Related papers: Diffusion Models are Efficient Data Generators for…
The field of generative models has recently witnessed significant progress, with diffusion models showing remarkable performance in image generation. In light of this success, there is a growing interest in exploring the application of…
Generating realistic human videos remains a challenging task, with the most effective methods currently relying on a human motion sequence as a control signal. Existing approaches often use existing motion extracted from other videos, which…
Recent advances in text-to-image generation with diffusion models present transformative capabilities in image quality. However, user controllability of the generated image, and fast adaptation to new tasks still remains an open challenge,…
Diffusion Handles is a novel approach to enabling 3D object edits on diffusion images. We accomplish these edits using existing pre-trained diffusion models, and 2D image depth estimation, without any fine-tuning or 3D object retrieval. The…
We present a unified and generalizable framework for synthesizing view-consistent and temporally coherent avatars from a single image, addressing the challenging task of single-image avatar generation. Existing diffusion-based methods often…
Recently, multiple formulations of vision problems as probabilistic inversions of generative models based on computer graphics have been proposed. However, applications to 3D perception from natural images have focused on low-dimensional…
3D meshes are a fundamental representation widely used in computer science and engineering. In robotics, they are particularly valuable because they capture objects in a form that aligns directly with how robots interact with the physical…
This paper presents DiffSurf, a transformer-based denoising diffusion model for generating and reconstructing 3D surfaces. Specifically, we design a diffusion transformer architecture that predicts noise from noisy 3D surface vertices and…
Generative diffusion models offer a natural choice for data augmentation when training complex vision models. However, ensuring reliability of their generative content as augmentation samples remains an open challenge. Despite a number of…
The recovery of occluded human meshes presents challenges for current methods due to the difficulty in extracting effective image features under severe occlusion. In this paper, we introduce DPMesh, an innovative framework for occluded…
The Skinned Multi-Person Linear (SMPL) model plays a crucial role in 3D human pose estimation, providing a streamlined yet effective representation of the human body. However, ensuring the validity of SMPL configurations during tasks such…
We introduce a framework for joint grounded scene graph - image generation, a challenging task involving high-dimensional, multi-modal structured data. To effectively model this complex joint distribution, we adopt a factorized approach:…
Accurate pain expression synthesis is essential for improving clinical training and human-robot interaction. Current Robotic Patient Simulators (RPSs) lack realistic pain facial expressions, limiting their effectiveness in medical training.…
Previous 3D human creation methods have made significant progress in synthesizing view-consistent and temporally aligned results from sparse-view images or monocular videos. However, it remains challenging to produce perpetually realistic,…
3D human shape reconstruction under severe occlusion due to human-object or human-human interaction is a challenging problem. Parametric models i.e., SMPL(-X), which are based on the statistics across human shapes, can represent whole human…
We study the problem of 3D-aware full-body human generation, aiming at creating animatable human avatars with high-quality textures and geometries. Generally, two challenges remain in this field: i) existing methods struggle to generate…
Modeling animatable human avatars from videos is a long-standing and challenging problem. While conventional methods require per-instance optimization, recent feed-forward methods have been proposed to generate 3D Gaussians with a learnable…
Automated cell segmentation in microscopy images is essential for biomedical research, yet conventional methods are labor-intensive and prone to error. While deep learning-based approaches have proven effective, they often require large…
We present En3D, an enhanced generative scheme for sculpting high-quality 3D human avatars. Unlike previous works that rely on scarce 3D datasets or limited 2D collections with imbalanced viewing angles and imprecise pose priors, our…
Training deep learning methods on small time series datasets that also include corrupted samples is challenging. Diffusion models have shown to be effective to generate realistic and synthetic data, and correct corrupted samples through…