Related papers: OmnimatteRF: Robust Omnimatte with 3D Background M…
Given a video and a set of input object masks, an omnimatte method aims to decompose the video into semantically meaningful layers containing individual objects along with their associated effects, such as shadows and reflections. Existing…
In Omnimatte, one aims to decompose a given video into semantically meaningful layers, including the background and individual objects along with their associated effects, such as shadows and reflections. Existing methods often require…
Computer vision is increasingly effective at segmenting objects in images and videos; however, scene effects related to the objects -- shadows, reflections, generated smoke, etc -- are typically overlooked. Identifying such scene effects…
We propose "factor matting", an alternative formulation of the video matting problem in terms of counterfactual video synthesis that is better suited for re-composition tasks. The goal of factor matting is to separate the contents of video…
Due to the difficulty of solving the matting problem, lots of methods use some kinds of assistance to acquire high quality alpha matte. Green screen matting methods rely on physical equipment. Trimap-based methods take manual interactions…
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…
We introduce a real-time, high-resolution background replacement technique which operates at 30fps in 4K resolution, and 60fps for HD on a modern GPU. Our technique is based on background matting, where an additional frame of the background…
Matting with a static background, often referred to as ``Background Matting" (BGM), has garnered significant attention within the computer vision community due to its pivotal role in various practical applications like webcasting and photo…
The most recent efforts in video matting have focused on eliminating trimap dependency since trimap annotations are expensive and trimap-based methods are less adaptable for real-time applications. Despite the latest tripmap-free methods…
Omnidirectional cameras are extensively used in various applications to provide a wide field of vision. However, they face a challenge in synthesizing novel views due to the inevitable presence of dynamic objects, including the…
Video matting has traditionally been limited by the lack of high-quality ground-truth data. Most existing video matting datasets provide only human-annotated imperfect alpha and foreground annotations, which must be composited to background…
Inpainting algorithms have achieved remarkable progress in removing objects from images, yet still face two challenges: 1) struggle to handle the object's visual effects such as shadow and reflection; 2) easily generate shape-like artifacts…
LED Virtual Production (VP) uses large LED volumes to render backgrounds in real time, enabling in-camera visual effects but making post-shot changes labor-intensive. We address this with CineMatte, a robust background matting framework for…
3D reconstruction from images has wide applications in Virtual Reality and Automatic Driving, where the precision requirement is very high. Ground-breaking research in the neural radiance field (NeRF) by utilizing Multi-Layer Perceptions…
Recent advancements in 4D scene reconstruction using neural radiance fields (NeRF) have demonstrated the ability to represent dynamic scenes from multi-view videos. However, they fail to reconstruct the dynamic scenes and struggle to fit…
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…
The ability to identify the static background in videos captured by a moving camera is an important pre-requisite for many video applications (e.g. video stabilization, stitching, and segmentation). Existing methods usually face…
We propose a novel neural-network-based method to perform matting of videos depicting people that does not require additional user input such as trimaps. Our architecture achieves temporal stability of the resulting alpha mattes by using…
In light of the success of contrastive learning in the image domain, current self-supervised video representation learning methods usually employ contrastive loss to facilitate video representation learning. When naively pulling two…
True video understanding requires making sense of non-lambertian scenes where the color of light arriving at the camera sensor encodes information about not just the last object it collided with, but about multiple mediums -- colored…