Related papers: Learning High-Quality Initial Noise for Single-Vie…
Novel-view synthesis aims to generate novel views of a scene from multiple input images or videos, and recent advancements like 3D Gaussian splatting (3DGS) have achieved notable success in producing photorealistic renderings with efficient…
Novel view synthesis (NVS) has shown significant promise for applications in cinematographic production, particularly through the exploitation of Neural Radiance Fields (NeRF) and Gaussian Splatting (GS). These methods model real 3D scenes,…
Diffusion models have emerged as the leading approach for image synthesis, demonstrating exceptional photorealism and diversity. However, training diffusion models at high resolutions remains computationally prohibitive, and existing…
Repurposing pre-trained diffusion models has been proven to be effective for NVS. However, these methods are mostly limited to a single object; directly applying such methods to compositional multi-object scenarios yields inferior results,…
Diffusion models have achieved remarkable success in generating high-resolution, realistic images across diverse natural distributions. However, their performance heavily relies on high-quality training data, making it challenging to learn…
Diffusion autoencoders (DAEs) are typically formulated as a noise prediction model and trained with a linear-$\beta$ noise schedule that spends much of its sampling steps at high noise levels. Because high noise levels are associated with…
3D Gaussian Splatting (3DGS) has demonstrated remarkable effectiveness in novel view synthesis (NVS). However, 3DGS tends to overfit when trained with sparse views, limiting its generalization to novel viewpoints. In this paper, we address…
Large scale image super-resolution is a challenging computer vision task, since vast information is missing in a highly degraded image, say for example forscale x16 super-resolution. Diffusion models are used successfully in recent years in…
Recently, research on denoising diffusion models has expanded its application to the field of image restoration. Traditional diffusion-based image restoration methods utilize degraded images as conditional input to effectively guide the…
Complex degradations like noise, blur, and low resolution are typical challenges in real world image fusion tasks, limiting the performance and practicality of existing methods. End to end neural network based approaches are generally…
Text-guided diffusion models have shown superior performance in image/video generation and editing. While few explorations have been performed in 3D scenarios. In this paper, we discuss three fundamental and interesting problems on this…
Novel view synthesis (NVS) is a challenging task requiring systems to generate photorealistic images of scenes from new viewpoints, where both quality and speed are important for applications. Previous image-based rendering (IBR) methods…
Diffusion models have established themselves as the de facto primary paradigm in visual generative modeling, revolutionizing the field through remarkable success across various diverse applications ranging from high-quality image synthesis…
Acquiring high-quality data for training discriminative models is a crucial yet challenging aspect of building effective predictive systems. In this paper, we present Diffusion Inversion, a simple yet effective method that leverages the…
With recent advances of diffusion model, generative speech enhancement (SE) has attracted a surge of research interest due to its great potential for unseen testing noises. However, existing efforts mainly focus on inherent properties of…
Classical diffusion models typically rely on isotropic Gaussian noise, treating all regions uniformly and overlooking structural information important for high-quality generation. We introduce an edge-preserving diffusion process that…
The prevalent convolutional neural network (CNN) based image denoising methods extract features of images to restore the clean ground truth, achieving high denoising accuracy. However, these methods may ignore the underlying distribution of…
Denoising diffusion models are widely used for high-quality image and video generation. Their performance depends on noise schedules, which define the distribution of noise levels applied during training and the sequence of noise levels…
We address the problem of novel view synthesis: given an input image, synthesizing new images of the same object or scene observed from arbitrary viewpoints. We approach this as a learning task but, critically, instead of learning to…
2D-to-3D reconstruction is an ill-posed problem, yet humans are good at solving this problem due to their prior knowledge of the 3D world developed over years. Driven by this observation, we propose NeRDi, a single-view NeRF synthesis…