in diffusion-based generative models allow for more realistic…

Continuous video monitoring in surveillance, robotics, and wearable systems faces a fundamental power constraint: conventional RGB cameras consume substantial energy through fixed-rate capture. Event cameras offer sparse, motion-driven…

In this paper, we present VideoGen, a text-to-video generation approach, which can generate a high-definition video with high frame fidelity and strong temporal consistency using reference-guided latent diffusion. We leverage an…

Large-scale video diffusion models achieve impressive visual quality, yet often fail to preserve geometric consistency. Prior approaches improve consistency either by augmenting the generator with additional modules or applying…

Modern video generative models based on diffusion models can produce very realistic clips, but they are computationally inefficient, often requiring minutes of GPU time for just a few seconds of video. This inefficiency poses a critical…

While recent foundational video generators produce visually rich output, they still struggle with appearance drift, where objects gradually degrade or change inconsistently across frames, breaking visual coherence. We hypothesize that this…

There is a bias in the inference pipeline of most diffusion models. This bias arises from a signal leak whose distribution deviates from the noise distribution, creating a discrepancy between training and inference processes. We demonstrate…

Advances in multimaterial 3D printing have the potential to reproduce various visual appearance attributes of an object in addition to its shape. Since many existing 3D file formats encode color and translucency by RGBA textures mapped to…