Related papers: From Understanding to Erasing: Towards Complete an…
Video editing increasingly demands the ability to incorporate specific real-world instances into existing footage, yet current approaches fundamentally fail to capture the unique visual characteristics of particular subjects and ensure…
The appearance of an object can be fleeting when it transforms. As eggs are broken or paper is torn, their color, shape and texture can change dramatically, preserving virtually nothing of the original except for the identity itself. Yet,…
Despite remarkable achievements in video synthesis, achieving granular control over complex dynamics, such as nuanced movement among multiple interacting objects, still presents a significant hurdle for dynamic world modeling, compounded by…
Object removal has so far been dominated by the mask-and-inpaint paradigm, where the masked region is excluded from the input, leaving models relying on unmasked areas to inpaint the missing region. However, this approach lacks contextual…
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…
The rapid development of diffusion models (DMs) has significantly advanced image and video applications, making "what you want is what you see" a reality. Among these, video editing has gained substantial attention and seen a swift rise in…
Video understanding is a growing field and a subject of intense research, which includes many interesting tasks to understanding both spatial and temporal information, e.g., action detection, action recognition, video captioning, video…
Diffusion-based generative models have revolutionized object-oriented image editing, yet their deployment in realistic object removal and insertion remains hampered by challenges such as the intricate interplay of physical effects and…
We study the problem of animating images by transferring spatio-temporal visual effects (such as melting) from a collection of videos. We tackle two primary challenges in visual effect transfer: 1) how to capture the effect we wish to…
Video segmentation aims at partitioning video sequences into meaningful segments based on objects or regions of interest within frames. Current video segmentation models are often derived from image segmentation techniques, which struggle…
In this thesis we discuss architectural designs and training methods for a neural network to have the ability of dissecting an image into objects of interest without supervision. The main challenge in 2D unsupervised object segmentation is…
Inspired by recent advances of deep learning in instance segmentation and object tracking, we introduce video object segmentation problem as a concept of guided instance segmentation. Our model proceeds on a per-frame basis, guided by the…
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…
Unsupervised object-centric learning from videos is a promising approach to extract structured representations from large, unlabeled collections of videos. To support downstream tasks like autonomous control, these representations must be…
We propose an end-to-end learning framework for segmenting generic objects in videos. Our method learns to combine appearance and motion information to produce pixel level segmentation masks for all prominent objects in videos. We formulate…
Video virtual try-on aims to transfer a clothing item onto the video of a target person. Directly applying the technique of image-based try-on to the video domain in a frame-wise manner will cause temporal-inconsistent outcomes while…
Recent advances in text-to-image diffusion models have substantially improved the quality of image customization, enabling the synthesis of highly realistic images. Despite this progress, achieving fast and efficient personalization remains…
The objective of this work is to learn an object-centric video representation, with the aim of improving transferability to novel tasks, i.e., tasks different from the pre-training task of action classification. To this end, we introduce a…
While modern generative models such as diffusion-based architectures have enabled impressive creative capabilities, they also raise important safety and ethical risks. These concerns have led to growing interest in concept erasure, the…
The rapid growth of text-to-image diffusion models has raised concerns about their potential misuse in generating harmful or unauthorized contents. To address these issues, several Concept Erasure methods have been proposed. However, most…