Related papers: HiFi-Mesh: High-Fidelity Efficient 3D Mesh Generat…
Autoregressive image modeling relies on visual tokenizers to compress images into compact latent representations. We design an end-to-end training pipeline that jointly optimizes reconstruction and generation, enabling direct supervision…
We introduce PixARMesh, a method to autoregressively reconstruct complete 3D indoor scene meshes directly from a single RGB image. Unlike prior methods that rely on implicit signed distance fields and post-hoc layout optimization, PixARMesh…
Recent advances in auto-regressive transformers have revolutionized generative modeling across different domains, from language processing to visual generation, demonstrating remarkable capabilities. However, applying these advances to 3D…
We present LATTICE, a new framework for high-fidelity 3D asset generation that bridges the quality and scalability gap between 3D and 2D generative models. While 2D image synthesis benefits from fixed spatial grids and well-established…
3D generation has witnessed significant advancements, yet efficiently producing high-quality 3D assets from a single image remains challenging. In this paper, we present a triplane autoencoder, which encodes 3D models into a compact…
4D mesh generation has recently emerged as a powerful paradigm for recovering dynamic 3D structure from videos, but existing methods remain slow, computationally expensive, and difficult to scale to longer sequences. We introduce a…
Generative world models for autonomous driving (AD) have become a trending topic. Unlike the widely studied image modality, in this work we explore generative world models for LiDAR data. Existing generation methods for LiDAR data only…
Mesh generation is a crucial step in numerical simulations, significantly impacting simulation accuracy and efficiency. However, generating meshes remains time-consuming and requires expensive computational resources. In this paper, we…
The field of neural rendering has witnessed significant progress with advancements in generative models and differentiable rendering techniques. Though 2D diffusion has achieved success, a unified 3D diffusion pipeline remains unsettled.…
We present a novel unconditional video generative model designed to address long-term spatial and temporal dependencies, with attention to computational and dataset efficiency. To capture long spatio-temporal dependencies, our approach…
This paper introduces a novel hierarchical autoencoder that maps 3D models into a highly compressed latent space. The hierarchical autoencoder is specifically designed to tackle the challenges arising from large-scale datasets and…
3D structure modeling is essential across scales, enabling applications from fluid simulation and 3D reconstruction to protein folding and molecular docking. Yet, despite shared 3D spatial patterns, current approaches remain fragmented,…
Latent diffusion models for image generation have crossed a quality threshold which enabled them to achieve mass adoption. Recently, a series of works have made advancements towards replicating this success in the 3D domain, introducing…
Autoregressive models have emerged as a powerful approach for visual generation but suffer from slow inference speed due to their sequential token-by-token prediction process. In this paper, we propose a simple yet effective approach for…
Autoregressive (AR) models, the theoretical performance benchmark for learned lossless image compression, are often dismissed as impractical due to prohibitive computational cost. This work re-thinks this paradigm, introducing a framework…
Masked autoregressive (MAR) models unify the strengths of masked and autoregressive generation by predicting tokens in a fixed order using bidirectional attention for image generation. While effective, MAR models suffer from significant…
The harnessing of machine learning, especially deep generative models, has opened up promising avenues in the field of synthetic DNA sequence generation. Whilst Generative Adversarial Networks (GANs) have gained traction for this…
Video prediction is an important yet challenging problem; burdened with the tasks of generating future frames and learning environment dynamics. Recently, autoregressive latent video models have proved to be a powerful video prediction…
Autoregressive models have demonstrated remarkable success in sequential data generation, particularly in NLP, but their extension to continuous-domain image generation presents significant challenges. Recent work, the masked autoregressive…
Latent 3D reconstruction has shown great promise in empowering 3D semantic understanding and 3D generation by distilling 2D features into the 3D space. However, existing approaches struggle with the domain gap between 2D feature space and…