Related papers: A Pytorch Reproduction of Masked Generative Image …
By leveraging the generative priors from pre-trained text-to-image diffusion models, significant progress has been made in real-world image super-resolution (Real-ISR). However, these methods tend to generate inaccurate and unnatural…
The Open-MAGVIT2 project produces an open-source replication of Google's MAGVIT-v2 tokenizer, a tokenizer with a super-large codebook (i.e., $2^{18}$ codes), and achieves the state-of-the-art reconstruction performance on ImageNet and UCF…
Masked diffusion enables region-specific image synthesis but suffers from computational redundancy, since the entire image is processed each timestep even though only the masked region requires generation. To address this, we introduce…
Artificial Intelligence Generated Content(AIGC), known for its superior visual results, represents a promising mitigation method for high-cost advertising applications. Numerous approaches have been developed to manipulate generated content…
Image tokenization, the process of transforming raw image pixels into a compact low-dimensional latent representation, has proven crucial for scalable and efficient image generation. However, mainstream image tokenization methods generally…
Recent advances in generative image compression (GIC) have delivered remarkable improvements in perceptual quality. However, many GICs rely on large-scale and rigid models, which severely constrain their utility for flexible transmission…
This work introduces CTorch, a PyTorch-compatible, GPU-accelerated, and auto-differentiable projector toolbox designed to handle various CT geometries with configurable projector algorithms. CTorch provides flexible scanner geometry…
Single-pixel imaging is a novel imaging scheme that has gained popularity due to its huge computational gain and potential for a low-cost alternative to imaging beyond the visible spectrum. The traditional reconstruction methods struggle to…
This paper undertakes the task of replicating the MaskFormer model a universal image segmentation model originally developed using the PyTorch framework, within the TensorFlow ecosystem, specifically optimized for execution on Tensor…
The use of coarse-grained layouts for controllable synthesis of complex scene images via deep generative models has recently gained popularity. However, results of current approaches still fall short of their promise of high-resolution…
Based on the standard VMAF implementation we propose an implementation of VMAF using PyTorch framework. For this implementation comparisons with the standard (libvmaf) show the discrepancy $\lesssim 10^{-2}$ in VMAF units. We investigate…
Learning a good image prior is a long-term goal for image restoration and manipulation. While existing methods like deep image prior (DIP) capture low-level image statistics, there are still gaps toward an image prior that captures rich…
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…
Electron ptychography has recently achieved unprecedented resolution, offering valuable insights across diverse material systems, including in three dimensions. However, high-quality ptychographic reconstruction is computationally expensive…
Representation and generative learning, as reconstruction-based methods, have demonstrated their potential for mutual reinforcement across various domains. In the field of point cloud processing, although existing studies have adopted…
It has been recently shown that neural networks can recover the geometric structure of a face from a single given image. A common denominator of most existing face geometry reconstruction methods is the restriction of the solution space to…
The degree of difficulty in image inpainting depends on the types and sizes of the missing parts. Existing image inpainting approaches usually encounter difficulties in completing the missing parts in the wild with pleasing visual and…
Recent advances in OpenAI's GPT-series multimodal generation models have shown remarkable capabilities in producing visually compelling images. In this work, we investigate its potential impact on the image restoration community. We…
We propose PyTorchGeoNodes, a differentiable module for reconstructing 3D objects and their parameters from images using interpretable shape programs. Unlike traditional CAD model retrieval, shape programs allow reasoning about semantic…
Deep generative models, like GANs, have considerably improved the state of the art in image synthesis, and are able to generate near photo-realistic images in structured domains such as human faces. Based on this success, recent work on…