相关论文: Multi-View Unsupervised Image Generation with Cros…

Diffusion models (DMs) have emerged as powerful foundation models for a variety of tasks, with a large focus in synthetic image generation. However, their requirement of large annotated datasets for training limits their applicability in…

Generating consistent human images with controllable pose and appearance is essential for applications in virtual try on, image editing, and digital human creation. Current methods often suffer from occlusions, garment style drift, and pose…

In recent years, various applications in computer vision have achieved substantial progress based on deep learning, which has been widely used for image fusion and shown to achieve adequate performance. However, suffering from limited…

We address the task of multi-view image editing from sparse input views, where the inputs can be seen as a mix of images capturing the scene from different viewpoints. The goal is to modify the scene according to a textual instruction while…

Given the remarkable results of motion synthesis with diffusion models, a natural question arises: how can we effectively leverage these models for motion editing? Existing diffusion-based motion editing methods overlook the profound…

Recent advances in self-supervised learning (SSL) have made it possible to learn general-purpose visual features that capture both the high-level semantics and the fine-grained spatial structure of images. Most notably, the recent DINOv2…

Geospatial imaging leverages data from diverse sensing modalities-such as EO, SAR, and LiDAR, ranging from ground-level drones to satellite views. These heterogeneous inputs offer significant opportunities for scene understanding but…

This paper presents a neural architecture MVDiffusion++ for 3D object reconstruction that synthesizes dense and high-resolution views of an object given one or a few images without camera poses. MVDiffusion++ achieves superior flexibility…

We tackle the problem of sparse novel view synthesis (NVS) using video diffusion models; given $K$ ($\approx 5$) multi-view images of a scene and their camera poses, we predict the view from a target camera pose. Many prior approaches…

Advances in unsupervised learning of object-representations have culminated in the development of a broad range of methods for unsupervised object segmentation and interpretable object-centric scene generation. These methods, however, are…

This paper proposes a method for precise learning and synthesizing multi-instance semantics from a single image. The difficulty of this problem lies in the limited training data, and it becomes even more challenging when the instances to be…

A plethora of text-guided image editing methods has recently been developed by leveraging the impressive capabilities of large-scale diffusion-based generative models especially Stable Diffusion. Despite the success of diffusion models in…

In this paper, we introduce a new challenge for synthesizing novel view images in practical environments with limited input multi-view images and varying lighting conditions. Neural radiance fields (NeRF), one of the pioneering works for…

Diffusion-based models have achieved state-of-the-art performance on text-to-image synthesis tasks. However, one critical limitation of these models is the low fidelity of generated images with respect to the text description, such as…

Generative image editing has recently witnessed extremely fast-paced growth. Some works use high-level conditioning such as text, while others use low-level conditioning. Nevertheless, most of them lack fine-grained control over the…

Driven by the scalable diffusion models trained on large-scale datasets, text-to-image synthesis methods have shown compelling results. However, these models still fail to precisely follow the text prompt involving multiple objects,…

We present an unsupervised approach for factorizing object appearance into highlight, shading, and albedo layers, trained by multi-view real images. To do so, we construct a multi-view dataset by collecting numerous customer product photos…

Recently, the progress of learning-by-synthesis has proposed a training model for synthetic images, which can effectively reduce the cost of human and material resources. However, due to the different distribution of synthetic images…

We present a novel approach to leverage prior knowledge encapsulated in pre-trained text-to-image diffusion models for blind super-resolution (SR). Specifically, by employing our time-aware encoder, we can achieve promising restoration…

Recently, text-to-image models based on diffusion have achieved remarkable success in generating high-quality images. However, the challenge of personalized, controllable generation of instances within these images remains an area in need…