Related papers: Guided Path Sampling: Steering Diffusion Models Ba…
Our goal is to develop fine-grained real-image editing methods suitable for real-world applications. In this paper, we first summarize four requirements for these methods and propose a novel diffusion-based image editing framework with…
Restoring degraded music signals is essential to enhance audio quality for downstream music manipulation. Recent diffusion-based music restoration methods have demonstrated impressive performance, and among them, diffusion posterior…
The ability of Flow Matching (FM) to model complex conditional distributions has established it as the state-of-the-art for prediction tasks (e.g., robotics, weather forecasting). However, deployment in safety-critical settings is hindered…
We propose a general framework for conditional sampling in PDE-based inverse problems, targeting the recovery of whole solutions from extremely sparse or noisy measurements. This is accomplished by a function-space diffusion model and…
Classifier-Free Guidance (CFG) is a widely used technique for conditional generation and improving sample quality in continuous diffusion models, and its extensions to discrete diffusion has recently started to be investigated. In order to…
Hashing has been widely used in approximate nearest neighbor search for its storage and computational efficiency. Deep supervised hashing methods are not widely used because of the lack of labeled data, especially when the domain is…
Diffusion models represent a class of generative models that produce data by denoising a sample corrupted by white noise. Despite the success of diffusion models in computer vision, audio synthesis, and point cloud generation, so far they…
Unlike discriminative approaches in autonomous driving that predict a fixed set of candidate trajectories of the ego vehicle, generative methods, such as diffusion models, learn the underlying distribution of future motion, enabling more…
Diffusion Models have demonstrated remarkable performance in image generation. However, their demanding computational requirements for training have prompted ongoing efforts to enhance the quality of generated images through modifications…
Blind image restoration remains a significant challenge in low-level vision tasks. Recently, denoising diffusion models have shown remarkable performance in image synthesis. Guided diffusion models, leveraging the potent generative priors…
Cameras and LiDAR are essential sensors for autonomous vehicles. Camera-LiDAR data fusion compensate for deficiencies of stand-alone sensors but relies on precise extrinsic calibration. Many learning-based calibration methods predict…
MeanFlow (MF) has recently been established as a framework for one-step generative modeling. However, its ``fastforward'' nature introduces key challenges in both the training objective and the guidance mechanism. First, the original MF's…
Training-free guided sampling in diffusion models leverages off-the-shelf pre-trained networks, such as an aesthetic evaluation model, to guide the generation process. Current training-free guided sampling algorithms obtain the guidance…
Classifier-Free Guidance (CFG) is widely used to improve conditional fidelity in diffusion models, but its impact on sampling dynamics remains poorly understood. Prior studies, often restricted to unimodal conditional distributions or…
Generative models, including diffusion and flow-based models, often exhibit systematic biases that degrade sample quality, particularly in high-dimensional settings. We revisit refinement methods and show that effective bias correction can…
The class-conditional image generation based on diffusion models is renowned for generating high-quality and diverse images. However, most prior efforts focus on generating images for general categories, e.g., 1000 classes in ImageNet-1k. A…
While Classifier-Free Guidance (CFG) has become standard for improving sample fidelity in conditional diffusion models, it can harm diversity and induce memorization by applying constant guidance regardless of whether a particular sample…
Conditional diffusion models have demonstrated impressive performance in image manipulation tasks. The general pipeline involves adding noise to the image and then denoising it. However, this method faces a trade-off problem: adding too…
Classifier-Free Guidance (CFG) improves sample quality in diffusion models, but its dual-pass inference and reliance on null-condition training limit its use in few-step regimes. Attention-space guidance has emerged as a complementary…
Diffusion models are powerful generative models that achieve state-of-the-art performance in image synthesis. However, training them demands substantial amounts of data and computational resources. Continual learning would allow for…