相关论文: f-VAEs: Improve VAEs with Conditional Flows

Normalizing flows and variational autoencoders are powerful generative models that can represent complicated density functions. However, they both impose constraints on the models: Normalizing flows use bijective transformations to model…

Flow maps enable high-quality image generation in a single forward pass. However, unlike iterative diffusion models, their lack of an explicit sampling trajectory impedes incorporating external constraints for conditional generation and…

As a widely recognized approach to deep generative modeling, Variational Auto-Encoders (VAEs) still face challenges with the quality of generated images, often presenting noticeable blurriness. This issue stems from the unrealistic…

Flow-based generative models have highly desirable properties like exact log-likelihood evaluation and exact latent-variable inference, however they are still in their infancy and have not received as much attention as alternative…

We develop Riemannian approaches to variational autoencoders (VAEs) for PDE-type ambient data with regularizing geometric latent dynamics, which we refer to as VAE-DLM, or VAEs with dynamical latent manifolds. We redevelop the VAE framework…

Underwater Image Enhancement (UIE) aims to restore visibility and correct color distortions caused by wavelength-dependent absorption and scattering. Recent hybrid approaches, which couple domain priors with modern deep neural…

Traditional fluid dynamics simulation pipelines combine numerical solvers with rendering, producing highly realistic results but at considerable computational cost. Diffusion-based generative video models offer a faster alternative, yet…

Predicting future frames for a video sequence is a challenging generative modeling task. Promising approaches include probabilistic latent variable models such as the Variational Auto-Encoder. While VAEs can handle uncertainty and model…

Recent studies have shown remarkable success in face manipulation task with the advance of GANs and VAEs paradigms, but the outputs are sometimes limited to low-resolution and lack of diversity. In this work, we propose Additive Focal…

We present a method to downscale idealized geophysical fluid simulations using generative models based on diffusion maps. By analyzing the Fourier spectra of images drawn from different data distributions, we show how one can chain together…

Unmanned underwater image analysis for marine monitoring faces two key challenges: (i) degraded image quality due to light attenuation and (ii) hardware storage constraints limiting high-resolution image collection. Existing methods…

Significant progress has been made for estimating optical flow using deep neural networks. Advanced deep models achieve accurate flow estimation often with a considerable computation complexity and time-consuming training processes. In this…

Visual counterfactual explanation (CF) methods modify image concepts, e.g, shape, to change a prediction to a predefined outcome while closely resembling the original query image. Unlike self-explainable models (SEMs) and heatmap…

Normalizing flows are a powerful class of generative models for continuous random variables, showing both strong model flexibility and the potential for non-autoregressive generation. These benefits are also desired when modeling discrete…

Normalizing Flows (NFs) are likelihood-based models for continuous inputs. They have demonstrated promising results on both density estimation and generative modeling tasks, but have received relatively little attention in recent years. In…

This paper introduces Goku, a state-of-the-art family of joint image-and-video generation models leveraging rectified flow Transformers to achieve industry-leading performance. We detail the foundational elements enabling high-quality…

The text-guided video inpainting technique has significantly improved the performance of content generation applications. A recent family for these improvements uses diffusion models, which have become essential for achieving high-quality…

Efficient image tokenization with high compression ratios remains a critical challenge for training generative models. We present SoftVQ-VAE, a continuous image tokenizer that leverages soft categorical posteriors to aggregate multiple…

The spatially-varying field of the human visual system has recently received a resurgence of interest with the development of virtual reality (VR) and neural networks. The computational demands of high resolution rendering desired for VR…

Recently normalizing flows (NFs) have demonstrated state-of-the-art performance on modeling 3D point clouds while allowing sampling with arbitrary resolution at inference time. However, these flow-based models still require long training…