Related papers: WAFT: Warping-Alone Field Transforms for Optical F…
The foundation model is not the last chapter of the model production pipeline. Transferring with few data in a general way to thousands of downstream tasks is becoming a trend of the foundation model's application. In this paper, we…
Large foundation models are becoming ubiquitous, but training them from scratch is prohibitively expensive. Thus, efficiently adapting these powerful models to downstream tasks is increasingly important. In this paper, we study a principled…
Optical flow estimation is a fundamental task in computer vision. Recent direct-regression methods using deep neural networks achieve remarkable performance improvement. However, they do not explicitly capture long-term motion…
The Wavelength-shifting Optical Module (WOM) is a novel photosensor concept for the instrumentation of large detector volumes with single-photon sensitivity. The key objective is to improve the signal-to-noise ratio which is achieved by…
Recent progress in dense optical flow has been driven by increasingly complex architectures and multi-step refinement for test-time scaling. While these approaches achieve strong benchmark performance, they also require substantial…
Transformer-based architectures have advanced medical image analysis by effectively modeling long-range dependencies, yet they often struggle in 3D settings due to substantial memory overhead and insufficient capture of fine-grained local…
Adapting pretrained models typically involves a trade-off between the high training costs of backpropagation and the heavy inference overhead of memory-based or in-context learning. We propose FAAST, a forward-only associative adaptation…
As a powerful technique in generative modeling, Flow Matching (FM) aims to learn velocity fields from noise to data, which is often explained and implemented as solving Optimal Transport (OT) problems. In this study, we bridge FM and the…
Feature Transformation is crucial for classic machine learning that aims to generate feature combinations to enhance the performance of downstream tasks from a data-centric perspective. Current methodologies, such as manual expert-driven…
Fast Fourier Transforms (FFT) are widely used to reduce memory and computational costs in deep learning. However, existing implementations, including standard FFT and real FFT (rFFT), cannot achieve true in-place computation. In particular,…
Real-time high-accuracy optical flow estimation is a crucial component in various applications, including localization and mapping in robotics, object tracking, and activity recognition in computer vision. While recent learning-based…
With the scale of vision Transformer-based models continuing to grow, finetuning these large-scale pretrained models for new tasks has become increasingly parameter-intensive. Visual prompt tuning is introduced as a parameter-efficient…
The Fractional Fourier Transform (FRT) corresponds to an arbitrary-angle rotation in the phase space, e.g. the time-frequency (TF) space, and generalizes the fundamentally important Fourier Transform. FRT applications range from classical…
In this paper, we propose a novel energy-efficient data collection and wireless power transfer (WPT) framework for internet of things (IoT) applications, via a multiple-input multiple-output (MIMO) full-duplex (FD) unmanned aerial vehicle…
Optical flow estimation is a crucial subfield of computer vision, serving as a foundation for video tasks. However, the real-world robustness is limited by animated synthetic datasets for training. This introduces domain gaps when applied…
The special affine Fourier transform (SAFT) is a promising tool for analyzing non-stationary signals with more degrees of freedom. However, the SAFT fails in obtaining the local features of non-transient signals due to its global kernel and…
The FFT of three-dimensional (3D) input data is an important computational kernel of numerical simulations and is widely used in High Performance Computing (HPC) codes running on a large number of processors. Performance of many scientific…
We present Consistent-Recurrent Feature Flow Transformer (CRFT), a unified coarse-to-fine framework based on feature flow learning for robust cross-modal image registration. CRFT learns a modality-independent feature flow representation…
Optical flow estimation is crucial to a variety of vision tasks. Despite substantial recent advancements, achieving real-time on-device optical flow estimation remains a complex challenge. First, an optical flow model must be sufficiently…
Accurate emulation of multi-scale physical systems governed by PDEs demands models that remain stable over long autoregressive rollouts while preserving fine-scale structures. Deterministic emulators produce overly-smoothed predictions,…