Related papers: Score Jacobian Chaining: Lifting Pretrained 2D Dif…

Deep neural networks (DNNs) have shown remarkable performance improvements on vision-related tasks such as object detection or image segmentation. Despite their success, they generally lack the understanding of 3D objects which form the…

In this work, we propose a novel framework for estimating the dimension of the data manifold using a trained diffusion model. A diffusion model approximates the score function i.e. the gradient of the log density of a noise-corrupted…

Reconstructing a renderable 3D model from images is a useful but challenging task. Recent feedforward 3D reconstruction methods have demonstrated remarkable success in efficiently recovering geometry, but still cannot accurately model the…

Score-based diffusion models are a powerful class of generative models, widely utilized across diverse domains. Despite significant advancements in large-scale tasks such as text-to-image generation, their application to constrained domains…

This book presents the core principles that have guided the development of diffusion models, tracing their origins and showing how diverse formulations arise from shared mathematical ideas. Diffusion modeling starts by defining a forward…

We introduce SceneDiffuser, a conditional generative model for 3D scene understanding. SceneDiffuser provides a unified model for solving scene-conditioned generation, optimization, and planning. In contrast to prior works, SceneDiffuser is…

We present a novel diffusion-based approach for coherent 3D scene reconstruction from a single RGB image. Our method utilizes an image-conditioned 3D scene diffusion model to simultaneously denoise the 3D poses and geometries of all objects…

This paper presents a novel approach to inpainting 3D regions of a scene, given masked multi-view images, by distilling a 2D diffusion model into a learned 3D scene representation (e.g. a NeRF). Unlike 3D generative methods that explicitly…

Diffusion models have recently achieved remarkable success in generative modeling, yet they are commonly formulated as black-box stochastic systems with limited interpretability and few structural guarantees. In this paper, we establish a…

This work presents an autoregressive generative diffusion model (DiffObs) to predict the global evolution of daily precipitation, trained on a satellite observational product, and assessed with domain-specific diagnostics. The model is…

The aim of this research is to reconstruct the 3D X-ray refractive index gradient maps by the proposed vector Radon transform and its inverse, assuming that the small-angle deviation condition is met. Theoretical analyses show that the…

In this work, we investigated the application of score-based gradient learning in discriminative and generative classification settings. Score function can be used to characterize data distribution as an alternative to density. It can be…

Drifting models train one-step generators by optimizing a kernel-induced mean-shift discrepancy between the data and model distributions, with Laplace kernels used by default in practice. At each point, this discrepancy compares the…

Video grounding aims to localize the target moment in an untrimmed video corresponding to a given sentence query. Existing methods typically select the best prediction from a set of predefined proposals or directly regress the target span…

Ambiguity in medical image segmentation calls for models that capture full conditional distributions rather than a single point estimate. We present Prior-Guided Residual Diffusion (PGRD), a diffusion-based framework that learns voxel-wise…

We present a diffusion-based model for 3D-aware generative novel view synthesis from as few as a single input image. Our model samples from the distribution of possible renderings consistent with the input and, even in the presence of…

While inference-time scaling through search has revolutionized Large Language Models, translating these gains to image generation has proven difficult. Recent attempts to apply search strategies to continuous diffusion models show limited…

Neural Radiance Fields (NeRFs) have emerged as a powerful neural 3D representation for objects and scenes derived from 2D data. Generating NeRFs, however, remains difficult in many scenarios. For instance, training a NeRF with only a small…

This paper presents a novel latent 3D diffusion model for the generation of neural voxel fields, aiming to achieve accurate part-aware structures. Compared to existing methods, there are two key designs to ensure high-quality and accurate…

We propose a new method for separating superimposed sources using diffusion-based generative models. Our method relies only on separately trained statistical priors of independent sources to establish a new objective function guided by…