中文
相关论文

相关论文: VEFX-Bench: A Holistic Benchmark for Generic Video…

200 篇论文

Facial expression image editing requires fine-grained control to strictly preserve human identity and background while precisely manipulating expression. However, existing editing benchmarks primarily focus on general scenarios, lacking…

计算机视觉与模式识别 · 计算机科学 2026-04-01 Fengjian Xue , Xuecheng Wu , Heli Sun , Yunyun Shi , Shi Chen , Liangyu Fu , Jinheng Xie , Dingkang Yang , Hao Wang , Junxiao Xue , Liang He

Recent generative models have achieved remarkable progress in image editing. However, existing systems and benchmarks remain largely text-guided. In contrast, human communication is inherently multimodal, where visual instructions such as…

计算机视觉与模式识别 · 计算机科学 2026-05-22 Huanyu Zhang , Xuehai Bai , Chengzu Li , Chen Liang , Haochen Tian , Haodong Li , Ruichuan An , Yifan Zhang , Anna Korhonen , Zhang Zhang , Liang Wang , Tieniu Tan

With the rapid advancement of video understanding, existing benchmarks are becoming increasingly saturated, exposing a critical discrepancy between inflated leaderboard scores and real-world model capabilities. To address this widening gap,…

A well-designed reward is critical for effective reinforcement learning-based policy improvement. In real-world robotics, obtaining such rewards typically requires either labor-intensive human labeling or brittle, handcrafted objectives.…

机器人学 · 计算机科学 2026-01-09 Tony Lee , Andrew Wagenmaker , Karl Pertsch , Percy Liang , Sergey Levine , Chelsea Finn

Instruction-based image editing aims to modify specific content within existing images according to user-provided instructions while preserving non-target regions. Beyond traditional object- and style-centric manipulation, text-centric…

计算机视觉与模式识别 · 计算机科学 2026-03-13 Hui Zhang , Juntao Liu , Zongkai Liu , Liqiang Niu , Fandong Meng , Zuxuan Wu , Yu-Gang Jiang

Recent text-guided image editing (TIE) models have achieved remarkable progress, however, many edited results still suffer from artifacts, unintended modifications, and suboptimal aesthetics. Although several benchmarks and evaluation…

计算机视觉与模式识别 · 计算机科学 2026-05-11 Honghua Chen , Zitong Xu , Huiyu Duan , Xinyun Zhang , Xiongkuo Min , Guangtao Zhai

Text-driven video editing is rapidly advancing, yet its rigorous evaluation remains challenging due to the absence of dedicated video quality assessment (VQA) models capable of discerning the nuances of editing quality. To address this…

计算机视觉与模式识别 · 计算机科学 2025-05-27 Juntong Wang , Jiarui Wang , Huiyu Duan , Guangtao Zhai , Xiongkuo Min

Video editing according to instructions is a highly challenging task due to the difficulty in collecting large-scale, high-quality edited video pair data. This scarcity not only limits the availability of training data but also hinders the…

计算机视觉与模式识别 · 计算机科学 2025-03-25 Chi Zhang , Chengjian Feng , Feng Yan , Qiming Zhang , Mingjin Zhang , Yujie Zhong , Jing Zhang , Lin Ma

Most of the existing video face super-resolution (VFSR) methods are trained and evaluated on VoxCeleb1, which is designed specifically for speaker identification and the frames in this dataset are of low quality. As a consequence, the VFSR…

图像与视频处理 · 电气工程与系统科学 2022-05-10 Liangbin Xie. Xintao Wang , Honglun Zhang , Chao Dong , Ying Shan

The rapid evolution of generative video foundation models has propelled the field toward professional-grade cinematic synthesis. To achieve such demanding quality, the community transitions towards Reinforcement Learning (RL) and agentic…

The burgeoning field of Artificial Intelligence Generated Content (AIGC) is witnessing rapid advancements, particularly in video generation. This paper introduces AIGCBench, a pioneering comprehensive and scalable benchmark designed to…

计算机视觉与模式识别 · 计算机科学 2024-01-24 Fanda Fan , Chunjie Luo , Wanling Gao , Jianfeng Zhan

Large multimodal models (LMMs) with advanced video analysis capabilities have recently garnered significant attention. However, most evaluations rely on traditional methods like multiple-choice questions in benchmarks such as VideoMME and…

计算机视觉与模式识别 · 计算机科学 2025-03-25 Ziyang Luo , Haoning Wu , Dongxu Li , Jing Ma , Mohan Kankanhalli , Junnan Li

Long videos contain a vast amount of information, making video-text retrieval an essential and challenging task in multimodal learning. However, existing benchmarks suffer from limited video duration, low-quality captions, and coarse…

计算机视觉与模式识别 · 计算机科学 2026-02-05 Qifeng Cai , Hao Liang , Zhaoyang Han , Hejun Dong , Meiyi Qiang , Ruichuan An , Quanqing Xu , Bin Cui , Wentao Zhang

Video generation has advanced significantly, evolving from producing unrealistic outputs to generating videos that appear visually convincing and temporally coherent. To evaluate these video generative models, benchmarks such as VBench have…

计算机视觉与模式识别 · 计算机科学 2025-08-21 Dian Zheng , Ziqi Huang , Hongbo Liu , Kai Zou , Yinan He , Fan Zhang , Lulu Gu , Yuanhan Zhang , Jingwen He , Wei-Shi Zheng , Yu Qiao , Ziwei Liu

While text-to-visual models now produce photo-realistic images and videos, they struggle with compositional text prompts involving attributes, relationships, and higher-order reasoning such as logic and comparison. In this work, we conduct…

计算机视觉与模式识别 · 计算机科学 2024-11-05 Baiqi Li , Zhiqiu Lin , Deepak Pathak , Jiayao Li , Yixin Fei , Kewen Wu , Tiffany Ling , Xide Xia , Pengchuan Zhang , Graham Neubig , Deva Ramanan

Recent advances in AI-generated content (AIGC) have led to the emergence of powerful text-to-video generation models. Despite these successes, evaluating the quality of AIGC-generated videos remains challenging due to limited…

计算机视觉与模式识别 · 计算机科学 2025-06-24 Xuanyu Zhang , Weiqi Li , Shijie Zhao , Junlin Li , Li Zhang , Jian Zhang

Video generation models have developed rapidly in recent years, where generating natural human motion plays a pivotal role. However, accurately evaluating the quality of generated human motion video remains a significant challenge. Existing…

计算机视觉与模式识别 · 计算机科学 2026-04-29 Bingzi Zhang , Kaisi Guan , Ruihua Song

Long-form video generation is rapidly moving from short, single-scene synthesis toward minute-long, multi-shot creation with narrative structure, cinematic control, audio, and cross-modal synchronization. However, evaluating such videos…

计算与语言 · 计算机科学 2026-05-29 Jiamin Chen , Qianben Chen , Jiawen Zhang , Yidi Wu , Yuchen Li , Xiaokun Zhang , Wangchunshu Zhou , Chen Ma

With AI-generated videos increasingly indistinguishable from reality, current benchmarks primarily focus on broad semantic alignment and basic physical consistency, offering limited discriminative power for evaluating them. To address this,…

计算机视觉与模式识别 · 计算机科学 2026-05-08 Jiaqi Wang , Weijia Wu , Yi Zhan , Rui Zhao , Ming Hu , James Cheng , Wei Liu , Philip Torr , Kevin Qinghong Lin

Evaluating instruction-guided image edits requires rewards that reflect subtle human preferences, yet current reward models typically depend on large-scale preference annotation and additional model training. This creates a data-efficiency…