相关论文: A Diffusion-based Data Generator for Training Obje…
Due to the significant advances in large-scale text-to-image generation by diffusion model (DM), controllable human image generation has been attracting much attention recently. Existing works, such as Controlnet [36], T2I-adapter [20] and…
The versatility and adaptability of human grasping catalyze advancing dexterous robotic manipulation. While significant strides have been made in dexterous grasp generation, current research endeavors pivot towards optimizing object…
The traditional techniques for extracting polycrystalline grain structures from microscopy images, such as transmission electron microscopy (TEM) and scanning electron microscopy (SEM), are labour-intensive, subjective, and time-consuming,…
Probabilistic Diffusion Models (PDMs) have recently emerged as a very promising class of generative models, achieving high performance in natural image generation. However, their performance relative to non-natural images, like radar-based…
Remote sensing images captured by different platforms exhibit significant disparities in spatial resolution. Large scale factor super-resolution (SR) algorithms are vital for maximizing the utilization of low-resolution (LR) satellite data…
We propose Context Diffusion, a diffusion-based framework that enables image generation models to learn from visual examples presented in context. Recent work tackles such in-context learning for image generation, where a query image is…
The availability of data is limited in some fields, especially for object detection tasks, where it is necessary to have correctly labeled bounding boxes around each object. A notable example of such data scarcity is found in the domain of…
Recent advances in one-step text-to-image generation have enabled real-time synthesis with remarkable efficiency and quality. Previous reinforcement learning methods for one-step generators combine image-space reward optimization with…
Articulated object generation has seen increasing advancements, yet existing models often lack the ability to be conditioned on text prompts. To address the significant gap between textual descriptions and 3D articulated object…
Recently simulation methods have been developed for optical tactile sensors to enable the Sim2Real learning, i.e., firstly training models in simulation before deploying them on the real robot. However, some artefacts in the real objects…
Natural and expressive human motion generation is the holy grail of computer animation. It is a challenging task, due to the diversity of possible motion, human perceptual sensitivity to it, and the difficulty of accurately describing it.…
Diffusion models, a family of generative models based on deep learning, have become increasingly prominent in cutting-edge machine learning research. With a distinguished performance in generating samples that resemble the observed data,…
Remote sensing imagery is essential for environmental monitoring, agricultural management, and disaster response. However, data loss due to cloud cover, sensor failures, or incomplete acquisition-especially in high-resolution and…
The Bird-Eye-View (BEV) is one of the most widely-used scene representations for visual perception in Autonomous Vehicles (AVs) due to its well suited compatibility to downstream tasks. For the enhanced safety of AVs, modeling perception…
Denoising diffusion models have shown great promise in human motion synthesis conditioned on natural language descriptions. However, integrating spatial constraints, such as pre-defined motion trajectories and obstacles, remains a challenge…
Diffusion models have recently achieved remarkable performance in image super-resolution (SR), but their high computational cost limits practical deployment in remote sensing applications. To address this issue, we propose SlimDiffSR, a…
Acquiring high-quality data for training discriminative models is a crucial yet challenging aspect of building effective predictive systems. In this paper, we present Diffusion Inversion, a simple yet effective method that leverages the…
Medical image understanding requires meticulous examination of fine visual details, with particular regions requiring additional attention. While radiologists build such expertise over years of experience, it is challenging for AI models to…
Strong generative models can accurately learn channel distributions. This could save recurring costs for physical measurements of the channel. Moreover, the resulting differentiable channel model supports training neural encoders by…
Diffusion models have shown remarkable results for image generation, editing and inpainting. Recent works explore diffusion models for 3D shape generation with neural implicit functions, i.e., signed distance function and occupancy…