Related papers: CurveFlow: Curvature-Guided Flow Matching for Imag…

Estimating continuous optical flow is a fundamental yet challenging problem in dynamic visual perception. Event-based cameras, with microsecond latency and high dynamic range, capture brightness changes asynchronously, offering a unique…

Simulation-free methods for training continuous-time generative models construct probability paths that go between noise distributions and individual data samples. Recent works, such as Flow Matching, derived paths that are optimal for each…

Diffusion models have achieved remarkable generation quality, but they suffer from significant inference cost due to their reliance on multiple sequential denoising steps, motivating recent efforts to distill this inference process into a…

We present OneFlow, the first non-autoregressive multimodal model that enables variable-length and concurrent mixed-modal generation. Unlike autoregressive models that enforce rigid causal ordering between text and image generation, OneFlow…

Strong semantic representations improve the convergence and generation quality of diffusion and flow models. Existing approaches largely rely on external models, which require separate training, operate on misaligned objectives, and exhibit…

Diffusion models (DMs) excel in photorealism, image editing, and solving inverse problems, aided by classifier-free guidance and image inversion techniques. However, rectified flow models (RFMs) remain underexplored for these tasks.…

Unsupervised optical flow methods typically lack reliable uncertainty estimation, limiting their robustness and interpretability. We propose U$^{2}$Flow, the first recurrent unsupervised framework that jointly estimates optical flow and…

Obtaining the ground truth labels from a video is challenging since the manual annotation of pixel-wise flow labels is prohibitively expensive and laborious. Besides, existing approaches try to adapt the trained model on synthetic datasets…

Flow-based text-to-image models follow deterministic trajectories, making it costly to explore diverse modes under limited sampling budgets. Existing approaches to improving diversity often rely on retraining or degrade image fidelity. To…

Explicitly disentangling style and content in vision models remains challenging due to their semantic overlap and the subjectivity of human perception. Existing methods propose separation through generative or discriminative objectives, but…

Deep generative models provide a promising approach to de novo 3D peptide design. Most of them jointly model the distributions of peptide's position, orientation, and conformation, attempting to simultaneously converge to the target pocket.…

MeanFlow has recently emerged as a powerful framework for few-step generative modeling trained from scratch, but its success is not yet fully understood. In this work, we show that the MeanFlow objective naturally decomposes into two parts:…

Defect segmentation is central to computer vision based inspection of infrastructure assets during both construction and operation. However, deployment remains limited due to scarce pixel-level labels and domain shift across environments.…

Text-to-video diffusion models are notoriously limited in their ability to model temporal aspects such as motion, physics, and dynamic interactions. Existing approaches address this limitation by retraining the model or introducing external…

Flow matching casts sample generation as learning a continuous-time velocity field that transports noise to data. Existing flow matching networks typically predict each point's velocity independently, considering only its location and time…

Generating molecular graphs with desired chemical properties driven by deep graph generative models provides a very promising way to accelerate drug discovery process. Such graph generative models usually consist of two steps: learning…

Generating human motion with precise spatial control is a challenging problem. Existing approaches often require task-specific training or slow optimization, and enforcing hard constraints frequently disrupts motion naturalness. Building on…

Motion transfer from the driving to the source portrait remains a key challenge in the portrait animation. Current diffusion-based approaches condition only on the driving motion, which fails to capture source-to-driving correspondences and…

Proof autoformalization, the task of translating natural language theorems and proofs into machine-verifiable code, is a critical step for integrating large language models into rigorous mathematical workflows. Current approaches focus on…

Inferring trajectories from longitudinal spatially-resolved omics data is fundamental to understanding the dynamics of structural and functional tissue changes in development, regeneration and repair, disease progression, and response to…