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

With the development of deep learning, ViT-based stereo matching methods have made significant progress due to their remarkable robustness and zero-shot ability. However, due to the limitations of ViTs in handling resolution sensitivity and…

Flow matching as a paradigm of generative model achieves notable success across various domains. However, existing methods use either multi-round training or knowledge within minibatches, posing challenges in finding a favorable coupling…

Despite stereo matching accuracy has greatly improved by deep learning in the last few years, recovering sharp boundaries and high-resolution outputs efficiently remains challenging. In this paper, we propose Stereo Mixture Density Networks…

Stereo matching is a critical task for robot navigation and autonomous vehicles, providing the depth estimation of surroundings. Among all stereo matching algorithms, Efficient Large-scale Stereo (ELAS) offers one of the best tradeoffs…

Diffusion models have achieved impressive generative quality across modalities like 2D images, videos, and 3D shapes, but their inference remains computationally expensive due to the iterative denoising process. While recent caching-based…

Partitioning large machine learning models across distributed accelerator systems is a complex process, requiring a series of interdependent decisions that are further complicated by internal sharding ambiguities. Consequently, existing…

We introduce RAFT-Stereo, a new deep architecture for rectified stereo based on the optical flow network RAFT. We introduce multi-level convolutional GRUs, which more efficiently propagate information across the image. A modified version of…

Flow-matching models have enabled high-quality text-to-speech synthesis, but their iterative sampling process during inference incurs substantial computational cost. Although distillation is widely used to reduce the number of inference…

We introduce a novel architecture for neural disparity refinement aimed at facilitating deployment of 3D computer vision on cheap and widespread consumer devices, such as mobile phones. Our approach relies on a continuous formulation that…

Clustering tabular data remains a significant open challenge in data analysis and machine learning. Unlike for image data, similarity between tabular records often varies across datasets, making the definition of clusters highly…

Deep networks for stereo matching typically leverage 2D or 3D convolutional encoder-decoder architectures to aggregate cost and regularize the cost volume for accurate disparity estimation. Due to content-insensitive convolutions and…

Diffusion Transformers (DiT) have attracted significant attention in research. However, they suffer from a slow convergence rate. In this paper, we aim to accelerate DiT training without any architectural modification. We identify the…

Image denoising is a fundamental problem in computer vision and medical imaging. However, real-world images are often degraded by structured noise with strong anisotropic correlations that existing methods struggle to remove. Most…

Video recognition models are typically trained on fixed taxonomies which are often too coarse, collapsing distinctions in object, manner or outcome under a single label. As tasks and definitions evolve, such models cannot accommodate…

With the advent of convolutional neural networks, stereo matching algorithms have recently gained tremendous progress. However, it remains a great challenge to accurately extract disparities from real-world image pairs taken by…

Dynamic tetrahedral simulation pipelines rebuild topology-dependent solver state after every fracture, refinement, or merge event - discarding structural continuity that survives each edit and spending global work on what are often local…

Depth estimation is a cornerstone of a vast number of applications requiring 3D assessment of the environment, such as robotics, augmented reality, and autonomous driving to name a few. One prominent technique for depth estimation is stereo…

Thanks to the powerful generative capacity of diffusion models, recent years have witnessed rapid progress in human motion generation. Existing diffusion-based methods employ disparate network architectures and training strategies. The…

Exiting deep-learning based dense stereo matching methods often rely on ground-truth disparity maps as the training signals, which are however not always available in many situations. In this paper, we design a simple convolutional neural…

Stereo matching is a fundamental task in scene comprehension. In recent years, the method based on iterative optimization has shown promise in stereo matching. However, the current iteration framework employs a single-peak lookup, which…