相关论文: Training-Free Neural Matte Extraction for Visual E…
Continual learning for video--language understanding is increasingly important as models face non-stationary data, domains, and query styles, yet prevailing solutions blur what should stay stable versus what should adapt, rely on static…
Understanding long, real-world videos requires modeling of long-range visual dependencies. To this end, we explore video-first architectures, building on the common paradigm of transferring large-scale, image--text models to video via…
Visual effects (VFX) are crucial to the expressive power of digital media, yet their creation remains a major challenge for generative AI. Prevailing methods often rely on the one-LoRA-per-effect paradigm, which is resource-intensive and…
The abundance and ease of utilizing sound, along with the fact that auditory clues reveal so much about what happens in the scene, make the audio-visual space a perfectly intuitive choice for self-supervised representation learning.…
We describe a technique that automatically generates plausible depth maps from videos using non-parametric depth sampling. We demonstrate our technique in cases where past methods fail (non-translating cameras and dynamic scenes). Our…
There has been a growing trend in compressing and transmitting videos from terminals for machine vision tasks. Nevertheless, most video coding optimization method focus on minimizing distortion according to human perceptual metrics,…
We aim to leverage diffusion to address the challenging image matting task. However, the presence of high computational overhead and the inconsistency of noise sampling between the training and inference processes pose significant obstacles…
This paper addresses the problem of transparent object matting. Existing image matting approaches for transparent objects often require tedious capturing procedures and long processing time, which limit their practical use. In this paper,…
Most existing human matting algorithms tried to separate pure human-only foreground from the background. In this paper, we propose a Virtual Multi-modality Foreground Matting (VMFM) method to learn human-object interactive foreground (human…
Learning an animatable and clothed human avatar model with vivid dynamics and photorealistic appearance from multi-view videos is an important foundational research problem in computer graphics and vision. Fueled by recent advances in…
Background In analytical chemistry, spatial information about materials is commonly captured through imaging techniques, such as traditional color cameras or with advanced hyperspectral cameras and microscopes. However, efficiently…
Recently, trimap-free methods have drawn increasing attention in human video matting due to their promising performance. Nevertheless, these methods still suffer from the lack of deterministic foreground-background cues, which impairs their…
Detecting video deepfakes has become increasingly urgent in recent years. Given the audio-visual information in videos, existing methods typically expose deepfakes by modeling cross-modal correspondence using specifically designed…
The design of deep learning methods for low light video enhancement remains a challenging problem owing to the difficulty in capturing low light and ground truth video pairs. This is particularly hard in the context of dynamic scenes or…
Feature visualization is used to visualize learned features for black box machine learning models. Our approach explores an altered training process to improve interpretability of the visualizations. We argue that by using background…
Video question-answering is a fundamental task in the field of video understanding. Although current vision--language models (VLMs) equipped with Video Transformers have enabled temporal modeling and yielded superior results, they are at…
Video salient object detection aims to find the most visually distinctive objects in a video. To explore the temporal dependencies, existing methods usually resort to recurrent neural networks or optical flow. However, these approaches…
Temporal modeling is crucial for various video learning tasks. Most recent approaches employ either factorized (2D+1D) or joint (3D) spatial-temporal operations to extract temporal contexts from the input frames. While the former is more…
Recently, with the enormous growth of online videos, fast video retrieval research has received increasing attention. As an extension of image hashing techniques, traditional video hashing methods mainly depend on hand-crafted features and…
A novel image matching method is proposed that utilizes learned features extracted by an off-the-shelf deep neural network to obtain a promising performance. The proposed method uses pre-trained VGG architecture as a feature extractor and…