Results 311 to 320 of about 24,691,873 (342)

DiffIR: Efficient Diffusion Model for Image Restoration

IEEE International Conference on Computer Vision, 2023
Diffusion model (DM) has achieved SOTA performance by modeling the image synthesis process into a sequential application of a denoising network. However, different from image synthesis, image restoration (IR) has a strong constraint to generate results ...
Bin Xia, Yulun Zhang, Shiyin Wang, Yitong Wang, Xing Wu, Yapeng Tian, Wenming Yang, L. Gool   +7 more
semanticscholar   +1 more source

DiffusionDet: Diffusion Model for Object Detection

IEEE International Conference on Computer Vision, 2022
We propose DiffusionDet, a new framework that formulates object detection as a denoising diffusion process from noisy boxes to object boxes. During the training stage, object boxes diffuse from ground-truth boxes to random distribution, and the model ...
Shoufa Chen, Pei Sun, Yibing Song, P. Luo   +3 more
semanticscholar   +1 more source

SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction

International Conference on Learning Representations, 2023
Recently video generation has achieved substantial progress with realistic results. Nevertheless, existing AI-generated videos are usually very short clips ("shot-level") depicting a single scene.
Xinyuan Chen, Yaohui Wang, Lingjun Zhang, Shaobin Zhuang, Xin Ma, Jiashuo Yu, Yali Wang, Dahua Lin, Yu Qiao, Ziwei Liu   +9 more
semanticscholar   +1 more source

GestureDiffuCLIP: Gesture Diffusion Model with CLIP Latents

ACM Transactions on Graphics, 2023
The automatic generation of stylized co-speech gestures has recently received increasing attention. Previous systems typically allow style control via predefined text labels or example motion clips, which are often not flexible enough to convey user ...
Tenglong Ao, Zeyi Zhang, Libin Liu
semanticscholar   +1 more source

Guiding a Diffusion Model with a Bad Version of Itself

Neural Information Processing Systems
The primary axes of interest in image-generating diffusion models are image quality, the amount of variation in the results, and how well the results align with a given condition, e.g., a class label or a text prompt. The popular classifier-free guidance
T. Karras, M. Aittala, T. Kynkäänniemi, J. Lehtinen, Timo Aila, S. Laine   +5 more
semanticscholar   +1 more source

DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Driving

Computer Vision and Pattern Recognition
Recently, the diffusion model has emerged as a powerful generative technique for robotic policy learning, capable of modeling multi-mode action distributions. Leveraging its capability for end-to-end autonomous driving is a promising direction.
Bencheng Liao, Shaoyu Chen, Haoran Yin, Bo Jiang, Cheng Wang, Sixu Yan, Xinbang Zhang, Xiangyu Li, Ying Zhang, Qian Zhang, Xinggang Wang   +10 more
semanticscholar   +1 more source