Related papers: JADE: Joint-aware Latent Diffusion for 3D Human Ge…

For humans, visual understanding is inherently generative: given a 3D shape, we can postulate how it would look in the world; given a 2D image, we can infer the 3D structure that likely gave rise to it. We can thus translate between the 2D…

Self-supervised learning has proved effective for skeleton-based human action understanding. However, previous works either rely on contrastive learning that suffers false negative problems or are based on reconstruction that learns too…

Human bodies exhibit various shapes for different identities or poses, but the body shape has certain similarities in structure and thus can be embedded in a low-dimensional space. This paper presents an autoencoder-like network…

We propose L3DG, the first approach for generative 3D modeling of 3D Gaussians through a latent 3D Gaussian diffusion formulation. This enables effective generative 3D modeling, scaling to generation of entire room-scale scenes which can be…

Reconstructing 3D human shape and pose from monocular images is challenging despite the promising results achieved by the most recent learning-based methods. The commonly occurred misalignment comes from the facts that the mapping from…

To represent people in mixed reality applications for collaboration and communication, we need to generate realistic and faithful avatar poses. However, the signal streams that can be applied for this task from head-mounted devices (HMDs)…

Augmentation by generative modelling yields a promising alternative to the accumulation of surgical data, where ethical, organisational and regulatory aspects must be considered. Yet, the joint synthesis of (image, mask) pairs for…

Recent advances in 3D generation have transitioned from multi-view 2D rendering approaches to 3D-native latent diffusion frameworks that exploit geometric priors in ground truth data. Despite progress, three key limitations persist: (1)…

Diffusion Transformers (DiTs) are a powerful yet underexplored class of generative models compared to U-Net-based diffusion architectures. We propose TIDE-Temporal-aware sparse autoencoders for Interpretable Diffusion transformErs-a…

Diffusion models have demonstrated impressive capabilities in modeling complex data distributions and are increasingly applied in various generative tasks. In this work, we propose Pose Analysis by Diffusion Synthesis PADS, a unified…

Self-supervised representation learning has gained increasing attention for strong generalization ability without relying on paired datasets. However, it has not been explored sufficiently for facial representation. Self-supervised facial…

While generative models have seen significant adoption across a wide range of data modalities, including 3D data, a consensus on which model is best suited for which task has yet to be reached. Further, conditional information such as text…

Generative Adversarial Networks (GANs) have emerged as a significant player in generative modeling by mapping lower-dimensional random noise to higher-dimensional spaces. These networks have been used to generate high-resolution images and…

Event skeleton generation, aiming to induce an event schema skeleton graph with abstracted event nodes and their temporal relations from a set of event instance graphs, is a critical step in the temporal complex event schema induction task.…

We introduce a novel 3D generation method for versatile and high-quality 3D asset creation. The cornerstone is a unified Structured LATent (SLAT) representation which allows decoding to different output formats, such as Radiance Fields, 3D…

Predicting and generating human hand grasp over objects is critical for animation and robotic tasks. In this work, we focus on generating both the hand and objects in a grasp by a single diffusion model. Our proposed Joint Hand-Object…

Learning powerful deep generative models for 3D shape synthesis is largely hindered by the difficulty in ensuring plausibility encompassing correct topology and reasonable geometry. Indeed, learning the distribution of plausible 3D shapes…

This paper focuses on the task of 4D shape reconstruction from a sequence of point clouds. Despite the recent success achieved by extending deep implicit representations into 4D space, it is still a great challenge in two respects, i.e. how…

Recent generative models can create visually plausible 3D representations of objects. However, the generation process often allows for implicit control signals, such as contextual descriptions, and rarely supports bold geometric distortions…

We present SAGNet, a structure-aware generative model for 3D shapes. Given a set of segmented objects of a certain class, the geometry of their parts and the pairwise relationships between them (the structure) are jointly learned and…