相关论文: Diffusion Time-step Curriculum for One Image to 3D…

We present a mechanism to steer the sampling diversity of denoising diffusion and flow matching models, allowing users to sample from a sharper or broader distribution than the training distribution. We build on the observation that these…

Recently, text-to-image generation has exhibited remarkable advancements, with the ability to produce visually impressive results. In contrast, text-to-3D generation has not yet reached a comparable level of quality. Existing methods…

Diffusion-based models have shown great promise in molecular generation but often require a large number of sampling steps to generate valid samples. In this paper, we introduce a novel Straight-Line Diffusion Model (SLDM) to tackle this…

Score Distillation Sampling (SDS) has been pivotal for leveraging pre-trained diffusion models in downstream tasks such as inverse problems, but it faces two major challenges: $(i)$ mode collapse and $(ii)$ latent space inversion, which…

In this paper, we unify more than 10 existing one-step diffusion distillation approaches, such as Diff-Instruct, DMD, SIM, SiD, $f$-distill, etc, inside a theory-driven framework which we name the \textbf{\emph{Uni-Instruct}}. Uni-Instruct…

Denoising diffusion models (DDMs) have led to staggering performance leaps in image generation, editing and restoration. However, existing DDMs use very large datasets for training. Here, we introduce a framework for training a DDM on a…

Large image diffusion models enable novel view synthesis with high quality and excellent zero-shot capability. However, such models based on image-to-image translation have no guarantee of view consistency, limiting the performance for…

Sound content creation, essential for multimedia works such as video games and films, often involves extensive trial-and-error, enabling creators to semantically reflect their artistic ideas and inspirations, which evolve throughout the…

Super-resolution (SR) aims to reconstruct high-resolution (HR) images from their low-resolution (LR) counterparts, often relying on effective downsampling to generate diverse and realistic training pairs. In this work, we propose a…

Score Distillation Sampling (SDS) has emerged as the de facto approach for text-to-content generation in non-image domains. In this paper, we reexamine the SDS process and introduce a straightforward interpretation that demystifies the…

Dataset distillation (DD) aims to compress large-scale datasets into compact synthetic sets while preserving training efficacy. However, existing studies mainly focus on image classification, leaving dense prediction tasks such as semantic…

Text-to-3D generation has recently garnered significant attention, fueled by 2D diffusion models trained on billions of image-text pairs. Existing methods primarily rely on score distillation to leverage the 2D diffusion priors to supervise…

Recent text-guided generation of individual 3D object has achieved great success using diffusion priors. However, these methods are not suitable for object insertion and replacement tasks as they do not consider the background, leading to…

Diffusion models have shown strong performance in speech enhancement, but their real-time applicability has been limited by multi-step iterative sampling. Consistency distillation has recently emerged as a promising alternative by…

We introduce Posterior Distillation Sampling (PDS), a novel optimization method for parametric image editing based on diffusion models. Existing optimization-based methods, which leverage the powerful 2D prior of diffusion models to handle…

Recent hybrid video generation models combine autoregressive temporal dynamics with diffusion-based spatial denoising, but their sequential, iterative nature leads to error accumulation and long inference times. In this work, we propose a…

Although continuous-time consistency models (e.g., sCM, MeanFlow) are theoretically principled and empirically powerful for fast academic-scale diffusion, its applicability to large-scale text-to-image and video tasks remains unclear due to…

Reverse sampling and score-distillation have emerged as main workhorses in recent years for image manipulation using latent diffusion models (LDMs). While reverse diffusion sampling often requires adjustments of LDM architecture or feature…

While diffusion models have demonstrated remarkable progress in 2D image generation and editing, extending these capabilities to 3D editing remains challenging, particularly in maintaining multi-view consistency. Classical approaches…

The recent advancements in text-to-3D generation mark a significant milestone in generative models, unlocking new possibilities for creating imaginative 3D assets across various real-world scenarios. While recent advancements in text-to-3D…