Related papers: SMFormer: Empowering Self-supervised Stereo Matchi…

With an unprecedented increase in the number of agents and systems that aim to navigate the real world using visual cues and the rising impetus for 3D Vision Models, the importance of depth estimation is hard to understate. While supervised…

Recent state-of-the-art semi-supervised learning (SSL) methods use a combination of image-based transformations and consistency regularization as core components. Such methods, however, are limited to simple transformations such as…

Tremendous progress has been made in deep stereo matching to excel on benchmark datasets through per-domain fine-tuning. However, achieving strong zero-shot generalization - a hallmark of foundation models in other computer vision tasks -…

Instance segmentation in electron microscopy (EM) volumes is tough due to complex shapes and sparse annotations. Self-supervised learning helps but still struggles with intricate visual patterns in EM. To address this, we propose a…

Enhancing forward-looking sonar images is critical for accurate underwater target detection. Current deep learning methods mainly rely on supervised training with simulated data, but the difficulty in obtaining high-quality real-world…

Supervised fine-tuning (SFT) on domain-specific data is the dominant approach for adapting foundation models to specialized tasks. However, it has been observed that SFT models tend to forget knowledge acquired during pretraining. In vision…

Subsequence matching has appeared to be an ideal approach for solving many problems related to the fields of data mining and similarity retrieval. It has been shown that almost any data class (audio, image, biometrics, signals) is or can be…

Local feature matching between images remains a challenging task, especially in the presence of significant appearance variations, e.g., extreme viewpoint changes. In this work, we propose DeepMatcher, a deep Transformer-based network built…

Photometric stereo is a technique aimed at determining surface normals through the utilization of shading cues derived from images taken under different lighting conditions. However, existing learning-based approaches often fail to…

Semi-supervised action recognition is a challenging but critical task due to the high cost of video annotations. Existing approaches mainly use convolutional neural networks, yet current revolutionary vision transformer models have been…

As a fundamental vision task, stereo matching has made remarkable progress. While recent iterative optimization-based methods have achieved promising performance, their feature extraction capabilities still have room for improvement.…

Self-supervised Learning (SSL) has recently gained much attention due to the high cost and data limitation in the training of supervised learning models. The current paradigm in the SSL is to utilize data augmentation at the input space to…

Stereo matching is a key technique for metric depth estimation in computer vision and robotics. Real-world challenges like occlusion and non-texture hinder accurate disparity estimation from binocular matching cues. Recently, monocular…

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…

Multi-frame depth estimation improves over single-frame approaches by also leveraging geometric relationships between images via feature matching, in addition to learning appearance-based features. In this paper we revisit feature matching…

We present a simple yet effective self-supervised framework for audio-visual representation learning, to localize the sound source in videos. To understand what enables to learn useful representations, we systematically investigate the…

GigaMVS presents several challenges to existing Multi-View Stereo (MVS) algorithms for its large scale, complex occlusions, and gigapixel images. To address these problems, we first apply one of the state-of-the-art learning-based MVS…

Music structure analysis (MSA) underpins music understanding and controllable generation, yet progress has been limited by small, inconsistent corpora. We present SongFormer, a scalable framework that learns from heterogeneous supervision.…

Self-supervised learning has been shown to be very effective in learning useful representations, and yet much of the success is achieved in data types such as images, audio, and text. The success is mainly enabled by taking advantage of…

Multi-modal data fusion has recently been shown promise in classification tasks in remote sensing. Optical data and radar data, two important yet intrinsically different data sources, are attracting more and more attention for potential…