Related papers: LLVD: LSTM-based Explicit Motion Modeling in Laten…
Existing 3D face modeling methods usually depend on 3D Morphable Models, which inherently constrain the representation capacity to fixed shape priors. Optimization-based approaches offer high-quality reconstructions but tend to be…
We present a new data-driven video inpainting method for recovering missing regions of video frames. A novel deep learning architecture is proposed which contains two sub-networks: a temporal structure inference network and a spatial detail…
When it comes to image compression in digital cameras, denoising is traditionally performed prior to compression. However, there are applications where image noise may be necessary to demonstrate the trustworthiness of the image, such as…
Recent open-vocabulary 3D scene understanding approaches mainly focus on training 3D networks through contrastive learning with point-text pairs or by distilling 2D features into 3D models via point-pixel alignment. While these methods show…
Simultaneous Localization and Mapping (SLAM) has been crucial across various domains, including autonomous driving, mobile robotics, and mixed reality. Dense visual SLAM, leveraging RGB-D camera systems, offers advantages but faces…
The proliferation of mobile devices and social media has revolutionized content dissemination, with short-form video becoming increasingly prevalent. This shift has introduced the challenge of video reframing to fit various screen aspect…
Spatio-temporal contexts are crucial in understanding human actions in videos. Recent state-of-the-art Convolutional Neural Network (ConvNet) based action recognition systems frequently involve 3D spatio-temporal ConvNet filters, chunking…
Deep convolutional neural networks (CNNs) for video denoising are typically trained with supervision, assuming the availability of clean videos. However, in many applications, such as microscopy, noiseless videos are not available. To…
Vision-and-language navigation (VLN) stands as a key research problem of Embodied AI, aiming at enabling agents to navigate in unseen environments following linguistic instructions. In this field, generalization is a long-standing…
Recent developments in Multimodal Large Language Models (MLLMs) have significantly improved Vision-Language (VL) reasoning in 2D domains. However, extending these capabilities to 3D scene understanding remains a major challenge. Existing 3D…
Unsupervised Video Object Segmentation (VOS) aims at identifying the contours of primary foreground objects in videos without any prior knowledge. However, previous methods do not fully use spatial-temporal context and fail to tackle this…
Low-light videos often exhibit spatiotemporal incoherent noise, leading to poor visibility and compromised performance across various computer vision applications. One significant challenge in enhancing such content using modern…
Decomposing a video into a layer-based representation is crucial for easy video editing for the creative industries, as it enables independent editing of specific layers. Existing video-layer decomposition models rely on implicit neural…
In this paper, we present an algorithm for real-world license plate recognition (LPR) from a low-quality image. Our method is built upon a framework that includes denoising and rectification, and each task is conducted by Convolutional…
With recent advancements in video backbone architectures, combined with the remarkable achievements of large language models (LLMs), the analysis of long-form videos spanning tens of minutes has become both feasible and increasingly…
Non-Line-of-Sight (NLOS) imaging aims at recovering the 3D geometry of objects that are hidden from the direct line of sight. In the past, this method has suffered from the weak available multibounce signal limiting scene size, capture…
Image processing on surfaces has drawn significant interest in recent years, particularly in the context of denoising. Salt-and-pepper noise is a special type of noise which randomly sets a portion of the image pixels to the minimum or…
Continual learning in large language models (LLMs) is prone to catastrophic forgetting, where adapting to new tasks significantly degrades performance on previously learned ones. Existing methods typically rely on low-rank,…
Neural Representations for Videos (NeRV) encode entire video sequences within neural network parameters, offering an alternative paradigm to conventional video codecs. However, the convolutional decoder of NeRV remains computationally…
Images obtained in real-world low-light conditions are not only low in brightness, but they also suffer from many other types of degradation, such as color bias, unknown noise, detail loss and halo artifacts. In this paper, we propose a…