Results 11 to 20 of about 24,691,873 (342)
ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model [PDF]
IEEE International Conference on Computer Vision, 2023 3D human motion generation is crucial for creative industry. Recent advances rely on generative models with domain knowledge for text-driven motion generation, leading to substantial progress in capturing common motions.
Mingyuan Zhang +7 more
semanticscholar +1 more source
GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation [PDF]
International Conference on Learning Representations, 2022 Predicting molecular conformations from molecular graphs is a fundamental problem in cheminformatics and drug discovery. Recently, significant progress has been achieved with machine learning approaches, especially with deep generative models.
Minkai Xu +5 more
semanticscholar +1 more source
Vector Quantized Diffusion Model for Text-to-Image Synthesis [PDF]
Computer Vision and Pattern Recognition, 2021 We present the vector quantized diffusion (VQ-Diffusion) model for text-to-image generation. This method is based on a vector quantized variational autoencoder (VQ-VAE) whose latent space is modeled by a conditional variant of the recently developed ...
Shuyang Gu +7 more
semanticscholar +1 more source
Radar-SR3: A Weather Radar Image Super-Resolution Generation Model Based on SR3
Atmosphere, 2023 To solve the problems of the current deep learning radar extrapolation model consuming many resources and the final prediction result lacking details, a weather radar image super-resolution weather model based on SR3 (super-resolution via image ...
Zhanpeng Shi +4 more
doaj +1 more source
UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild [PDF]
Neural Information Processing Systems, 2023 Achieving machine autonomy and human control often represent divergent objectives in the design of interactive AI systems. Visual generative foundation models such as Stable Diffusion show promise in navigating these goals, especially when prompted with ...
Can Qin +12 more
semanticscholar +1 more source
Stable VITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-On [PDF]
Computer Vision and Pattern Recognition, 2023 Given a clothing image and a person image, an image-based virtual try-on aims to generate a customized image that appears natural and accurately reflects the character-istics of the clothing image.
Jeongho Kim +4 more
semanticscholar +1 more source
Leapfrog Diffusion Model for Stochastic Trajectory Prediction [PDF]
Computer Vision and Pattern Recognition, 2023 To model the indeterminacy of human behaviors, stochastic trajectory prediction requires a sophisticated multi-modal distribution of future trajectories.
Wei Mao +4 more
semanticscholar +1 more source
LayoutDiffusion: Controllable Diffusion Model for Layout-to-Image Generation [PDF]
Computer Vision and Pattern Recognition, 2023 Recently, diffusion models have achieved great success in image synthesis. However, when it comes to the layout-to-image generation where an image often has a complex scene of multiple objects, how to make strong control over both the global layout map ...
Guangcong Zheng +5 more
semanticscholar +1 more source
DDP: Diffusion Model for Dense Visual Prediction [PDF]
IEEE International Conference on Computer Vision, 2023 We propose a simple, efficient, yet powerful framework for dense visual predictions based on the conditional diffusion pipeline. Our approach follows a "noise-to-map" generative paradigm for prediction by progressively removing noise from a random ...
Yuanfeng Ji +8 more
semanticscholar +1 more source
Diff-Retinex: Rethinking Low-light Image Enhancement with A Generative Diffusion Model [PDF]
IEEE International Conference on Computer Vision, 2023 In this paper, we rethink the low-light image enhancement task and propose a physically explainable and generative diffusion model for low-light image enhancement, termed as Diff-Retinex.
Xunpeng Yi +4 more
semanticscholar +1 more source