Related papers: FlowFormer: A Transformer Architecture and Its Mas…

Accurate autoregressive prediction of 3D turbulent flows remains challenging for neural PDE solvers, as small errors in fine-scale structures can accumulate rapidly over rollout. In this paper, we propose FlowRefiner, a flow matching-based…

We propose a novel flow synthesis based visual servoing framework enabling long-range obstacle avoidance for Micro Air Vehicles (MAV) flying amongst tall skyscrapers. Recent deep learning based frameworks use optical flow to do…

The CNN-based methods have achieved impressive results in medical image segmentation, but they failed to capture the long-range dependencies due to the inherent locality of the convolution operation. Transformer-based methods are recently…

Referring Video Object Segmentation (RVOS) requires segmenting specific objects in a video guided by a natural language description. The core challenge of RVOS is to anchor abstract linguistic concepts onto a specific set of pixels and…

Flow matching offers a robust and stable approach to training diffusion models. However, directly applying flow matching to neural vocoders can result in subpar audio quality. In this work, we present WaveFM, a reparameterized flow matching…

Image Representation learning via input reconstruction is a common technique in machine learning for generating representations that can be effectively utilized by arbitrary downstream tasks. A well-established approach is using…

Multi-task networks can potentially improve performance and computational efficiency compared to single-task networks, facilitating online deployment. However, current multi-task architectures in point cloud perception combine multiple…

Recently, Vision Transformers (ViTs) have achieved unprecedented effectiveness in the general domain of image classification. Nonetheless, these models remain underexplored in the field of deepfake detection, given their lower performance…

We propose DepthTCM, a physics-aware end-to-end framework for depth map compression. In our framework of DepthTCM, the high-bit depth map is first converted to a conventional 3-channel image representation losslessly using a method inspired…

Multimodal transformer exhibits high capacity and flexibility to align image and text for visual grounding. However, the existing encoder-only grounding framework (e.g., TransVG) suffers from heavy computation due to the self-attention…

The proliferation of Transformer models is often constrained by the significant computational and memory bandwidth demands of deployment. To address this, we present MXFormer, a novel, hybrid, weight-stationary Compute-in-Memory (CIM)…

Active research is currently underway to enhance the efficiency of vision transformers (ViTs). Most studies have focused solely on effective token mixers, overlooking the potential relationship with normalization. To boost diverse feature…

The core of Multi-view Stereo(MVS) is the matching process among reference and source pixels. Cost aggregation plays a significant role in this process, while previous methods focus on handling it via CNNs. This may inherit the natural…

Audio super-resolution aims to recover missing high-frequency details from bandwidth-limited low-resolution audio, thereby improving the naturalness and perceptual quality of the reconstructed signal. However, most existing methods directly…

In this paper, we propose TransMEF, a transformer-based multi-exposure image fusion framework that uses self-supervised multi-task learning. The framework is based on an encoder-decoder network, which can be trained on large natural image…

Feature pyramids have been widely adopted in convolutional neural networks and transformers for tasks in medical image segmentation. However, existing models generally focus on the Encoder-side Transformer for feature extraction. We further…

Due to the computational complexity of self-attention (SA), prevalent techniques for image deblurring often resort to either adopting localized SA or employing coarse-grained global SA methods, both of which exhibit drawbacks such as…

Variational autoencoders (VAEs) are fundamental for generative modeling and image reconstruction, yet their performance often struggles to maintain high fidelity in reconstructions. This study introduces a hybrid model, quantum variational…

Solving flow through porous media is a crucial step in the topology optimisation of cold plates, a key component in modern thermal management. Traditional computational fluid dynamics (CFD) methods, while accurate, are often prohibitively…

Building on the success of diffusion models in visual generation, flow-based models reemerge as another prominent family of generative models that have achieved competitive or better performance in terms of both visual quality and inference…