PyTorchKR Papers

최신 논문

총 7,086편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2412.01199공식 코드 · Papers with Code

TinyFusion: Diffusion Transformers Learned Shallow

Diffusion Transformers have demonstrated remarkable capabilities in image generation but often come with excessive parameterization, resulting in considerable inference overhead in real-world applications. In this work, we present TinyFusion, a depth pruning method designed to remove redundant layers from diffusion transformers via end-to-end learning. The core principle of our approach is to create a pruned model with high recoverability, allowing it to regain strong performance after fine-tuning. To accomplish this, we introduce a differentiable sampling technique to make pruning learnable, paired with a co-optimized parameter to simulate future fine-tuning. While prior works focus on minimizing loss or error after pruning, our method explicitly models and optimizes the post-fine-tuning performance of pruned models. Experimental results indicate that this learnable paradigm offers substantial benefits for layer pruning of diffusion transformers, surpassing existing importance-based and error-based methods. Additionally, TinyFusion exhibits strong generalization across diverse architectures, such as DiTs, MARs, and SiTs. Experiments with DiT-XL show that TinyFusion can craft a shallow diffusion transformer at less than 7% of the pre-training cost, achieving a 2$\times$ speedup with an FID score of 2.86, outperforming competitors with comparable efficiency. Code is available at https://github.com/VainF/TinyFusion.

arXiv:2412.00887공식 코드 · Papers with Code

Playable Game Generation

In recent years, Artificial Intelligence Generated Content (AIGC) has advanced from text-to-image generation to text-to-video and multimodal video synthesis. However, generating playable games presents significant challenges due to the stringent requirements for real-time interaction, high visual quality, and accurate simulation of game mechanics. Existing approaches often fall short, either lacking real-time capabilities or failing to accurately simulate interactive mechanics. To tackle the playability issue, we propose a novel method called \emph{PlayGen}, which encompasses game data generation, an autoregressive DiT-based diffusion model, and a comprehensive playability-based evaluation framework. Validated on well-known 2D and 3D games, PlayGen achieves real-time interaction, ensures sufficient visual quality, and provides accurate interactive mechanics simulation. Notably, these results are sustained even after over 1000 frames of gameplay on an NVIDIA RTX 2060 GPU. Our code is publicly available: https://github.com/GreatX3/Playable-Game-Generation. Our playable demo generated by AI is: http://124.156.151.207.

arXiv:2412.00754

CtrlNeRF: The Generative Neural Radiation Fields for the Controllable Synthesis of High-fidelity 3D-Aware Images

The neural radiance field (NERF) advocates learning the continuous representation of 3D geometry through a multilayer perceptron (MLP). By integrating this into a generative model, the generative neural radiance field (GRAF) is capable of producing images from random noise z without 3D supervision. In practice, the shape and appearance are modeled by z_s and z_a, respectively, to manipulate them separately during inference. However, it is challenging to represent multiple scenes using a solitary MLP and precisely control the generation of 3D geometry in terms of shape and appearance. In this paper, we introduce a controllable generative model (i.e. \textbf{CtrlNeRF}) that uses a single MLP network to represent multiple scenes with shared weights. Consequently, we manipulated the shape and appearance codes to realize the controllable generation of high-fidelity images with 3D consistency. Moreover, the model enables the synthesis of novel views that do not exist in the training sets via camera pose alteration and feature interpolation. Extensive experiments were conducted to demonstrate its superiority in 3D-aware image generation compared to its counterparts.

arXiv:2412.01824공식 코드 · Papers with Code

X-Prompt: Towards Universal In-Context Image Generation in Auto-Regressive Vision Language Foundation Models

In-context generation is a key component of large language models' (LLMs) open-task generalization capability. By leveraging a few examples as context, LLMs can perform both in-domain and out-of-domain tasks. Recent advancements in auto-regressive vision-language models (VLMs) built upon LLMs have showcased impressive performance in text-to-image generation. However, the potential of in-context learning for general image generation tasks remains largely unexplored. To address this, we introduce X-Prompt, a purely auto-regressive large-vision language model designed to deliver competitive performance across a wide range of both seen and unseen image generation tasks, all within a unified in-context learning framework. X-Prompt incorporates a specialized design that efficiently compresses valuable features from in-context examples, supporting longer in-context token sequences and improving its ability to generalize to unseen tasks. A unified training task for both text and image prediction enables X-Prompt to handle general image generation with enhanced task awareness from in-context examples. Extensive experiments validate the model's performance across diverse seen image generation tasks and its capacity to generalize to previously unseen tasks.

arXiv:2412.01794공식 코드 · Papers with Code

IQA-Adapter: Exploring Knowledge Transfer from Image Quality Assessment to Diffusion-based Generative Models

Diffusion-based models have recently transformed conditional image generation, achieving unprecedented fidelity in generating photorealistic and semantically accurate images. However, consistently generating high-quality images remains challenging, partly due to the lack of mechanisms for conditioning outputs on perceptual quality. In this work, we propose methods to integrate image quality assessment (IQA) models into diffusion-based generators, enabling quality-aware image generation. First, we experiment with gradient-based guidance to optimize image quality directly and show this approach has limited generalizability. To address this, we introduce IQA-Adapter, a novel architecture that conditions generation on target quality levels by learning the relationship between images and quality scores. When conditioned on high target quality, IQA-Adapter shifts the distribution of generated images towards a higher-quality subdomain. This approach achieves up to a 10% improvement across multiple objective metrics, as confirmed by a subjective study, while preserving generative diversity and content. Additionally, IQA-Adapter can be used inversely as a degradation model, generating progressively more distorted images when conditioned on lower quality scores. Our quality-aware methods also provide insights into the adversarial robustness of IQA models, underscoring the potential of quality conditioning in generative modeling and the importance of robust IQA methods.

arXiv:2412.01528

CopyrightShield: Spatial Similarity Guided Backdoor Defense against Copyright Infringement in Diffusion Models

The diffusion model has gained significant attention due to its remarkable data generation ability in fields such as image synthesis. However, its strong memorization and replication abilities with respect to the training data also make it a prime target for copyright infringement attacks. This paper provides an in-depth analysis of the spatial similarity of replication in diffusion model and leverages this key characteristic to design a method for detecting poisoning data. By employing a joint assessment of spatial-level and feature-level information from the detected segments, we effectively identify covertly dispersed poisoned samples. Building upon detected poisoning data, we propose a novel defense method specifically targeting copyright infringement attacks by introducing a protection constraint term into the loss function to mitigate the impact of poisoning. Extensive experimental results demonstrate that our approach achieves an average F1 score of 0.709 in detecting copyright infringement backdoors, resulting in an average increase of 68.1% in First-Attack Epoch (FAE) and an average decrease of 51.4% in Copyright Infringement Rate (CIR) of the poisoned model, effectively defending against copyright infringement. Additionally, we introduce the concept of copyright feature inversion, which aids in determining copyright responsibility and expands the application scenarios of defense strategies.

arXiv:2412.01284공식 코드 · Papers with Code

MFTF: Mask-free Training-free Object Level Layout Control Diffusion Model

Text-to-image generation models have revolutionized content creation, but diffusion-based vision-language models still face challenges in precisely controlling the shape, appearance, and positional placement of objects in generated images using text guidance alone. Existing global image editing models rely on additional masks or images as guidance to achieve layout control, often requiring retraining of the model. While local object-editing models allow modifications to object shapes, they lack the capability to control object positions. To address these limitations, we propose the Mask-free Training-free Object-Level Layout Control Diffusion Model (MFTF), which provides precise control over object positions without requiring additional masks or images. The MFTF model supports both single-object and multi-object positional adjustments, such as translation and rotation, while enabling simultaneous layout control and object semantic editing. The MFTF model employs a parallel denoising process for both the source and target diffusion models. During this process, attention masks are dynamically generated from the cross-attention layers of the source diffusion model and applied to queries from the self-attention layers to isolate objects. These queries, generated in the source diffusion model, are then adjusted according to the layout control parameters and re-injected into the self-attention layers of the target diffusion model. This approach ensures accurate and precise positional control of objects. Project source code available at https://github.com/syang-genai/MFTF.

arXiv:2412.02530

WEM-GAN: Wavelet transform based facial expression manipulation

Facial expression manipulation aims to change human facial expressions without affecting face recognition. In order to transform the facial expressions to target expressions, previous methods relied on expression labels to guide the manipulation process. However, these methods failed to preserve the details of facial features, which causes the weakening or the loss of identity information in the output image. In our work, we propose WEM-GAN, in short for wavelet-based expression manipulation GAN, which puts more efforts on preserving the details of the original image in the editing process. Firstly, we take advantage of the wavelet transform technique and combine it with our generator with a U-net autoencoder backbone, in order to improve the generator's ability to preserve more details of facial features. Secondly, we also implement the high-frequency component discriminator, and use high-frequency domain adversarial loss to further constrain the optimization of our model, providing the generated face image with more abundant details. Additionally, in order to narrow the gap between generated facial expressions and target expressions, we use residual connections between encoder and decoder, while also using relative action units (AUs) several times. Extensive qualitative and quantitative experiments have demonstrated that our model performs better in preserving identity features, editing capability, and image generation quality on the AffectNet dataset. It also shows superior performance in metrics such as Average Content Distance (ACD) and Expression Distance (ED).

arXiv:2412.02368공식 코드 · Papers with Code

ScImage: How Good Are Multimodal Large Language Models at Scientific Text-to-Image Generation?

Multimodal large language models (LLMs) have demonstrated impressive capabilities in generating high-quality images from textual instructions. However, their performance in generating scientific images--a critical application for accelerating scientific progress--remains underexplored. In this work, we address this gap by introducing ScImage, a benchmark designed to evaluate the multimodal capabilities of LLMs in generating scientific images from textual descriptions. ScImage assesses three key dimensions of understanding: spatial, numeric, and attribute comprehension, as well as their combinations, focusing on the relationships between scientific objects (e.g., squares, circles). We evaluate five models, GPT-4o, Llama, AutomaTikZ, Dall-E, and StableDiffusion, using two modes of output generation: code-based outputs (Python, TikZ) and direct raster image generation. Additionally, we examine four different input languages: English, German, Farsi, and Chinese. Our evaluation, conducted with 11 scientists across three criteria (correctness, relevance, and scientific accuracy), reveals that while GPT-4o produces outputs of decent quality for simpler prompts involving individual dimensions such as spatial, numeric, or attribute understanding in isolation, all models face challenges in this task, especially for more complex prompts.

arXiv:2412.02237공식 코드 · Papers with Code

Cross-Attention Head Position Patterns Can Align with Human Visual Concepts in Text-to-Image Generative Models

Recent text-to-image diffusion models leverage cross-attention layers, which have been effectively utilized to enhance a range of visual generative tasks. However, our understanding of cross-attention layers remains somewhat limited. In this study, we present a method for constructing Head Relevance Vectors (HRVs) that align with useful visual concepts. An HRV for a given visual concept is a vector with a length equal to the total number of cross-attention heads, where each element represents the importance of the corresponding head for the given visual concept. We develop and employ an ordered weakening analysis to demonstrate the effectiveness of HRVs as interpretable features. To demonstrate the utility of HRVs, we propose concept strengthening and concept adjusting methods and apply them to enhance three visual generative tasks. We show that misinterpretations of polysemous words in image generation can be corrected in most cases, five challenging attributes in image editing can be successfully modified, and catastrophic neglect in multi-concept generation can be mitigated. Overall, our work provides an advancement in understanding cross-attention layers and introduces new approaches for fine-controlling these layers at the head level.

arXiv:2412.02099공식 코드 · Papers with Code

AccDiffusion v2: Towards More Accurate Higher-Resolution Diffusion Extrapolation

Diffusion models suffer severe object repetition and local distortion when the inference resolution differs from its pre-trained resolution. We propose AccDiffusion v2, an accurate method for patch-wise higher-resolution diffusion extrapolation without training. Our in-depth analysis in this paper shows that using an identical text prompt for different patches leads to repetitive generation, while the absence of a prompt undermines image details. In response, our AccDiffusion v2 novelly decouples the vanilla image-content-aware prompt into a set of patch-content-aware prompts, each of which serves as a more precise description of a patch. Further analysis reveals that local distortion arises from inaccurate descriptions in prompts about the local structure of higher-resolution images. To address this issue, AccDiffusion v2, for the first time, introduces an auxiliary local structural information through ControlNet during higher-resolution diffusion extrapolation aiming to mitigate the local distortions. Finally, our analysis indicates that global semantic information is conducive to suppressing both repetitive generation and local distortion. Hence, our AccDiffusion v2 further proposes dilated sampling with window interaction for better global semantic information during higher-resolution diffusion extrapolation. We conduct extensive experiments, including both quantitative and qualitative comparisons, to demonstrate the efficacy of our AccDiffusion v2. The quantitative comparison shows that AccDiffusion v2 achieves state-of-the-art performance in image generation extrapolation without training. The qualitative comparison intuitively illustrates that AccDiffusion v2 effectively suppresses the issues of repetitive generation and local distortion in image generation extrapolation. Our code is available at \url{https://github.com/lzhxmu/AccDiffusion_v2}.

arXiv:2412.02692공식 코드 · Papers with Code

Taming Scalable Visual Tokenizer for Autoregressive Image Generation

Existing vector quantization (VQ) methods struggle with scalability, largely attributed to the instability of the codebook that undergoes partial updates during training. The codebook is prone to collapse as utilization decreases, due to the progressively widening distribution gap between non-activated codes and visual features. To solve the problem, we propose Index Backpropagation Quantization (IBQ), a new VQ method for the joint optimization of all codebook embeddings and the visual encoder. Applying a straight-through estimator on the one-hot categorical distribution between the encoded feature and codebook, all codes are differentiable and maintain a consistent latent space with the visual encoder. IBQ enables scalable training of visual tokenizers and, for the first time, achieves a large-scale codebook ($2^{18}$) with high dimension ($256$) and high utilization. Experiments on the standard ImageNet benchmark demonstrate the scalability and superiority of IBQ, achieving competitive results on both reconstruction ($1.00$ rFID) and autoregressive visual generation ($2.05$ gFID). The code and models are available at https://github.com/TencentARC/SEED-Voken.

arXiv:2412.01137공식 코드 · Papers with Code

TextSSR: Diffusion-based Data Synthesis for Scene Text Recognition

Scene text recognition (STR) suffers from the challenges of either less realistic synthetic training data or the difficulty of collecting sufficient high-quality real-world data, limiting the effectiveness of trained STR models. Meanwhile, despite producing holistically appealing text images, diffusion-based text image generation methods struggle to generate accurate and realistic instance-level text on a large scale. To tackle this, we introduce TextSSR: a novel framework for Synthesizing Scene Text Recognition data via a diffusion-based universal text region synthesis model. It ensures accuracy by focusing on generating text within a specified image region and leveraging rich glyph and position information to create the less complex text region compared to the entire image. Furthermore, we utilize neighboring text within the region as a prompt to capture real-world font styles and layout patterns, guiding the generated text to resemble actual scenes. Finally, due to its prompt-free nature and capability for character-level synthesis, TextSSR enjoys a wonderful scalability and we construct an anagram-based TextSSR-F dataset with 0.4 million text instances with complexity and realism. Experiments show that models trained on added TextSSR-F data exhibit better accuracy compared to models trained on 4 million existing synthetic data. Moreover, its accuracy margin to models trained fully on a real-world dataset is less than 3.7%, confirming TextSSR's effectiveness and its great potential in scene text image synthesis. Our code is available at https://github.com/YesianRohn/TextSSR.

arXiv:2412.00837

AniMer: Animal Pose and Shape Estimation Using Family Aware Transformer

Quantitative analysis of animal behavior and biomechanics requires accurate animal pose and shape estimation across species, and is important for animal welfare and biological research. However, the small network capacity of previous methods and limited multi-species dataset leave this problem underexplored. To this end, this paper presents AniMer to estimate animal pose and shape using family aware Transformer, enhancing the reconstruction accuracy of diverse quadrupedal families. A key insight of AniMer is its integration of a high-capacity Transformer-based backbone and an animal family supervised contrastive learning scheme, unifying the discriminative understanding of various quadrupedal shapes within a single framework. For effective training, we aggregate most available open-sourced quadrupedal datasets, either with 3D or 2D labels. To improve the diversity of 3D labeled data, we introduce CtrlAni3D, a novel large-scale synthetic dataset created through a new diffusion-based conditional image generation pipeline. CtrlAni3D consists of about 10k images with pixel-aligned SMAL labels. In total, we obtain 41.3k annotated images for training and validation. Consequently, the combination of a family aware Transformer network and an expansive dataset enables AniMer to outperform existing methods not only on 3D datasets like Animal3D and CtrlAni3D, but also on out-of-distribution Animal Kingdom dataset. Ablation studies further demonstrate the effectiveness of our network design and CtrlAni3D in enhancing the performance of AniMer for in-the-wild applications. The project page of AniMer is https://luoxue-star.github.io/AniMer_project_page/.

arXiv:2412.00176

Opt-In Art: Learning Art Styles Only from Few Examples

We explore whether pre-training on datasets with paintings is necessary for a model to learn an artistic style with only a few examples. To investigate this, we train a text-to-image model exclusively on photographs, without access to any painting-related content. We show that it is possible to adapt a model that is trained without paintings to an artistic style, given only few examples. User studies and automatic evaluations confirm that our model (post-adaptation) performs on par with state-of-the-art models trained on massive datasets that contain artistic content like paintings, drawings or illustrations. Finally, using data attribution techniques, we analyze how both artistic and non-artistic datasets contribute to generating artistic-style images. Surprisingly, our findings suggest that high-quality artistic outputs can be achieved without prior exposure to artistic data, indicating that artistic style generation can occur in a controlled, opt-in manner using only a limited, carefully selected set of training examples.

arXiv:2411.16749

AnySynth: Harnessing the Power of Image Synthetic Data Generation for Generalized Vision-Language Tasks

Diffusion models have recently been employed to generate high-quality images, reducing the need for manual data collection and improving model generalization in tasks such as object detection, instance segmentation, and image perception. However, the synthetic framework is usually designed with meticulous human effort for each task due to various requirements on image layout, content, and annotation formats, restricting the application of synthetic data on more general scenarios. In this paper, we propose AnySynth, a unified framework integrating adaptable, comprehensive, and highly controllable components capable of generating an arbitrary type of synthetic data given diverse requirements. Specifically, the Task-Specific Layout Generation Module is first introduced to produce reasonable layouts for different tasks by leveraging the generation ability of large language models and layout priors of real-world images. A Uni-Controlled Image Generation Module is then developed to create high-quality synthetic images that are controllable and based on the generated layouts. In addition, user specific reference images, and style images can be incorporated into the generation to task requirements. Finally, the Task-Oriented Annotation Module offers precise and detailed annotations for the generated images across different tasks. We have validated our framework's performance across various tasks, including Few-shot Object Detection, Cross-domain Object Detection, Zero-shot Composed Image Retrieval, and Multi-modal Image Perception and Grounding. The specific data synthesized by our framework significantly improves model performance in these tasks, demonstrating the generality and effectiveness of our framework.

arXiv:2411.19005

Locally-Focused Face Representation for Sketch-to-Image Generation Using Noise-Induced Refinement

This paper presents a novel deep-learning framework that significantly enhances the transformation of rudimentary face sketches into high-fidelity colour images. Employing a Convolutional Block Attention-based Auto-encoder Network (CA2N), our approach effectively captures and enhances critical facial features through a block attention mechanism within an encoder-decoder architecture. Subsequently, the framework utilises a noise-induced conditional Generative Adversarial Network (cGAN) process that allows the system to maintain high performance even on domains unseen during the training. These enhancements lead to considerable improvements in image realism and fidelity, with our model achieving superior performance metrics that outperform the best method by FID margin of 17, 23, and 38 on CelebAMask-HQ, CUHK, and CUFSF datasets; respectively. The model sets a new state-of-the-art in sketch-to-image generation, can generalize across sketch types, and offers a robust solution for applications such as criminal identification in law enforcement.

arXiv:2411.18936

Self-Cross Diffusion Guidance for Text-to-Image Synthesis of Similar Subjects

Diffusion models have achieved unprecedented fidelity and diversity for synthesizing image, video, 3D assets, etc. However, subject mixing is a known and unresolved issue for diffusion-based image synthesis, particularly for synthesizing multiple similar-looking subjects. We propose Self-Cross diffusion guidance to penalize the overlap between cross-attention maps and aggregated self-attention maps. Compared to previous methods based on self-attention or cross-attention alone, our self-cross guidance is more effective in eliminating subject mixing. What's more, our guidance addresses mixing for all relevant patches of a subject beyond the most discriminant one, e.g., beak of a bird. We aggregate self-attention maps of automatically selected patches for a subject to form a region that the whole subject attends to. Our method is training-free and can boost the performance of any transformer-based diffusion model such as Stable Diffusion.% for synthesizing similar subjects. We also release a more challenging benchmark with many text prompts of similar-looking subjects and utilize GPT-4o for automatic and reliable evaluation. Extensive qualitative and quantitative results demonstrate the effectiveness of our Self-Cross guidance.

arXiv:2411.18824

FaithDiff: Unleashing Diffusion Priors for Faithful Image Super-resolution

Faithful image super-resolution (SR) not only needs to recover images that appear realistic, similar to image generation tasks, but also requires that the restored images maintain fidelity and structural consistency with the input. To this end, we propose a simple and effective method, named FaithDiff, to fully harness the impressive power of latent diffusion models (LDMs) for faithful image SR. In contrast to existing diffusion-based SR methods that freeze the diffusion model pre-trained on high-quality images, we propose to unleash the diffusion prior to identify useful information and recover faithful structures. As there exists a significant gap between the features of degraded inputs and the noisy latent from the diffusion model, we then develop an effective alignment module to explore useful features from degraded inputs to align well with the diffusion process. Considering the indispensable roles and interplay of the encoder and diffusion model in LDMs, we jointly fine-tune them in a unified optimization framework, facilitating the encoder to extract useful features that coincide with diffusion process. Extensive experimental results demonstrate that FaithDiff outperforms state-of-the-art methods, providing high-quality and faithful SR results.

arXiv:2411.18810

Enhancing Compositional Text-to-Image Generation with Reliable Random Seeds

Text-to-image diffusion models have demonstrated remarkable capability in generating realistic images from arbitrary text prompts. However, they often produce inconsistent results for compositional prompts such as "two dogs" or "a penguin on the right of a bowl". Understanding these inconsistencies is crucial for reliable image generation. In this paper, we highlight the significant role of initial noise in these inconsistencies, where certain noise patterns are more reliable for compositional prompts than others. Our analyses reveal that different initial random seeds tend to guide the model to place objects in distinct image areas, potentially adhering to specific patterns of camera angles and image composition associated with the seed. To improve the model's compositional ability, we propose a method for mining these reliable cases, resulting in a curated training set of generated images without requiring any manual annotation. By fine-tuning text-to-image models on these generated images, we significantly enhance their compositional capabilities. For numerical composition, we observe relative increases of 29.3% and 19.5% for Stable Diffusion and PixArt-{\alpha}, respectively. Spatial composition sees even larger gains, with 60.7% for Stable Diffusion and 21.1% for PixArt-{\alpha}.