Related papers: Structure-Aware Flow Generation for Human Body Res…
Conventional physically based rendering (PBR) pipelines generate photorealistic images through computationally intensive light transport simulations. Although recent deep learning approaches leverage diffusion model priors with geometry…
Learning 3D+t shape completion and generation from multi-view cardiac magnetic resonance (CMR) images requires a large amount of high-resolution 3D whole-heart segmentations (WHS) to capture shape priors. In this work, we leverage flow…
Vector-quantized image modeling has shown great potential in synthesizing high-quality images. However, generating high-resolution images remains a challenging task due to the quadratic computational overhead of the self-attention process.…
Diffusion models (DMs) have demonstrated remarkable success in real-world image super-resolution (SR), yet their reliance on time-consuming multi-step sampling largely hinders their practical applications. While recent efforts have…
Diffusion and flow-based models have become the state of the art for generative AI across a wide range of data modalities, including images, videos, shapes, molecules, music, and more. This tutorial provides a self-contained introduction to…
Although recent 3D-native generators have made great progress in synthesizing reliable geometry, they still fall short in achieving realistic appearances. A key obstacle lies in the lack of diverse and high-quality real-world 3D assets with…
Current subject-driven image generation methods encounter significant challenges in person-centric image generation. The reason is that they learn the semantic scene and person generation by fine-tuning a common pre-trained diffusion, which…
This article introduces the structure flow field; a flow field that can provide high-speed robo-centric motion information for motion control of highly dynamic robotic devices and autonomous vehicles. Structure flow is the angular 3D…
Diffusion-based video generation techniques have significantly improved zero-shot talking-head avatar generation, enhancing the naturalness of both head motion and facial expressions. However, existing methods suffer from poor…
We present FlowFixer, a refinement framework for subject-driven generation (SDG) that restores fine details lost during generation caused by changes in scale and perspective of a subject. FlowFixer proposes direct image-to-image translation…
New technologies such as Rectified Flow and Flow Matching have significantly improved the performance of generative models in the past two years, especially in terms of control accuracy, generation quality, and generation efficiency.…
Estimating three-dimensional conformations of a molecular graph allows insight into the molecule's biological and chemical functions. Fast generation of valid conformations is thus central to molecular modeling. Recent advances in…
Multiview diffusion models have rapidly emerged as a powerful tool for content creation with spatial consistency across viewpoints, offering rich visual realism without requiring explicit geometry and appearance representation. However,…
3D content creation is referred to as one of the most fundamental tasks of computer graphics. And many 3D modeling algorithms from 2D images or curves have been developed over the past several decades. Designers are allowed to align some…
Large-scale video generative models are trained on vast and diverse visual data, enabling them to internalize rich structural, semantic, and dynamic priors of the visual world. While these models have demonstrated impressive generative…
Inspired by generative paradigms in image and video, 3D shape generation has made notable progress, enabling the rapid synthesis of high-fidelity 3D assets from a single image. However, current methods still face challenges, including the…
Generative models have proven effective at modeling 3D shapes and their statistical variations. In this paper we investigate their application to point clouds, a 3D shape representation widely used in computer vision for which, however,…
This thesis presents novel contributions in two primary areas: advancing the efficiency of generative models, particularly normalizing flows, and applying generative models to solve real-world computer vision challenges. The first part…
We propose an end-to-end trainable, cross-category method for reconstructing multiple man-made articulated objects from a single RGBD image, focusing on part-level shape reconstruction and pose and kinematics estimation. We depart from…
Reconstruction of 3D neural fields from posed images has emerged as a promising method for self-supervised representation learning. The key challenge preventing the deployment of these 3D scene learners on large-scale video data is their…