Related papers: Fast-FoundationStereo: Real-Time Zero-Shot Stereo …

We introduce WAFT-Stereo, a simple and effective warping-based method for stereo matching. WAFT-Stereo demonstrates that cost volumes, a common design used in many leading methods, are not necessary for strong performance and can be…

Diffusion generative models have achieved remarkable success in generating images with a fixed resolution. However, existing models have limited ability to generalize to different resolutions when training data at those resolutions are not…

We present Buffer Anytime, a framework for estimation of depth and normal maps (which we call geometric buffers) from video that eliminates the need for paired video--depth and video--normal training data. Instead of relying on large-scale…

Diffusion models are cutting-edge generative models adept at producing diverse, high-quality images. Despite their effectiveness, these models often require significant computational resources owing to their numerous sequential denoising…

Medical image segmentation is vital for clinical diagnosis, yet current deep learning methods often demand extensive expert effort, i.e., either through annotating large training datasets or providing prompts at inference time for each new…

This work introduces a novel method for surface normal estimation from rectified stereo image pairs, leveraging affine transformations derived from disparity values to achieve fast and accurate results. We demonstrate how the rectification…

We present FoundationSLAM, a learning-based monocular dense SLAM system that addresses the absence of geometric consistency in previous flow-based approaches for accurate and robust tracking and mapping. Our core idea is to bridge flow…

We introduce the first end-to-end learning-based solution to near-field Photometric Stereo (PS), where the light sources are close to the object of interest. This setup is especially useful for reconstructing large immobile objects. Our…

Visual Autoregressive modeling (VAR) has emerged as a highly efficient alternative to diffusion-based frameworks, achieving comparable synthesis quality. However, as this paradigm extends to Spacetime Autoregressive modeling (STAR) for…

We present Match-and-Fuse - a zero-shot, training-free method for consistent controlled generation of unstructured image sets - collections that share a common visual element, yet differ in viewpoint, time of capture, and surrounding…

We present a new deep learning-based approach for dense stereo matching. Compared to previous works, our approach does not use deep learning of pixel appearance descriptors, employing very fast classical matching scores instead. At the same…

In this paper, we present Shift Convolution Network (ShiftConvNet) to provide matching capability between two feature maps for stereo estimation. The proposed method can speedily produce a highly accurate disparity map from stereo images. A…

Galvatron is a distributed system for efficiently training large-scale Foundation Models. It overcomes the complexities of selecting optimal parallelism strategies by automatically identifying the most efficient hybrid strategy,…

Diffusion models have achieved remarkable success in text-to-speech (TTS), even in zero-shot scenarios. Recent efforts aim to address the trade-off between inference speed and sound quality, often considered the primary drawback of…

Conditional generative models typically demand large annotated training sets to achieve high-quality synthesis. As a result, there has been significant interest in designing models that perform plug-and-play generation, i.e., to use a…

High-throughput screening using automated microscopes is a key driver in biopharma drug discovery, enabling the parallel evaluation of thousands of drug candidates for diseases such as cancer. Traditional image analysis and deep learning…

Zero-shot learning enables models to generalise to unseen classes by leveraging semantic information, bridging the gap between training and testing sets with non-overlapping classes. While much research has focused on zero-shot learning in…

Foundation models for interactive segmentation in 2D natural images and videos have sparked significant interest in building 3D foundation models for medical imaging. However, the domain gaps and clinical use cases for 3D medical imaging…

Recently, leveraging on the development of end-to-end convolutional neural networks (CNNs), deep stereo matching networks have achieved remarkable performance far exceeding traditional approaches. However, state-of-the-art stereo frameworks…

Perfect synchronization in distributed machine learning problems is inefficient and even impossible due to the existence of latency, package losses and stragglers. We propose a Robust Fully-Asynchronous Stochastic Gradient Tracking method…