Related papers: CART: Compositional Auto-Regressive Transformer fo…
Existing vector quantization (VQ) based autoregressive models follow a two-stage generation paradigm that first learns a codebook to encode images as discrete codes, and then completes generation based on the learned codebook. However, they…
In this paper, we explore a new generative approach for learning visual representations. Our method, DARL, employs a decoder-only Transformer to predict image patches autoregressively. We find that training with Mean Squared Error (MSE)…
In the rapidly advancing field of image generation, Visual Auto-Regressive (VAR) modeling has garnered considerable attention for its innovative next-scale prediction approach. This paradigm offers substantial improvements in efficiency,…
Image compositions are helpful in the study of image structures and assist in discovering the semantics of the underlying scene portrayed across art forms and styles. With the digitization of artworks in recent years, thousands of images of…
Auto-regressive (AR) models, initially successful in language generation, have recently shown promise in visual generation tasks due to their superior sampling efficiency. Unlike image generation, video generation requires a substantially…
Autoregressive (AR) approaches, which represent images as sequences of discrete tokens from a finite codebook, have achieved remarkable success in image generation. However, the quantization process and the limited codebook size inevitably…
Visual autoregressive (VAR) models have recently emerged as a promising alternative for image generation, offering stable training, non-iterative inference, and high-fidelity synthesis through next-scale prediction. This encourages the…
Cross-view image translation is challenging because it involves images with drastically different views and severe deformation. In this paper, we propose a novel approach named Multi-Channel Attention SelectionGAN (SelectionGAN) that makes…
Autoregressive (AR) visual generation has emerged as a powerful paradigm for image and multimodal synthesis, owing to its scalability and generality. However, existing AR image generation suffers from severe memory bottlenecks due to the…
Displaying high-quality images on edge devices, such as augmented reality devices, is essential for enhancing the user experience. However, these devices often face power consumption and computing resource limitations, making it challenging…
Images can be viewed as layered compositions, foreground objects over background, with potential occlusions. This layered representation enables independent editing of elements, offering greater flexibility for content creation. Despite the…
This paper introduces an innovative approach for image matting that redefines the traditional regression-based task as a generative modeling challenge. Our method harnesses the capabilities of latent diffusion models, enriched with…
Recent neural network models for image captioning usually employ an encoder-decoder architecture, where the decoder adopts a recursive sequence decoding way. However, such autoregressive decoding may result in sequential error accumulation…
In this paper, we propose ZipAR, a training-free, plug-and-play parallel decoding framework for accelerating auto-regressive (AR) visual generation. The motivation stems from the observation that images exhibit local structures, and…
Recent advances in subject-driven image generation using diffusion models have attracted considerable attention for their remarkable capabilities in producing high-quality images. Nevertheless, the potential of Visual Autoregressive (VAR)…
Decoder-only autoregressive image generation typically relies on fixed-length tokenization schemes whose token counts grow quadratically with resolution, substantially increasing the computational and memory demands of attention. We present…
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…
Existing image-to-image transformation approaches primarily focus on synthesizing visually pleasing data. Generating images with correct identity labels is challenging yet much less explored. It is even more challenging to deal with image…
Composed Image Retrieval (CIR) is a challenging multimodal task that retrieves a target image based on a reference image and accompanying modification text. Due to the high cost of annotating CIR triplet datasets, zero-shot (ZS) CIR has…
Recent segmentation methods, such as OCR and CPNet, utilizing "class level" information in addition to pixel features, have achieved notable success for boosting the accuracy of existing network modules. However, the extracted class-level…