Related papers: HiFi-Mesh: High-Fidelity Efficient 3D Mesh Generat…
3D content generation has wide applications in various fields. One of its dominant paradigms is by sparse-view reconstruction using multi-view images generated by diffusion models. However, since directly reconstructing triangle meshes from…
Despite the latest remarkable advances in generative modeling, efficient generation of high-quality 3D assets from textual prompts remains a difficult task. A key challenge lies in data scarcity: the most extensive 3D datasets encompass…
Unconstrained lip-to-speech synthesis aims to generate corresponding speeches from silent videos of talking faces with no restriction on head poses or vocabulary. Current works mainly use sequence-to-sequence models to solve this problem,…
Inspired by the remarkable success of autoregressive models in language modeling, this paradigm has been widely adopted in visual generation. However, the sequential token-by-token decoding mechanism inherent in traditional autoregressive…
There remains an important need for the development of image reconstruction methods that can produce diagnostically useful images from undersampled measurements. In magnetic resonance imaging (MRI), for example, such methods can facilitate…
By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond. Additionally, their formulation allows for a…
Autoregressive large language models (LLMs) have unified a vast range of language tasks, inspiring preliminary efforts in autoregressive (AR) video generation. Existing AR video generators either diverge from standard LLM architectures,…
Flow models are effective at progressively generating realistic images, but they generally struggle to capture long-range dependencies during the generation process as they compress all the information from previous time steps into a single…
Visual Auto-Regressive modeling (VAR) has shown promise in bridging the speed and quality gap between autoregressive image models and diffusion models. VAR reformulates autoregressive modeling by decomposing an image into successive…
The dominant paradigm for high-fidelity 3D generation relies on a VAE-Diffusion pipeline, where the VAE's reconstruction capability sets a firm upper bound on generation quality. A fundamental challenge limiting existing VAEs is the…
Building an online 3D LiDAR mapping system that produces a detailed surface reconstruction while remaining computationally efficient is a challenging task. In this paper, we present PlanarMesh, a novel incremental, mesh-based LiDAR…
Most existing random walk based network embedding methods often follow only one of two principles, homophily or structural equivalence. In real world networks, however, nodes exhibit a mixture of homophily and structural equivalence, which…
Recovering 3D face models from 2D in-the-wild images has gained considerable attention in the computer vision community due to its wide range of potential applications. However, the lack of ground-truth labeled datasets and the complexity…
High-quality textures are critical for realistic 3D content creation, yet existing generative methods are slow, rely on UV maps, and often fail to remain faithful to a reference image. To address these challenges, we propose a…
Masked Autoregressive (MAR) models promise better efficiency in visual generation than autoregressive (AR) models for the ability of parallel generation, yet their acceleration potential remains constrained by the modeling complexity of…
Table-to-text generation refers to generating a descriptive text from a key-value table. Traditional autoregressive methods, though can generate text with high fluency, suffer from low coverage and poor faithfulness problems. To mitigate…
Visual Autoregressive (VAR) has emerged as a promising approach in image generation, offering competitive potential and performance comparable to diffusion-based models. However, current AR-based visual generation models require substantial…
Learning latent representations of registered meshes is useful for many 3D tasks. Techniques have recently shifted to neural mesh autoencoders. Although they demonstrate higher precision than traditional methods, they remain unable to…
The rapid advancement of Artificial Intelligence Generated Content (AIGC) techniques has unlocked opportunities in generating diverse and compelling advertising images based on referenced product images and textual scene descriptions. This…
This paper challenges the dominance of continuous pipelines in visual generation. We systematically investigate the performance gap between discrete and continuous methods. Contrary to the belief that discrete tokenizers are intrinsically…