41 to 50 of 2,022 Results
Nov 25, 2024 - S-Lab for Advanced Intelligence
Ouyang, Wenqi; Dong, Yi; Yang, Lei; Si, Jianlou; Pan, Xingang, 2024, "I2VEdit: First-Frame-Guided Video Editing via Image-to-Video Diffusion Models", https://doi.org/10.21979/N9/2ZLRYG, DR-NTU (Data), V1
The remarkable generative capabilities of diffusion models have motivated extensive research in both image and video editing. Compared to video editing which faces additional challenges in the time dimension, image editing has witnessed the development of more diverse, high-quali... |
Nov 7, 2024 - S-Lab for Advanced Intelligence
Xiao, Zeqi; Zhou, Yifan; Yang, Shuai; Pan, Xingang, 2024, "Video Diffusion Models are Training-free Motion Interpreter and Controller", https://doi.org/10.21979/N9/HQM313, DR-NTU (Data), V1
Video generation primarily aims to model authentic and customized motion across frames, making understanding and controlling the motion a crucial topic. Most diffusion-based studies on video motion focus on motion customization with training-based paradigms, which, however, deman... |
Oct 23, 2024 - S-Lab for Advanced Intelligence
Jiang, Xueying; Jin, Sheng; Zhang, Xiaoqin; Shao, Ling; Lu, Shijian, 2024, "MonoMAE: Enhancing Monocular 3D Detection through Depth-Aware Masked Autoencoders", https://doi.org/10.21979/N9/5ILJOM, DR-NTU (Data), V1
Monocular 3D object detection aims for precise 3D localization and identification of objects from a single-view image. Despite its recent progress, it often struggles while handling pervasive object occlusions that tend to complicate and degrade the prediction of object dimension... |
Oct 8, 2024 - S-Lab for Advanced Intelligence
Huang, Ziqi; Wu, Tianxing; Jiang, Yuming; Chan, Kelvin C. K.; Liu, Ziwei, 2024, "Replication Data for: ReVersion: Diffusion-Based Relation Inversion from Images", https://doi.org/10.21979/N9/UWSAXU, DR-NTU (Data), V1
A replication of the ReVersion Benchmark, for the paper "ReVersion: Diffusion-Based Relation Inversion from Images". |
Oct 8, 2024 - S-Lab for Advanced Intelligence
Xie, Binzhu; Zhang, Sicheng; Zhou, Zitang; Li, Bo; Zhang, Yuanhan; Hessel, Jack; Yang, Jingkang; Liu, Ziwei, 2024, "FunQA: Towards Surprising Video Comprehension", https://doi.org/10.21979/N9/SMR703, DR-NTU (Data), V1
Surprising videos, e.g., funny clips, creative performances, or visual illusions, attract significant attention. Enjoyment of these videos is not simply a response to visual stimuli; rather, it hinges on the human capacity to understand (and appreciate) commonsense violations dep... |
Oct 8, 2024 - S-Lab for Advanced Intelligence
Yang, Jingkang; Dong, Yuhao; Liu, Shuai; Li, Bo; Wang, Ziyue; Jiang, Chencheng; Tan, Haoran; Kang, Jiamu; Zhang, Yuanhan; Zhou, Kaiyang; Liu, Ziwei, 2024, "Octopus: Embodied Vision-Language Programmer from Environmental Feedback", https://doi.org/10.21979/N9/9EIB8X, DR-NTU (Data), V1
Large vision-language models (VLMs) have achieved substantial progress in multimodal perception and reasoning. Furthermore, when seamlessly integrated into an embodied agent, it signifies a crucial stride towards the creation of autonomous and context-aware systems capable of for... |
ZIP Archive - 6.3 GB -
MD5: df5972717c2859d34b4fadd702476a70
|
Oct 7, 2024 - S-Lab for Advanced Intelligence
Ma, Yubo; Zang, Yuhang; Chan, Liangyu; Chen, Meiqi; Jiao, Yizhu; Li, Xinze; Lu Xinyuan; Liu, Ziyu; Ma, Yan; Dong, Xiaoyi; Zhang, Pan; Pan, Liangming; Jiang, Yu-Gang; Wang, Jiaqi; Cao, Yixin; Sun, Aixin, 2024, "Replication Data for: MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations", https://doi.org/10.21979/N9/IMVWT4, DR-NTU (Data), V1
Understanding documents with rich layouts and multi-modal components is a long-standing and practical task. Recent Large Vision-Language Models (LVLMs) have made remarkable strides in various tasks, particularly in single-page document understanding (DU). However, their abilities... |
Oct 4, 2024 - S-Lab for Advanced Intelligence
Yue, Zongsheng; Wang, Jianyi; Loy, Chen Change, 2024, "Efficient Diffusion Model for Image Restoration by Residual Shifting", https://doi.org/10.21979/N9/VYPJ0O, DR-NTU (Data), V1
While diffusion-based image restoration (IR) methods have achieved remarkable success, they are still limited by the low inference speed attributed to the necessity of executing hundreds or even thousands of sampling steps. Existing acceleration sampling techniques, though seekin... |
Oct 3, 2024 - S-Lab for Advanced Intelligence
Guo, Zujin; Li, Wei; Loy, Chen Change, 2024, "Generalizable Implicit Motion Modeling for Video Frame Interpolation", https://doi.org/10.21979/N9/EDKWDC, DR-NTU (Data), V1
Motion modeling is critical in flow-based Video Frame Interpolation (VFI). Existing paradigms either consider linear combinations of bidirectional flows or directly predict bilateral flows for given timestamps without exploring favorable motion priors, thus lacking the capability... |
