相关论文: COT Flow: Learning Optimal-Transport Image Samplin…

Recent advances in text-to-image generation with diffusion models present transformative capabilities in image quality. However, user controllability of the generated image, and fast adaptation to new tasks still remains an open challenge,…

Dynamical generative models that produce samples through an iterative process, such as Flow Matching and denoising diffusion models, have seen widespread use, but there have not been many theoretically-sound methods for improving these…

Current image generation and editing methods primarily process textual prompts as direct inputs without reasoning about visual composition and explicit operations. We present Generation Chain-of-Thought (GoT), a novel paradigm that enables…

Finding a suitable layout represents a crucial task for diverse applications in graphic design. Motivated by simpler and smoother sampling trajectories, we explore the use of Flow Matching as an alternative to current diffusion-based layout…

We introduce COT-GAN, an adversarial algorithm to train implicit generative models optimized for producing sequential data. The loss function of this algorithm is formulated using ideas from Causal Optimal Transport (COT), which combines…

Text-guided diffusion models have revolutionized image generation and editing, offering exceptional realism and diversity. Specifically, in the context of diffusion-based editing, where a source image is edited according to a target prompt,…

Text-to-image diffusion models have achieved unprecedented success but still struggle to produce high-quality results under limited sampling budgets. Existing training-free sampling acceleration methods are typically developed…

In this paper, we propose an efficient, fast, and versatile distillation method to accelerate the generation of pre-trained diffusion models: Flash Diffusion. The method reaches state-of-the-art performances in terms of FID and CLIP-Score…

Recently, GAN inversion methods combined with Contrastive Language-Image Pretraining (CLIP) enables zero-shot image manipulation guided by text prompts. However, their applications to diverse real images are still difficult due to the…

Diffusion models have shown remarkable progress in text-to-audio generation. However, text-guided audio editing remains in its early stages. This task focuses on modifying the target content within an audio signal while preserving the rest,…

Recently, diffusion models have garnered significant interest in the field of text processing due to their many potential advantages compared to conventional autoregressive models. In this work, we propose Diffusion-of-Thought (DoT), a…

Flow matching models have emerged as a strong alternative to diffusion models, but existing inversion and editing methods designed for diffusion are often ineffective or inapplicable to them. The straight-line, non-crossing trajectories of…

Recent advances in diffusion and flow-based generative models have demonstrated remarkable success in image restoration tasks, achieving superior perceptual quality compared to traditional deep learning approaches. However, these methods…

Collecting multi-view driving scenario videos to enhance the performance of 3D visual perception tasks presents significant challenges and incurs substantial costs, making generative models for realistic data an appealing alternative. Yet,…

Instruction-guided generative models, especially those using text-to-image (T2I) and text-to-video (T2V) diffusion frameworks, have advanced the field of content editing in recent years. To extend these capabilities to 4D scene, we…

Diffusion and flow matching models generate samples by learning time-dependent vector fields whose integration transports noise to data, requiring tens to hundreds of network evaluations at inference. We instead learn the transport map…

Scene flow estimation is a crucial component in the development of autonomous driving and 3D robotics, providing valuable information for environment perception and navigation. Despite the advantages of learning-based scene flow estimation…

Although diffusion models in text-to-speech have become a popular choice due to their strong generative ability, the intrinsic complexity of sampling from diffusion models harms their efficiency. Alternatively, we propose VoiceFlow, an…

Event cameras deliver visual information characterized by a high dynamic range and high temporal resolution, offering significant advantages in estimating optical flow for complex lighting conditions and fast-moving objects. Current…

In this work, we introduce Modulated Flows (ModFlows), a novel approach for color transfer between images based on rectified flows. The primary goal of the color transfer is to adjust the colors of a target image to match the color…