中文
相关论文

相关论文: Rebalancing Reference Frame Dominance to Improve M…

200 篇论文

Recent video multimodal large language models (MLLMs) increasingly couple step-by-step reasoning with on-demand visual evidence retrieval, allowing models to revisit relevant video segments during inference. However, two structural gaps…

计算机视觉与模式识别 · 计算机科学 2026-05-27 Peng Zhang , Guanghao Zhang , Wanggui He , Longxiang Zhang , Mushui Liu , Yan Xia , Zhenhao Peng , Weilong Dai , Jinlong Liu , Haobing Tang , Le Zhang , Hao Jiang , Pipei Huang

Text-guided image-to-video generation has made substantial progress, yet it still struggles to execute text-specified edits that require substantial changes to a reference image (\textit{e.g., object addition, removal, or modification}).…

计算机视觉与模式识别 · 计算机科学 2026-05-29 Yexin Liu , Wen-Jie Shu , Zile Huang , Haoze Zheng , Yueze Wang , Jingjin Zhu , Manyuan Zhang , Ser-Nam Lim , Harry Yang

Temporal modeling on regular respiration-induced motions is crucial to image-guided clinical applications. Existing methods cannot simulate temporal motions unless high-dose imaging scans including starting and ending frames exist…

计算机视觉与模式识别 · 计算机科学 2025-06-26 Xin You , Minghui Zhang , Hanxiao Zhang , Jie Yang , Nassir Navab

Image watermarking supports authenticity and provenance, yet many schemes are still easy to bypass with various distortions and powerful generative edits. Deep learning-based watermarking has improved robustness to diffusion-based image…

计算机视觉与模式识别 · 计算机科学 2025-12-23 Utae Jeong , Sumin In , Hyunju Ryu , Jaewan Choi , Feng Yang , Jongheon Jeong , Seungryong Kim , Sangpil Kim

Existing implicit neural representation (INR) methods do not fully exploit spatiotemporal redundancies in videos. Index-based INRs ignore the content-specific spatial features and hybrid INRs ignore the contextual dependency on adjacent…

计算机视觉与模式识别 · 计算机科学 2023-04-14 Qi Zhao , M. Salman Asif , Zhan Ma

Recent advances in Video Large Language Models (VLLMs) have achieved remarkable video understanding capabilities, yet face critical efficiency bottlenecks due to quadratic computational growth with lengthy visual token sequences of long…

计算机视觉与模式识别 · 计算机科学 2025-12-09 Yulin Li , Haokun Gui , Ziyang Fan , Junjie Wang , Bin Kang , Bin Chen , Zhuotao Tian

Training an effective video-and-language model intuitively requires multiple frames as model inputs. However, it is unclear whether using multiple frames is beneficial to downstream tasks, and if yes, whether the performance gain is worth…

计算机视觉与模式识别 · 计算机科学 2022-06-08 Jie Lei , Tamara L. Berg , Mohit Bansal

Image restoration aims to enhance low quality images, producing high quality images that exhibit natural visual characteristics and fine semantic attributes. Recently, the diffusion model has emerged as a powerful technique for image…

计算机视觉与模式识别 · 计算机科学 2024-07-23 Jiangtong Tan , Feng Zhao

Image denoising is a fundamental problem in computational photography, where achieving high perception with low distortion is highly demanding. Current methods either struggle with perceptual quality or suffer from significant distortion.…

计算机视觉与模式识别 · 计算机科学 2024-11-19 Tong Li , Hansen Feng , Lizhi Wang , Zhiwei Xiong , Hua Huang

Advances in diffusion-based video generation models, while significantly improving human animation, poses threats of misuse through the creation of fake videos from a specific person's photo and text prompts. Recent efforts have focused on…

计算机视觉与模式识别 · 计算机科学 2026-03-26 Duc Vu , Anh Nguyen , Chi Tran , Anh Tran

Driven by the upsurge progress in text-to-image (T2I) generation models, text-to-video (T2V) generation has experienced a significant advance as well. Accordingly, tasks such as modifying the object or changing the style in a video have…

计算机视觉与模式识别 · 计算机科学 2023-12-06 Yeji Song , Wonsik Shin , Junsoo Lee , Jeesoo Kim , Nojun Kwak

Aligning text-to-image (T2I) diffusion models with human preferences has emerged as a critical research challenge. While recent advances in this area have extended preference optimization techniques from large language models (LLMs) to the…

计算机视觉与模式识别 · 计算机科学 2025-12-25 Junyong Kang , Seohyun Lim , Kyungjune Baek , Hyunjung Shim

Despite impressive advancements in diffusion-based video editing models in altering video attributes, there has been limited exploration into modifying motion information while preserving the original protagonist's appearance and…

计算机视觉与模式识别 · 计算机科学 2024-05-31 Shuyuan Tu , Qi Dai , Zihao Zhang , Sicheng Xie , Zhi-Qi Cheng , Chong Luo , Xintong Han , Zuxuan Wu , Yu-Gang Jiang

Recent prosperity of text-to-image diffusion models, e.g. Stable Diffusion, has stimulated research to adapt them to 360-degree panorama generation. Prior work has demonstrated the feasibility of using conventional low-rank adaptation…

计算机视觉与模式识别 · 计算机科学 2025-05-29 Jinhong Ni , Chang-Bin Zhang , Qiang Zhang , Jing Zhang

Learning-to-optimize (L2O) is an emerging research area in large-scale optimization with applications in data science. Recently, researchers have proposed a novel L2O framework called learned mirror descent (LMD), based on the classical…

最优化与控制 · 数学 2024-05-13 Hong Ye Tan , Subhadip Mukherjee , Junqi Tang , Carola-Bibiane Schönlieb

Controllable human image animation aims to generate videos from reference images using driving videos. Due to the limited control signals provided by sparse guidance (e.g., skeleton pose), recent works have attempted to introduce additional…

计算机视觉与模式识别 · 计算机科学 2025-02-26 Hongxiang Li , Yaowei Li , Yuhang Yang , Junjie Cao , Zhihong Zhu , Xuxin Cheng , Long Chen

Video is a rich and scalable source of 3D/4D visual observations, and camera control is a key capability for video generation models to produce geometrically meaningful content. Existing approaches typically learn a mapping from camera…

计算机视觉与模式识别 · 计算机科学 2026-05-15 Chen Hou , Christian Rupprecht

One significant factor we expect the video representation learning to capture, especially in contrast with the image representation learning, is the object motion. However, we found that in the current mainstream video datasets, some action…

计算机视觉与模式识别 · 计算机科学 2020-12-17 Jinpeng Wang , Yuting Gao , Ke Li , Jianguo Hu , Xinyang Jiang , Xiaowei Guo , Rongrong Ji , Xing Sun

Recent progress in video diffusion models has markedly advanced character animation, which synthesizes motioned videos by animating a static identity image according to a driving video. Explicit methods represent motion using skeleton,…

计算机视觉与模式识别 · 计算机科学 2026-02-10 Zhufeng Xu , Xuan Gao , Feng-Lin Liu , Haoxian Zhang , Zhixue Fang , Yu-Kun Lai , Xiaoqiang Liu , Pengfei Wan , Lin Gao

Precise camera pose control is crucial for video generation with diffusion models. Existing methods require fine-tuning with additional datasets containing paired videos and camera pose annotations, which are both data-intensive and…

计算机视觉与模式识别 · 计算机科学 2024-12-10 Zhenghong Zhou , Jie An , Jiebo Luo