中文
相关论文

相关论文: CoCoCo: Improving Text-Guided Video Inpainting for…

200 篇论文

Talking head video generation aims to generate a realistic talking head video that preserves the person's identity from a source image and the motion from a driving video. Despite the promising progress made in the field, it remains a…

计算机视觉与模式识别 · 计算机科学 2025-03-26 Shuling Zhao , Fa-Ting Hong , Xiaoshui Huang , Dan Xu

This paper presents a novel framework termed Cut-and-Paste for real-word semantic video editing under the guidance of text prompt and additional reference image. While the text-driven video editing has demonstrated remarkable ability to…

计算机视觉与模式识别 · 计算机科学 2023-11-21 Zhichao Zuo , Zhao Zhang , Yan Luo , Yang Zhao , Haijun Zhang , Yi Yang , Meng Wang

Deep learning-based video inpainting has yielded promising results and gained increasing attention from researchers. Generally, these methods usually assume that the corrupted region masks of each frame are known and easily obtained.…

计算机视觉与模式识别 · 计算机科学 2022-11-18 Zhiliang Wu , Hanyu Xuan , Changchang Sun , Kang Zhang , Yan Yan

Existing video colorization methods struggle with temporal flickering or demand extensive manual input. We propose a novel approach automating high-fidelity video colorization using rich semantic guidance derived from language and…

计算机视觉与模式识别 · 计算机科学 2025-12-01 Silvia Dani , Tiberio Uricchio , Lorenzo Seidenari

Generating geometrically consistent videos remains an open challenge: text-to-video diffusion models trained on web-scale data treat geometry only implicitly, leading to object deformation, texture drift, and non-rigid backgrounds under…

计算机视觉与模式识别 · 计算机科学 2026-05-19 Jan Ackermann , Shengqu Cai , Boyang Deng , Zhengfei Kuang , Songyou Peng , Gordon Wetzstein

While recent years have witnessed great progress on using diffusion models for video generation, most of them are simple extensions of image generation frameworks, which fail to explicitly consider one of the key differences between videos…

计算机视觉与模式识别 · 计算机科学 2024-07-31 Jingyun Liang , Yuchen Fan , Kai Zhang , Radu Timofte , Luc Van Gool , Rakesh Ranjan

Diffusion models have recently advanced video editing, yet controllable editing remains challenging due to the need for precise manipulation of diverse object properties. Current methods require different control signal for diverse editing…

计算机视觉与模式识别 · 计算机科学 2025-09-03 Yuqing Chen , Junjie Wang , Lin Liu , Ruihang Chu , Xiaopeng Zhang , Qi Tian , Yujiu Yang

This study introduces Text-Guided Subject-Driven Image Inpainting, a novel task that combines text and exemplar images for image inpainting. While both text and exemplar images have been used independently in previous efforts, their…

计算机视觉与模式识别 · 计算机科学 2023-12-08 Shaoan Xie , Yang Zhao , Zhisheng Xiao , Kelvin C. K. Chan , Yandong Li , Yanwu Xu , Kun Zhang , Tingbo Hou

Current multimodal models leveraging contrastive learning often face limitations in developing fine-grained conceptual understanding. This is due to random negative samples during pretraining, causing almost exclusively very dissimilar…

计算机视觉与模式识别 · 计算机科学 2024-08-06 Philipp J. Rösch , Norbert Oswald , Michaela Geierhos , Jindřich Libovický

Foreground-conditioned inpainting aims to seamlessly fill the background region of an image by utilizing the provided foreground subject and a text description. While existing T2I-based image inpainting methods can be applied to this task,…

计算机视觉与模式识别 · 计算机科学 2025-08-07 Guangben Lu , Yuzhen Du , Zhimin Sun , Ran Yi , Yifan Qi , Yizhe Tang , Tianyi Wang , Lizhuang Ma , Fangyuan Zou

Synthesizing motion-rich and temporally consistent videos remains a challenge in artificial intelligence, especially when dealing with extended durations. Existing text-to-video (T2V) models commonly employ spatial cross-attention for text…

计算机视觉与模式识别 · 计算机科学 2025-08-18 Jiasong Feng , Ao Ma , Jing Wang , Ke Cao , Zhanjie Zhang

Viewpoint change invariance and action temporal consistency are critical aspects for the effective deployment of human action detection of untrimmed videos. Existing appearance-based video detection methods often struggle with limited…

计算机视觉与模式识别 · 计算机科学 2026-05-22 Yannick Porto , Renato Martins , Thomas Chalumeau , Cedric Demonceaux

Reward-based fine-tuning of video diffusion models is an effective approach to improve the quality of generated videos, as it can fine-tune models without requiring real-world video datasets. However, it can sometimes be limited to specific…

计算机视觉与模式识别 · 计算机科学 2025-10-24 Takehiro Aoshima , Yusuke Shinohara , Byeongseon Park

Trajectory-controlled human motion generation aims to synthesize realistic human motions conditioned on both textual descriptions and spatial trajectories. However, existing methods suffer from two critical limitations: first, the conflict…

计算机视觉与模式识别 · 计算机科学 2026-05-14 Deli Cai , Haoyang Ma , Changxing Ding

Video colorization task has recently attracted wide attention. Recent methods mainly work on the temporal consistency in adjacent frames or frames with small interval. However, it still faces severe challenge of the inconsistency between…

计算机视觉与模式识别 · 计算机科学 2023-05-16 Yu Zhang , Siqi Chen , Mingdao Wang , Xianlin Zhang , Chuang Zhu , Yue Zhang , Xueming Li

Despite advancements in Text-to-Video (T2V) generation, producing videos with realistic motion remains challenging. Current models often yield static or minimally dynamic outputs, failing to capture complex motions described by text. This…

计算机视觉与模式识别 · 计算机科学 2024-11-01 Penghui Ruan , Pichao Wang , Divya Saxena , Jiannong Cao , Yuhui Shi

This paper presents DreamDance, a novel character art animation framework capable of producing stable, consistent character and scene motion conditioned on precise camera trajectories. To achieve this, we re-formulate the animation task as…

计算机视觉与模式识别 · 计算机科学 2025-06-02 Jiaxu Zhang , Xianfang Zeng , Xin Chen , Wei Zuo , Gang Yu , Guosheng Lin , Zhigang Tu

The field of video generation has expanded significantly in recent years, with controllable and compositional video generation garnering considerable interest. Most methods rely on leveraging annotations such as text, objects' bounding…

计算机视觉与模式识别 · 计算机科学 2025-03-25 Aram Davtyan , Sepehr Sameni , Björn Ommer , Paolo Favaro

To generate accurate videos, algorithms have to understand the spatial and temporal dependencies in the world. Current algorithms enable accurate predictions over short horizons but tend to suffer from temporal inconsistencies. When…

计算机视觉与模式识别 · 计算机科学 2023-06-02 Wilson Yan , Danijar Hafner , Stephen James , Pieter Abbeel

Giving machines the ability to imagine possible new objects or scenes from linguistic descriptions and produce their realistic renderings is arguably one of the most challenging problems in computer vision. Recent advances in deep…

计算机视觉与模式识别 · 计算机科学 2022-11-08 Levent Karacan , Tolga Kerimoğlu , İsmail İnan , Tolga Birdal , Erkut Erdem , Aykut Erdem