Related papers: MAR-3D: Progressive Masked Auto-regressor for High…

Despite recent advancements in 3D generation methods, achieving controllability still remains a challenging issue. Current approaches utilizing score-distillation sampling are hindered by laborious procedures that consume a significant…

RGB cloth generation has been deeply studied in the related literature, however, 3D garment generation remains an open problem. In this paper, we build a conditional variational autoencoder for 3D garment generation and draping. We propose…

High-resolution (HR) MRI scans obtained from research-grade medical centers provide precise information about imaged tissues. However, routine clinical MRI scans are typically in low-resolution (LR) and vary greatly in contrast and spatial…

As a class of fruitful approaches, diffusion probabilistic models (DPMs) have shown excellent advantages in high-resolution image reconstruction. On the other hand, masked autoencoders (MAEs), as popular self-supervised vision learners,…

Transformer-based end-to-end speech recognition has achieved great success. However, the large footprint and computational overhead make it difficult to deploy these models in some real-world applications. Model compression techniques can…

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…

LiDAR-based 3D object detectors typically rely on proposal heads with hand-crafted components like anchor assignment and non-maximum suppression (NMS), complicating training and limiting extensibility. We present AutoReg3D, an…

We propose a combined generative and contrastive neural architecture for learning latent representations of 3D volumetric shapes. The architecture uses two encoder branches for voxel grids and multi-view images from the same underlying…

Reinforcement learning (RL), earlier proven to be effective in large language and multi-modal models, has been successfully extended to enhance 2D image generation recently. However, applying RL to 3D generation remains largely unexplored…

Controllable generation, which enables fine-grained control over generated outputs, has emerged as a critical focus in visual generative models. Currently, there are two primary technical approaches in visual generation: diffusion models…

Discrete diffusion models have emerged as a powerful class of models and a promising route to fast language generation, but practical implementations typically rely on factored reverse transitions ignoring cross-token dependencies and…

The Large-scale 3D reconstruction, texturing and semantic mapping are nowadays widely used for automated driving vehicles, virtual reality and automatic data generation. However, most approaches are developed for RGB-D cameras with colored…

Diffusion Transformers have recently shown remarkable effectiveness in generating high-quality 3D point clouds. However, training voxel-based diffusion models for high-resolution 3D voxels remains prohibitively expensive due to the cubic…

Learned 3D representations of human faces are useful for computer vision problems such as 3D face tracking and reconstruction from images, as well as graphics applications such as character generation and animation. Traditional models learn…

Continual learning enables models to acquire new knowledge over time while retaining previously learned capabilities. However, its application to text-to-3D generation remains unexplored. We present ReConText3D, the first framework for…

This paper introduces a generative model for 3D surfaces based on a representation of shapes with mean curvature and metric, which are invariant under rigid transformation. Hence, compared with existing 3D machine learning frameworks, our…

Modern computationally-intensive applications often operate under time constraints, necessitating acceleration methods and distribution of computational workloads across multiple entities. However, the outcome is either achieved within the…

While autoregressive (AR) models have demonstrated remarkable success in image generation, extending them to layout-conditioned generation remains challenging due to the sparse nature of layout conditions and the risk of feature…

Advancements in language foundation models have primarily fueled the recent surge in artificial intelligence. In contrast, generative learning of non-textual modalities, especially videos, significantly trails behind language modeling. This…

The limited availability of 3D medical image datasets, due to privacy concerns and high collection or annotation costs, poses significant challenges in the field of medical imaging. While a promising alternative is the use of synthesized…