Related papers: Realism Control One-step Diffusion for Real-World …
Diffusion transformer (DiT) architectures show great potential for real-world image super-resolution (Real-ISR). However, their computationally expensive iterative sampling necessitates one-step distillation. Existing one-step distillation…
While recent diffusion-based generative image codecs have shown impressive performance, their iterative sampling process introduces unpleasing latency. In this work, we revisit the design of a diffusion-based codec and argue that multi-step…
Existing image SR and generic diffusion models transfer poorly to fluid SR: they are sampling-intensive, ignore physical constraints, and often yield spectral mismatch and spurious divergence. We address fluid super-resolution (SR) with…
Guidance techniques are simple yet effective for improving conditional generation in diffusion models. Albeit their empirical success, the practical implementation of guidance diverges significantly from its theoretical motivation. In this…
Recent advancements have explored text-to-image diffusion models for synthesizing out-of-distribution (OOD) samples, substantially enhancing the performance of OOD detection. However, existing approaches typically rely on perturbing…
Offline black-box optimization aims to maximize a black-box function using an offline dataset of designs and their measured properties. Two main approaches have emerged: the forward approach, which learns a mapping from input to its value,…
Distillation addresses the slow sampling problem in diffusion models by creating models with smaller size or fewer steps that approximate the behavior of high-step teachers. In this work, we propose a reinforcement learning based…
Current diffusion-based super-resolution (SR) approaches achieve commendable performance at the cost of high inference overhead. Therefore, distillation techniques are utilized to accelerate the multi-step teacher model into one-step…
Diffusion policies are a powerful paradigm for robotic control, but fine-tuning them with human preferences is fundamentally challenged by the multi-step structure of the denoising process. To overcome this, we introduce a Unified Markov…
Score distillation sampling~(SDS) has been widely adopted to overcome the absence of unseen views in reconstructing 3D objects from a \textbf{single} image. It leverages pre-trained 2D diffusion models as teacher to guide the reconstruction…
Recent approaches have shown promises distilling diffusion models into efficient one-step generators. Among them, Distribution Matching Distillation (DMD) produces one-step generators that match their teacher in distribution, without…
Recently, diffusion models (DMs) have made significant strides in high-quality image generation. However, the multi-step denoising process often results in considerable computational overhead, impeding deployment on resource-constrained…
Prior research on out-of-distribution detection (OoDD) has primarily focused on single-modality models. Recently, with the advent of large-scale pretrained vision-language models such as CLIP, OoDD methods utilizing such multi-modal…
Recently, diffusion-based blind super-resolution (SR) methods have shown great ability to generate high-resolution images with abundant high-frequency detail, but the detail is often achieved at the expense of fidelity. Meanwhile, another…
While diffusion models can learn complex distributions, sampling requires a computationally expensive iterative process. Existing distillation methods enable efficient sampling, but have notable limitations, such as performance degradation…
In diffusion models, samples are generated through an iterative refinement process, requiring hundreds of sequential model evaluations. Several recent methods have introduced approximations (fewer discretization steps or distillation) to…
Diffusion Policies (DPs) have attracted attention for their ability to achieve significant accuracy improvements in various imitation learning tasks. However, DPs depend on Diffusion Models, which require multiple noise removal steps to…
There is a rapidly growing interest in controlling consistency across multiple generated images using diffusion models. Among various methods, recent works have found that simply manipulating attention modules by concatenating features from…
Robot manipulation in the real world is fundamentally constrained by the visual sim2real gap, where depth observations collected in simulation fail to reflect the complex noise patterns inherent to real sensors. In this work, inspired by…
Recent advancements in text-guided diffusion models have unlocked powerful image manipulation capabilities. However, applying these methods to real images necessitates the inversion of the images into the domain of the pretrained diffusion…