相关论文: FlowLoss: Dynamic Flow-Conditioned Loss Strategy f…

The difficulty of obtaining paired data remains a major bottleneck for learning image restoration and enhancement models for real-world applications. Current strategies aim to synthesize realistic training data by modeling noise and…

Diffusion and flow matching models have achieved remarkable success in text-to-image generation. However, these models typically rely on the predetermined denoising schedules for all prompts. The multi-step reverse diffusion process can be…

Diffusion and flow-based generative models have achieved remarkable success in domains such as image synthesis, video generation, and natural language modeling. In this work, we extend these advances to weight space learning by leveraging…

We consider the problem of using diffusion models to generate fast, smooth, and temporally consistent robot motions. Although diffusion models have demonstrated superior performance in robot learning due to their task scalability and…

Denoising diffusion models have emerged as a dominant approach for image generation, however they still suffer from slow convergence in training and color shift issues in sampling. In this paper, we identify that these obstacles can be…

Conventional methods for human motion synthesis are either deterministic or struggle with the trade-off between motion diversity and motion quality. In response to these limitations, we introduce MoFusion, i.e., a new…

Existing work on scene flow estimation focuses on autonomous driving and mobile robotics, while automated solutions are lacking for motion in nature, such as that exhibited by debris flows. We propose DEFLOW, a model for 3D motion…

Event cameras respond to scene dynamics and offer advantages to estimate motion. Following recent image-based deep-learning achievements, optical flow estimation methods for event cameras have rushed to combine those image-based methods…

Dynamic mode decomposition (DMD) is a popular approach to analyzing and modeling fluid flows. In practice, datasets are almost always corrupted to some degree by noise. The vanilla DMD is highly noise-sensitive, which is why many…

Several state-of-the-art video deblurring methods are based on a strong assumption that the captured scenes are static. These methods fail to deblur blurry videos in dynamic scenes. We propose a video deblurring method to deal with general…

Current video diffusion models generate visually compelling content but often violate basic laws of physics, producing subtle artifacts like rubber-sheet deformations and inconsistent object motion. We introduce a frequency-domain physics…

We address the challenging problem of jointly inferring the 3D flow and volumetric densities moving in a fluid from a monocular input video with a deep neural network. Despite the complexity of this task, we show that it is possible to…

Video generation models have achieved notable progress in static scenarios, yet their performance in motion video generation remains limited, with quality degrading under drastic dynamic changes. This is due to noise disrupting temporal…

Dynamic environments are challenging for visual SLAM since the moving objects occlude the static environment features and lead to wrong camera motion estimation. In this paper, we present a novel dense RGB-D SLAM solution that…

Optical flow is a crucial component of the feature space for early visual processing of dynamic scenes especially in new applications such as self-driving vehicles, drones and autonomous robots. The dynamic vision sensors are well suited…

Recent advancements in diffusion models have greatly improved the quality and diversity of synthesized content. To harness the expressive power of diffusion models, researchers have explored various controllable mechanisms that allow users…

Despite the remarkable progress in deep generative models, synthesizing high-resolution and temporally coherent videos still remains a challenge due to their high-dimensionality and complex temporal dynamics along with large spatial…

Video generation using diffusion-based models is constrained by high computational costs due to the frame-wise iterative diffusion process. This work presents a Diffusion Reuse MOtion (Dr. Mo) network to accelerate latent video generation.…

We propose a novel approach for dynamic negative prompting in diffusion models that leverages Vision-Language Models (VLMs) to adaptively generate negative prompts during the denoising process. Unlike traditional Negative Prompting methods…

We present FlowDet, the first formulation of object detection using modern Conditional Flow Matching techniques. This work follows from DiffusionDet, which originally framed detection as a generative denoising problem in the bounding box…