Related papers: RobustMVS: Single Domain Generalized Deep Multi-vi…

Despite the success on few-shot learning problems, most meta-learned models only focus on achieving good performance on clean examples and thus easily break down when given adversarially perturbed samples. While some recent works have shown…

Multimodal models ideally should generalize to unseen domains while remaining data-efficient to reduce annotation costs. To this end, we introduce and study a new problem, Semi-Supervised Multimodal Domain Generalization (SSMDG), which aims…

Multi-view data analysis has gained increasing popularity because multi-view data are frequently encountered in machine learning applications. A simple but promising approach for clustering of multi-view data is multi-view clustering (MVC),…

While successful for various computer vision tasks, deep neural networks have shown to be vulnerable to texture style shifts and small perturbations to which humans are robust. In this work, we show that the robustness of neural networks…

Video stabilization is pivotal for video processing, as it removes unwanted shakiness while preserving the original user motion intent. Existing approaches, depending on the domain they operate, suffer from several issues (e.g. geometric…

In multi-label classification, machine learning encounters the challenge of domain generalization when handling tasks with distributions differing from the training data. Existing approaches primarily focus on vision object recognition and…

Feedforward 3D Gaussian Splatting (3DGS) overcomes the limitations of optimization-based 3DGS by enabling fast and high-quality reconstruction without the need for per-scene optimization. However, existing feedforward approaches typically…

Multi-modal large language models (MLLMs) have recently achieved great success in processing and understanding information from diverse modalities (e.g., text, audio, and visual signals). Despite their growing popularity, there remains a…

Stereo matching has recently witnessed remarkable progress using Deep Neural Networks (DNNs). But, how robust are they? Although it has been well-known that DNNs often suffer from adversarial vulnerability with a catastrophic drop in…

The reconstruction of textureless areas has long been a challenging problem in MVS due to lack of reliable pixel correspondences between images. In this paper, we propose the Textureless-aware Segmentation And Correlative Refinement guided…

Domain generalization seeks to develop models trained on a limited set of source domains that are capable of generalizing effectively to unseen target domains. While the predominant approach leverages large-scale pre-trained vision models…

Recent work in multi-view stereo (MVS) combines learnable photometric scores and regularization with PatchMatch-based optimization to achieve robust pixelwise estimates of depth, normals, and visibility. However, non-learning based methods…

Domain generalization (DG) aims to incorporate knowledge from multiple source domains into a single model that could generalize well on unseen target domains. This problem is ubiquitous in practice since the distributions of the target data…

Multimodal Large Language Models struggle to maintain reliable performance under extreme real-world visual degradations, which impede their practical robustness. Existing robust MLLMs predominantly rely on implicit training/adaptation that…

Multi-view stereo methods have achieved great success for depth estimation based on the coarse-to-fine depth learning frameworks, however, the existing methods perform poorly in recovering the depth of object boundaries and detail regions.…

Adapting machine learning models to medical time series across different domains remains a challenge due to complex temporal dependencies and dynamic distribution shifts. Current approaches often focus on isolated feature representations,…

This study addresses the challenge of online 3D model generation for neural rendering using an RGB image stream. Previous research has tackled this issue by incorporating Neural Radiance Fields (NeRF) or 3D Gaussian Splatting (3DGS) as…

We propose MVGBench, a comprehensive benchmark for multi-view image generation models (MVGs) that evaluates 3D consistency in geometry and texture, image quality, and semantics (using vision language models). Recently, MVGs have been the…

Recent works in volume rendering, \textit{e.g.} NeRF and 3D Gaussian Splatting (3DGS), significantly advance the rendering quality and efficiency with the help of the learned implicit neural radiance field or 3D Gaussians. Rendering on top…

The dissertation presents four key contributions toward fairness and robustness in vision learning. First, to address the problem of large-scale data requirements, the dissertation presents a novel Fairness Domain Adaptation approach…