Related papers: Motion Prior Distillation in Time Reversal Samplin…
Diffusion probabilistic models learn to remove noise added during training, generating novel data (e.g., images) from Gaussian noise through sequential denoising. However, conditioning the generative process on corrupted or masked images is…
Upsampling videos of human activity is an interesting yet challenging task with many potential applications ranging from gaming to entertainment and sports broadcasting. The main difficulty in synthesizing video frames in this setting stems…
Iterative refinement methods based on a denoising-inversion cycle are powerful tools for enhancing the quality and control of diffusion models. However, their effectiveness is critically limited when combined with standard Classifier-Free…
RGB cameras excel at capturing rich texture details with high spatial resolution, whereas event cameras offer exceptional temporal resolution and a high dynamic range (HDR). Leveraging their complementary strengths can substantially enhance…
We propose progressive radiance distillation, an inverse rendering method that combines physically-based rendering with Gaussian-based radiance field rendering using a distillation progress map. Taking multi-view images as input, our method…
Due to the success of large-scale visual-language pretraining (VLP) models and the widespread use of image-text retrieval in industry areas, it is now critically necessary to reduce the model size and streamline their mobile-device…
Class-incremental learning aims to learn new classes in an incremental fashion without forgetting the previously learned ones. Several research works have shown how additional data can be used by incremental models to help mitigate…
Denoising Diffusion Models (DDMs) have become a popular tool for generating high-quality samples from complex data distributions. These models are able to capture sophisticated patterns and structures in the data, and can generate samples…
End-to-end motion planning models equipped with deep neural networks have shown great potential for enabling full autonomous driving. However, the oversized neural networks render them impractical for deployment on resource-constrained…
Deep learning models have emerged as a powerful tool for various medical applications. However, their success depends on large, high-quality datasets that are challenging to obtain due to privacy concerns and costly annotation. Generative…
The increased demand for 3D data in AR/VR, robotics and gaming applications, gave rise to powerful generative pipelines capable of synthesizing high-quality 3D objects. Most of these models rely on the Score Distillation Sampling (SDS)…
We pose a new problem, In-2-4D, for generative 4D (i.e., 3D + motion) inbetweening to interpolate two single-view images. In contrast to video/4D generation from only text or a single image, our interpolative task can leverage more precise…
The remarkable generative capabilities of diffusion models have motivated extensive research in both image and video editing. Compared to video editing which faces additional challenges in the time dimension, image editing has witnessed the…
Prior masked modeling motion generation methods predominantly study text-to-motion. We present DiMo, a discrete diffusion-style framework, which extends masked modeling to bidirectional text--motion understanding and generation. Unlike…
Although diffusion model has shown great potential for generating higher quality images than GANs, slow sampling speed hinders its wide application in practice. Progressive distillation is thus proposed for fast sampling by progressively…
Per-scene optimization methods such as 3D Gaussian Splatting provide state-of-the-art novel view synthesis quality but extrapolate poorly to under-observed areas. Methods that leverage generative priors to correct artifacts in these areas…
We introduce Adversarial Diffusion Distillation (ADD), a novel training approach that efficiently samples large-scale foundational image diffusion models in just 1-4 steps while maintaining high image quality. We use score distillation to…
To achieve real-time interactive video generation, current methods distill pretrained bidirectional video diffusion models into few-step autoregressive (AR) models, facing an architectural gap when full attention is replaced by causal…
We present InterHandGen, a novel framework that learns the generative prior of two-hand interaction. Sampling from our model yields plausible and diverse two-hand shapes in close interaction with or without an object. Our prior can be…
Recent advancements in timestep-distilled diffusion models have enabled high-quality image generation that rivals non-distilled multi-step models, but with significantly fewer inference steps. While such models are attractive for…