Related papers: FlexVAR: Flexible Visual Autoregressive Modeling w…

While visual autoregressive modeling (VAR) strategies have shed light on image generation with the autoregressive models, their potential for segmentation, a task that requires precise low-level spatial perception, remains unexplored.…

This work presents SimpleAR, a vanilla autoregressive visual generation framework without complex architecure modifications. Through careful exploration of training and inference optimization, we demonstrate that: 1) with only 0.5B…

Visual Autoregressive (VAR) models have emerged as a powerful paradigm for image synthesis by performing hierarchical next-scale prediction. However, VAR models are inherently prone to cascading error propagation, where subtle coarse-scale…

Autoregressive (AR) modeling has achieved remarkable success in natural language processing by enabling models to generate text with coherence and contextual understanding through next token prediction. Recently, in image generation, VAR…

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…

Recent advances in autoregressive (AR) generative models have produced increasingly powerful systems for media synthesis. Among them, next-scale prediction has emerged as a popular paradigm, where models generate images in a coarse-to-fine…

Image Super-Resolution (ISR) has seen significant progress with the introduction of remarkable generative models. However, challenges such as the trade-off issues between fidelity and realism, as well as computational complexity, have also…

Generating high-quality 3D content from text, single images, or sparse view images remains a challenging task with broad applications. Existing methods typically employ multi-view diffusion models to synthesize multi-view images, followed…

We present FlexAvatar, a flexible large reconstruction model for high-fidelity 3D head avatars with detailed dynamic deformation from single or sparse images, without requiring camera poses or expression labels. It leverages a…

We introduce FlexAvatar, a method for creating high-quality and complete 3D head avatars from a single image. A core challenge lies in the limited availability of multi-view data and the tendency of monocular training to yield incomplete 3D…

Masked autoregressive models (MAR) have emerged as a powerful paradigm for image and video generation, combining the flexibility of masked modeling with the expressiveness of continuous tokenizers. However, when sampling individual frames,…

The current conditional autoregressive image generation methods have shown promising results, yet their potential remains largely unexplored in the practical unsupervised image translation domain, which operates without explicit…

Visual AutoRegressive (VAR) models based on next-scale prediction enable efficient hierarchical generation, yet the inference cost grows quadratically at high resolutions. We observe that the computationally intensive later scales…

Recent studies on Visual Autoregressive (VAR) models have highlighted that high-frequency components, or later steps, in the generation process contribute disproportionately to inference latency. However, the underlying computational…

Visual autoregressive modeling, based on the next-scale prediction paradigm, exhibits notable advantages in image quality and model scalability over traditional autoregressive and diffusion models. It generates images by progressively…

This paper presents Randomized AutoRegressive modeling (RAR) for visual generation, which sets a new state-of-the-art performance on the image generation task while maintaining full compatibility with language modeling frameworks. The…

Text-guided image editing is an essential task that enables users to modify images through natural language descriptions. Recent advances in diffusion models and rectified flows have significantly improved editing quality, primarily relying…

Monocular depth estimation has seen significant advances through discriminative approaches, yet their performance remains constrained by the limitations of training datasets. While generative approaches have addressed this challenge by…

Recent advances in text-to-image generative models have enabled numerous practical applications, including subject-driven generation, which fine-tunes pretrained models to capture subject semantics from only a few examples. While…

Recent advances in diffusion models have brought remarkable visual fidelity to instruction-guided image editing. However, their global denoising process inherently entangles the edited region with the entire image context, leading to…