Related papers: Authoring image decompositions with generative mod…

Variational autoencoders (VAEs) have received much attention recently as an end-to-end architecture for text generation with latent variables. In this paper, we investigate several multi-level structures to learn a VAE model to generate…

Novel view synthesis from a single image has recently achieved remarkable results, although the requirement of some form of 3D, pose, or multi-view supervision at training time limits the deployment in real scenarios. This work aims at…

Haze and smog are among the most common environmental factors impacting image quality and, therefore, image analysis. This paper proposes an end-to-end generative method for image dehazing. It is based on designing a fully convolutional…

The advancement of generative radiance fields has pushed the boundary of 3D-aware image synthesis. Motivated by the observation that a 3D object should look realistic from multiple viewpoints, these methods introduce a multi-view constraint…

We propose a MultiScale AutoEncoder(MSAE) based extreme image compression framework to offer visually pleasing reconstruction at a very low bitrate. Our method leverages the "priors" at different resolution scale to improve the compression…

We tackle the problem of automatically reconstructing a complete 3D model of a scene from a single RGB image. This challenging task requires inferring the shape of both visible and occluded surfaces. Our approach utilizes viewer-centered,…

We propose spatially-adaptive normalization, a simple but effective layer for synthesizing photorealistic images given an input semantic layout. Previous methods directly feed the semantic layout as input to the deep network, which is then…

Learned progressive image compression is gaining momentum as it allows improved image reconstruction as more bits are decoded at the receiver. We propose a progressive image compression method in which an image is first represented as a…

We present a conditional variational auto-encoder (VAE) which, to avoid the substantial cost of training from scratch, uses an architecture and training objective capable of leveraging a foundation model in the form of a pretrained…

Interpreting computations in the visual cortex as learning and inference in a generative model of the environment has received wide support both in neuroscience and cognitive science. However, hierarchical computations, a hallmark of visual…

The usage of deep generative models for image compression has led to impressive performance gains over classical codecs while neural video compression is still in its infancy. Here, we propose an end-to-end, deep generative modeling…

Recent progress on image captioning has made it possible to generate novel sentences describing images in natural language, but compressing an image into a single sentence can describe visual content in only coarse detail. While one new…

State-of-the-art approaches for image captioning require supervised training data consisting of captions with paired image data. These methods are typically unable to use unsupervised data such as textual data with no corresponding images,…

Deep neural networks, in particular convolutional neural networks, have become highly effective tools for compressing images and solving inverse problems including denoising, inpainting, and reconstruction from few and noisy measurements.…

We present a method that tackles the challenge of predicting color and depth behind the visible content of an image. Our approach aims at building up a Layered Depth Image (LDI) from a single RGB input, which is an efficient representation…

For humans, visual understanding is inherently generative: given a 3D shape, we can postulate how it would look in the world; given a 2D image, we can infer the 3D structure that likely gave rise to it. We can thus translate between the 2D…

In semantic image synthesis the state of the art is dominated by methods that use customized variants of the SPatially-Adaptive DE-normalization (SPADE) layers, which allow for good visual generation quality and editing versatility. By…

In this paper, we treat the image generation task using an autoencoder, a representative latent model. Unlike many studies regularizing the latent variable's distribution by assuming a manually specified prior, we approach the image…

Rich feature representations derived from CLIP-ViT have been widely utilized in AI-generated image detection. While most existing methods primarily leverage features from the final layer, we systematically analyze the contributions of…

Probabilistic generative models are attractive for scientific modeling because their inferred parameters can be used to generate hypotheses and design experiments. This requires that the learned model provide an accurate representation of…