相关论文: Pixel-Aligned Multi-View Generation with Depth Gui…

Variational auto-encoders (VAEs) provide an attractive solution to image generation problem. However, they tend to produce blurred and over-smoothed images due to their dependence on pixel-wise reconstruction loss. This paper introduces a…

Text-to-3D generation, which synthesizes 3D assets according to an overall text description, has significantly progressed. However, a challenge arises when the specific appearances need customizing at designated viewpoints but referring…

Text-to-image diffusion models, which are theoretically equivalent to score-based generative models, generate images through a multi-step denoising process guided by text embeddings extracted from pretrained vision-language models such as…

Generating consistent multiple views for 3D reconstruction tasks is still a challenge to existing image-to-3D diffusion models. Generally, incorporating 3D representations into diffusion model decrease the model's speed as well as…

Multimodal variational autoencoders have demonstrated their ability to learn the relationships between different modalities by mapping them into a latent representation. Their design and capacity to perform any-to-any conditional and…

Layout-to-image generation refers to the task of synthesizing photo-realistic images based on semantic layouts. In this paper, we propose LayoutDiffuse that adapts a foundational diffusion model pretrained on large-scale image or text-image…

Recently, text-to-image generation models have achieved remarkable advancements, particularly with diffusion models facilitating high-quality image synthesis from textual descriptions. However, these models often struggle with achieving…

Signal reconstruction is a challenging aspect of computational imaging as it often involves solving ill-posed inverse problems. Recently, deep feed-forward neural networks have led to state-of-the-art results in solving various inverse…

Multi-view deep neural network is perhaps the most successful approach in 3D shape classification. However, the fusion of multi-view features based on max or average pooling lacks a view selection mechanism, limiting its application in,…

Large-scale diffusion generative models are greatly simplifying image, video and 3D asset creation from user-provided text prompts and images. However, the challenging problem of text-to-4D dynamic 3D scene generation with diffusion…

Text-to-image diffusion models have an unprecedented ability to generate diverse and high-quality images. However, they often struggle to faithfully capture the intended semantics of complex input prompts that include multiple subjects.…

Most practical high-resolution text-to-image systems, including latent diffusion and autoregressive models, perform generation in a compact latent space, and a decoder maps the generated latents back to pixels. Yet the latent-to-pixel…

Pose transfer refers to the probabilistic image generation of a person with a previously unseen novel pose from another image of that person having a different pose. Due to potential academic and commercial applications, this problem is…

This paper presents a family of advanced vision encoder, named OpenVision 3, that learns a single, unified visual representation that can serve both image understanding and image generation. Our core architecture is simple: we feed…

We develop an approach for text-to-image generation that embraces additional retrieval images, driven by a combination of implicit visual guidance loss and generative objectives. Unlike most existing text-to-image generation methods which…

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…

Reconstructing 3D scenes from a single image is a fundamentally ill-posed task due to the severely under-constrained nature of the problem. Consequently, when the scene is rendered from novel camera views, existing single image to 3D…

Existing two-stream models, such as CLIP, encode images and text through independent representations, showing good performance while ensuring retrieval speed, have attracted attention from industry and academia. However, the single…

Generating high-quality 3D content requires models capable of learning robust distributions of complex scenes and the real-world objects within them. Recent Gaussian-based 3D reconstruction techniques have achieved impressive results in…

Novel view synthesis (NVS) from a single image is highly ill-posed due to large unobserved regions, especially for views that deviate significantly from the input. While existing methods focus on consistency between the source and generated…