相关论文: ASTRA: Let Arbitrary Subjects Transform in Video E…
We propose FlowAnchor, a training-free framework for stable and efficient inversion-free, flow-based video editing. Inversion-free editing methods have recently shown impressive efficiency and structure preservation in images by directly…
Despite the considerable progress achieved in the long video generation problem, there is still significant room to improve the consistency of the generated videos, particularly in terms of their smoothness and transitions between scenes.…
In many video restoration/translation tasks, image processing operations are na\"ively extended to the video domain by processing each frame independently, disregarding the temporal connection of the video frames. This disregard for the…
Text-based speech editing aims to modify specific segments while preserving speaker identity and acoustic context. Existing methods rely on task-specific training, which incurs high data costs and struggles with temporal fidelity in…
Recent advancements in video generation highlight that realistic audio-visual synchronization is crucial for engaging content creation. However, existing video editing methods largely overlook audio-visual synchronization and lack the…
This paper proposes a novel deep learning-based video object matting method that can achieve temporally coherent matting results. Its key component is an attention-based temporal aggregation module that maximizes image matting networks'…
Selecting informative frames from long videos is a combinatorial problem that existing methods address either through efficient heuristics without explicit modeling of query-conditioned temporal structure, or through multi stage retrieval…
Video generation has recently emerged as a central task in the field of generative AI. However, the substantial computational cost inherent in video synthesis makes model distillation a critical technique for efficient deployment. Despite…
Recent video foundation models such as SAM2 excel at prompted video segmentation by treating masks as a general-purpose primitive. However, many real-world settings require unprompted segmentation that aims to detect and track all objects…
Autoregressive video diffusion models hold promise for world simulation but are vulnerable to exposure bias arising from the train-test mismatch. While recent works address this via post-training, they typically rely on a bidirectional…
Video editing serves as a fundamental pillar of digital media, spanning applications in entertainment, education, and professional communication. However, previous methods often overlook the necessity of comprehensively understanding both…
Text-to-video editing aims to edit the visual appearance of a source video conditional on textual prompts. A major challenge in this task is to ensure that all frames in the edited video are visually consistent. Most recent works apply…
In video editing, the hallmark of a quality edit lies in its consistent and unobtrusive adjustment. Modification, when integrated, must be smooth and subtle, preserving the natural flow and aligning seamlessly with the original vision.…
Recent advances in diffusion transformers have empowered video generation models to generate high-quality video clips from texts or images. However, world models with the ability to predict long-horizon futures from past observations and…
Latent space-based facial attribute editing methods have gained popularity in applications such as digital entertainment, virtual avatar creation, and human-computer interaction systems due to their potential for efficient and flexible…
Video summarization aims to generate a concise representation of a video, capturing its essential content and key moments while reducing its overall length. Although several methods employ attention mechanisms to handle long-term…
Video deblurring aims to enhance the quality of restored results in motion-blurred videos by effectively gathering information from adjacent video frames to compensate for the insufficient data in a single blurred frame. However, when faced…
Inversion-based image editing in flow matching models has emerged as a powerful paradigm for training-free, text-guided image manipulation. A central challenge in this paradigm is the injection dilemma: injecting source features during…
The task of language-guided video temporal grounding is to localize the particular video clip corresponding to a query sentence in an untrimmed video. Though progress has been made continuously in this field, some issues still need to be…
Inspired by the impressive performance of recent face image editing methods, several studies have been naturally proposed to extend these methods to the face video editing task. One of the main challenges here is temporal consistency among…