Related papers: DiveUp: Learning Feature Upsampling from Diverse V…

Vision foundation models (VFMs) such as DINOv2 and CLIP have achieved impressive results on various downstream tasks, but their limited feature resolution hampers performance in applications requiring pixel-level understanding. Feature…

Vision Foundation Models (VFMs) are large-scale, pre-trained models that serve as general-purpose backbones for various computer vision tasks. As VFMs' popularity grows, there is an increasing interest in understanding their effectiveness…

Although large-scale visual foundation models (VFMs) achieve remarkable performance in semantic understanding, they still underperform in instance-aware dense prediction tasks. They exhibit different biases in representation: for instance,…

Vision Foundation Models (VFMs) extract spatially downsampled representations, posing challenges for pixel-level tasks. Existing upsampling approaches face a fundamental trade-off: classical filters are fast and broadly applicable but rely…

Deep features are a cornerstone of computer vision research, capturing image semantics and enabling the community to solve downstream tasks even in the zero- or few-shot regime. However, these features often lack the spatial resolution to…

We introduce AnyUp, a method for feature upsampling that can be applied to any vision feature at any resolution, without encoder-specific training. Existing learning-based upsamplers for features like DINO or CLIP need to be re-trained for…

Deep-learning-based local feature extraction algorithms that combine detection and description have made significant progress in visible image matching. However, the end-to-end training of such frameworks is notoriously unstable due to the…

Source-Free Object Detection (SFOD) aims to adapt a source-pretrained object detector to a target domain without access to source data. However, existing SFOD methods predominantly rely on internal knowledge from the source model, which…

Recent advances in end-to-end unsupervised learning has significantly improved the performance of monocular depth prediction and alleviated the requirement of ground truth depth. Although a plethora of work has been done in enforcing…

Image fusion aims to integrate complementary information from multiple source images to produce a more informative and visually consistent representation, benefiting both human perception and downstream vision tasks. Despite recent…

Learning versatile, fine-grained representations from irregular event streams is pivotal yet nontrivial, primarily due to the heavy annotation that hinders scalability in dataset size, semantic richness, and application scope. To mitigate…

Vision Foundation Models (VFMs) have become the cornerstone of modern computer vision, offering robust representations across a wide array of tasks. While recent advances allow these models to handle varying input sizes during training,…

Leveraging the vision foundation models has emerged as a mainstream paradigm that improves the performance of image feature matching. However, previous works have ignored the misalignment when introducing the foundation models into feature…

Generating high-dimensional visual modalities is a computationally intensive task. A common solution is progressive generation, where the outputs are synthesized in a coarse-to-fine spectral autoregressive manner. While diffusion models…

Multimodal image matching seeks pixel-level correspondences between images of different modalities, crucial for cross-modal perception, fusion and analysis. However, the significant appearance differences between modalities make this task…

Vision foundation models (VFMs) are predominantly developed using data-centric methods. These methods require training on vast amounts of data usually with high-quality labels, which poses a bottleneck for most institutions that lack both…

Deep learning underlies most modern approaches and tools in computer vision, including biomedical imaging. However, for interactive semantic segmentation (often called pixel classification in this context) and interactive object-level…

Diffusion Probabilistic Field (DPF) models the distribution of continuous functions defined over metric spaces. While DPF shows great potential for unifying data generation of various modalities including images, videos, and 3D geometry, it…

We introduce a unified single and multi-view neural implicit 3D reconstruction framework VPFusion. VPFusion attains high-quality reconstruction using both - 3D feature volume to capture 3D-structure-aware context, and pixel-aligned image…

Foundation models are vital tools in various Computer Vision applications. They take as input a single RGB image and output a deep feature representation that is useful for various applications. However, in case we have multiple views of…