中文
相关论文

相关论文: Castle in the Sky: Dynamic Sky Replacement and Har…

200 篇论文

Image harmonization aims to improve the quality of image compositing by matching the "appearance" (\eg, color tone, brightness and contrast) between foreground and background images. However, collecting large-scale annotated datasets for…

计算机视觉与模式识别 · 计算机科学 2021-08-19 Yifan Jiang , He Zhang , Jianming Zhang , Yilin Wang , Zhe Lin , Kalyan Sunkavalli , Simon Chen , Sohrab Amirghodsi , Sarah Kong , Zhangyang Wang

Acquisition of data with adverse conditions in robotics is a cumbersome task due to the difficulty in guaranteeing proper ground truth and synchronising with desired weather conditions. In this paper, we present a simple method - recording…

计算机视觉与模式识别 · 计算机科学 2020-03-11 Horia Porav , Valentina-Nicoleta Musat , Tom Bruls , Paul Newman

Unwanted camera occlusions, such as debris, dust, rain-drops, and snow, can severely degrade the performance of computer-vision systems. Dynamic occlusions are particularly challenging because of the continuously changing pattern. Existing…

计算机视觉与模式识别 · 计算机科学 2023-08-02 Rong Zou , Manasi Muglikar , Nico Messikommer , Davide Scaramuzza

We introduce a framework that enables both multi-view character consistency and 3D camera control in video diffusion models through a novel customization data pipeline. We train the character consistency component with recorded volumetric…

Precise camera control for reshooting dynamic videos is bottlenecked by the severe scarcity of paired multi-view data for non-rigid scenes. We overcome this limitation with a highly scalable self-supervised framework capable of leveraging…

计算机视觉与模式识别 · 计算机科学 2026-04-27 Avinash Paliwal , Adithya Iyer , Shivin Yadav , Muhammad Ali Afridi , Midhun Harikumar

The visual entities in cross-view images exhibit drastic domain changes due to the difference in viewpoints each set of images is captured from. Existing state-of-the-art methods address the problem by learning view-invariant descriptors…

计算机视觉与模式识别 · 计算机科学 2019-08-12 Krishna Regmi , Mubarak Shah

The issue of image haze removal has attracted wide attention in recent years. However, most existing haze removal methods cannot restore the scene with clear blue sky, since the color and texture information of the object in the original…

计算机视觉与模式识别 · 计算机科学 2022-10-17 Xiaoyan Zhang , Gaoyang Tang , Yingying Zhu , Qi Tian

Image composition plays a common but important role in photo editing. To acquire photo-realistic composite images, one must adjust the appearance and visual style of the foreground to be compatible with the background. Existing deep…

计算机视觉与模式识别 · 计算机科学 2021-06-08 Jun Ling , Han Xue , Li Song , Rong Xie , Xiao Gu

We tackle a 3D scene stylization problem - generating stylized images of a scene from arbitrary novel views given a set of images of the same scene and a reference image of the desired style as inputs. Direct solution of combining novel…

计算机视觉与模式识别 · 计算机科学 2021-09-16 Hsin-Ping Huang , Hung-Yu Tseng , Saurabh Saini , Maneesh Singh , Ming-Hsuan Yang

Dynamic novel view synthesis aims to capture the temporal evolution of visual content within videos. Existing methods struggle to distinguishing between motion and structure, particularly in scenarios where camera poses are either unknown…

计算机视觉与模式识别 · 计算机科学 2024-01-12 Chaoyang Wang , Peiye Zhuang , Aliaksandr Siarohin , Junli Cao , Guocheng Qian , Hsin-Ying Lee , Sergey Tulyakov

We propose technology to enable a new medium of expression, where video elements can be looped, merged, and triggered, interactively. Like audio, video is easy to sample from the real world but hard to segment into clean reusable elements.…

Diffusion-based video depth estimation methods have achieved remarkable success with strong generalization ability. However, predicting depth for long videos remains challenging. Existing methods typically split videos into overlapping…

计算机视觉与模式识别 · 计算机科学 2025-08-08 Yue-Jiang Dong , Wang Zhao , Jiale Xu , Ying Shan , Song-Hai Zhang

Many compelling video processing effects can be achieved if per-pixel depth information and 3D camera calibrations are known. However, the success of such methods is highly dependent on the accuracy of this "scene-space" information. We…

计算机视觉与模式识别 · 计算机科学 2021-02-08 Felix Klose , Oliver Wang , Jean-Charles Bazin , Marcus Magnor , Alexander Sorkine-Hornung

Music videos, as a prevalent form of multimedia entertainment, deliver engaging audio-visual experiences to audiences and have gained immense popularity among singers and fans. Creators can express their interpretations of music naturally…

人机交互 · 计算机科学 2025-04-25 Chuer Chen , Shengqi Dang , Yuqi Liu , Nanxuan Zhao , Yang Shi , Nan Cao

Existing video generation models struggle to maintain long-term spatial and temporal consistency due to the dense, high-dimensional nature of video signals. To overcome this limitation, we propose Spatia, a spatial memory-aware video…

计算机视觉与模式识别 · 计算机科学 2025-12-18 Jinjing Zhao , Fangyun Wei , Zhening Liu , Hongyang Zhang , Chang Xu , Yan Lu

In recent years there have been remarkable breakthroughs in image-to-video generation. However, the 3D consistency and camera controllability of generated frames have remained unsolved. Recent studies have attempted to incorporate camera…

计算机视觉与模式识别 · 计算机科学 2024-10-15 Dejia Xu , Yifan Jiang , Chen Huang , Liangchen Song , Thorsten Gernoth , Liangliang Cao , Zhangyang Wang , Hao Tang

We introduce a novel geometry-guided online video view synthesis method with enhanced view and temporal consistency. Traditional approaches achieve high-quality synthesis from dense multi-view camera setups but require significant…

计算机视觉与模式识别 · 计算机科学 2025-05-27 Hyunho Ha , Lei Xiao , Christian Richardt , Thu Nguyen-Phuoc , Changil Kim , Min H. Kim , Douglas Lanman , Numair Khan

Panoramic image stitching provides a unified, wide-angle view of a scene that extends beyond the camera's field of view. Stitching frames of a panning video into a panoramic photograph is a well-understood problem for stationary scenes, but…

计算机视觉与模式识别 · 计算机科学 2024-10-29 Jingwei Ma , Erika Lu , Roni Paiss , Shiran Zada , Aleksander Holynski , Tali Dekel , Brian Curless , Michael Rubinstein , Forrester Cole

Lens flare is a degradation phenomenon caused by strong light sources. Existing researches on flare removal have mainly focused on images, while the spatiotemporal characteristics of video flare remain largely unexplored. Video flare…

计算机视觉与模式识别 · 计算机科学 2025-12-15 Junqiao Wang , Yuanfei Huang , Hua Huang

Recent advances in image-based human pose estimation make it possible to capture 3D human motion from a single RGB video. However, the inherent depth ambiguity and self-occlusion in a single view prohibit the recovery of as high-quality…

计算机视觉与模式识别 · 计算机科学 2020-08-20 Junting Dong , Qing Shuai , Yuanqing Zhang , Xian Liu , Xiaowei Zhou , Hujun Bao