Related papers: VSFormer: Visual-Spatial Fusion Transformer for Co…

Video personalization aims to generate videos that faithfully reflect a user-provided subject while following a text prompt. However, existing approaches often rely on heavy video-based finetuning or large-scale video datasets, which impose…

Visual Prompt Tuning (VPT) is a parameter-efficient fune-tuning technique that adapts a pre-trained vision Transformer (ViT) by learning a small set of parameters in the input space, known as prompts. In VPT, we uncover ``burstiness'' in…

Accurate camera-LiDAR fusion relies on precise extrinsic calibration, which fundamentally depends on establishing reliable cross-modal correspondences under potentially large misalignments. Existing learning-based methods typically project…

Creating novel images by fusing visual cues from multiple sources is a fundamental yet underexplored problem in image-to-image generation, with broad applications in artistic creation, virtual reality and visual media. Existing methods…

Vision encoders serve as the cornerstone of multimodal understanding. Single-encoder architectures like CLIP exhibit inherent constraints in generalizing across diverse multimodal tasks, while recent multi-encoder fusion methods introduce…

Generating robust and reliable correspondences across images is a fundamental task for a diversity of applications. To capture context at both global and local granularity, we propose ASpanFormer, a Transformer-based detector-free matcher…

DAVIS camera, streaming two complementary sensing modalities of asynchronous events and frames, has gradually been used to address major object detection challenges (e.g., fast motion blur and low-light). However, how to effectively…

We propose FusionBERT, a novel multi-view visual fusion framework for image-3D multimodal retrieval. Existing image-3D representation learning methods predominantly focus on feature alignment of a single object image and its 3D model,…

In this work, we present a conceptually simple yet effective framework for cross-modality 3D object detection, named voxel field fusion. The proposed approach aims to maintain cross-modality consistency by representing and fusing augmented…

Video matting aims to predict the alpha mattes for each frame from a given input video sequence. Recent solutions to video matting have been dominated by deep convolutional neural networks (CNN) for the past few years, which have become the…

Multi-view inverse rendering aims to recover geometry, materials, and illumination consistently across multiple viewpoints. When applied to multi-view images, existing single-view approaches often ignore cross-view relationships, leading to…

Semantic segmentation assigns labels to pixels in images, a critical yet challenging task in computer vision. Convolutional methods, although capturing local dependencies well, struggle with long-range relationships. Vision Transformers…

Video super-resolution (VSR), with the aim to restore a high-resolution video from its corresponding low-resolution version, is a spatial-temporal sequence prediction problem. Recently, Transformer has been gaining popularity due to its…

Although Vision Transformer (ViT) has achieved significant success in computer vision, it does not perform well in dense prediction tasks due to the lack of inner-patch information interaction and the limited diversity of feature scale.…

Document shadow is a common issue that arises when capturing documents using mobile devices, which significantly impacts readability. Current methods encounter various challenges, including inaccurate detection of shadow masks and…

Image matching that finding robust and accurate correspondences across images is a challenging task under extreme conditions. Capturing local and global features simultaneously is an important way to mitigate such an issue but recent…

Medical image segmentation plays an important role in computer-aided diagnosis. Existing methods mainly utilize spatial attention to highlight the region of interest. However, due to limitations of medical imaging devices, medical images…

Convolutional neural network (CNN) based methods have achieved great successes in medical image segmentation, but their capability to learn global representations is still limited due to using small effective receptive fields of convolution…

Vision-Language-Action (VLA) models have shown great potential for embodied AI by integrating visual perception, language understanding, and action execution. In real-time deployment, these models must process continuous visual streams,…

When using cut-and-paste to acquire a composite image, the geometry inconsistency between foreground and background may severely harm its fidelity. To address the geometry inconsistency in composite images, several existing works learned to…