Generative models have enabled intuitive image creation and manipulation using natural language. In particular, diffusion models have recently shown remarkable results for natural image editing. In this work, we propose to apply diffusion techniques to edit textures, a specific class of images that are an essential part of 3D content creation pipelines. We analyze existing editing methods and show that they are not directly applicable to textures, since their common underlying approach, manipulating attention maps, is unsuitable for the texture domain. To address this, we propose a novel approach that instead manipulates CLIP image embeddings to condition the diffusion generation. We define editing directions using simple text prompts (e.g., “aged wood” to “new wood”) and map these to CLIP image embedding space using a texture prior, with a sampling-based approach that gives us identity-preserving directions in CLIP space. To further improve identity preservation, we project these directions to a CLIP subspace that minimizes identity variations resulting from entangled texture attributes. Our editing pipeline facilitates the creation of arbitrary sliders using natural language prompts only, with no ground-truth annotated data necessary.
论文检索
输入标题、作者或关键词，从 9,256 篇学术成果中精准定位
The recent success of pre-trained diffusion models unlocks the possibility of the automatic generation of textures for arbitrary 3D meshes in the wild. However, these models are trained in the screen space, while converting them to a multi-view consistent texture image poses a major obstacle to the output quality. In this paper, we propose a novel method to enforce multi-view consistency. Our method is based on the observation that latent space in a pre-trained diffusion model is noised separately for each camera view, making it difficult to achieve multi-view consistency by directly manipulating the latent codes. Based on the celebrated Denoising Diffusion Implicit Models (DDIM) scheme, we propose to use an optimization-based color-fusion to enforce consistency and indirectly modify the latent codes by gradient back-propagation. Our method further relaxes the sequential dependency assumption among the camera views. By evaluating on a series of general 3D models, we find our simple approach improves consistency and overall quality of the generated textures as compared to competing state-of-the-arts. Our implementation is available at: https://github.com/Quantuman134/TexPainter
We present a technique that leverages 2D generative diffusion models (DMs) for interactive texture painting on the surface of 3D meshes. Unlike existing texture painting systems, our method allows artists to paint with any complex image texture, and in contrast with traditional texture synthesis, our brush not only generates seamless strokes in real-time, but can inpaint realistic transitions between different textures. To enable this application, we present a stamp-based method that applies an adapted pre-trained DM to inpaint patches in local render space, which is then projected into the texture image, allowing artists control over brush stroke shape and texture orientation. We further present a way to adapt the inference of a pre-trained DM to ensure stable texture brush identity, while allowing the DM to hallucinate infinite variations of the source texture. Our method is the first to use DMs for interactive texture painting, and we hope it will inspire work on applying generative models to highly interactive artist-driven workflows. Code and data for this paper are at github.com/nv-tlabs/DiffusionTexturePainting.
This paper aims to generate materials for 3D meshes from text descriptions. Unlike existing methods that synthesize texture maps, we propose to generate segment-wise procedural material graphs as the appearance representation, which supports high-quality rendering and provides substantial flexibility in editing. Instead of relying on extensive paired data, i.e., 3D meshes with material graphs and corresponding text descriptions, to train a material graph generative model, we propose to leverage the pre-trained 2D diffusion model as a bridge to connect the text and material graphs. Specifically, our approach decomposes a shape into a set of segments and designs a segment-controlled diffusion model to synthesize 2D images that are aligned with mesh parts. Based on generated images, we initialize parameters of material graphs and fine-tune them through the differentiable rendering module to produce materials in accordance with the textual description. Extensive experiments demonstrate the superior performance of our framework in photorealism, resolution, and editability over existing methods.
Few-shot font generation (FFG) aims to streamline the manual aspects of the font design process. Existing models are capable of generating glyph images in the same style of a few input reference glyphs. However, mainly due to their inefficient glyph representations, these existing FFG methods are limited to generating low-resolution glyph images. To address this problem, we introduce QT-Font, an efficient quadtree-based diffusion model specifically designed for FFG. More specifically, we design a sparse quadtree-based glyph representation to reduce the complexity of the representation space, exhibiting linear complexity and uniqueness. Concurrently, to reduce computational complexity, we propose a U-net model based on the dual quadtree graph network and the discrete diffusion model. Furthermore, a content-aware pooling module is also adopted to lessen the computational demands of the diffusion process. Qualitative and quantitative experiments have been conducted to demonstrate that our QT-Font, compared to existing approaches, can generate high-resolution glyph images with superior quality and more visually pleasing details, meanwhile significantly reducing both parameter sizes and computational costs.
Humans naturally build mental models of object interactions and dynamics, allowing them to imagine how their surroundings will change if they take a certain action. While generative models today have shown impressive results on generating/editing images unconditionally or conditioned on text, current methods do not provide the ability to perform fine-grained object manipulation conditioned on actions, an important tool for world modeling and action planning. Therefore, we propose learning to model interactions through a novel form of visual conditioning: hands. Hands are a natural way to specify control through actions such as grasping, pulling, pushing, etc. Given an input image and a representation of a hand interacting with the scene, our approach, CoSHAND, synthesizes a depiction of what the scene would look like after the interaction has occurred. We show that CoSHAND is able to recover the dynamics of manipulation by learning from large amounts of unlabeled videos of human hands interacting with objects, and leveraging internet-scale latent diffusion model priors. The model demonstrates strong capabilities on a variety of actions and object types beyond the dataset, and the ability to generate multiple possible futures depending on the actions performed. CoSHAND is also able to generalize zero-shot to tasks where the agent is a robot arm rather than a human hand. Our hand-conditioned model has several exciting applications in robotic planning and augmented or virtual reality.
This paper introduces innovative solutions to enhance spatial controllability in diffusion models reliant on text queries. We first introduce vision guidance as a foundational spatial cue within the perturbed distribution. This significantly refines the search space in a zero-shot paradigm to focus on the image sampling process adhering to the spatial layout conditions. To precisely control the spatial layouts of multiple visual concepts with the employment of vision guidance, we propose a universal framework, Layered Rendering Diffusion (LRDiff), which constructs an image-rendering process with multiple layers, each of which applies the vision guidance to instructively estimate the denoising direction for a single object. Such a layered rendering strategy effectively prevents issues like unintended conceptual blending or mismatches while allowing for more coherent and contextually accurate image synthesis. The proposed method offers a more efficient and accurate means of synthesising images that align with specific layout and contextual requirements. Through experiments, we demonstrate that our method outperforms existing techniques, both quantitatively and qualitatively, in two specific layout-to-image tasks: bounding box-to-image and instance mask-to-image. Furthermore, we extend the proposed framework to enable spatially controllable editing.
SEDiff: Structure Extraction for Domain Adaptive Depth Estimation via Denoising Diffusion Models
PDF ↗In monocular depth estimation, it is challenging to acquire a large amount of depth-annotated training data, which leads to a reliance on synthetic datasets. However, the inherent discrepancies between the synthetic environment and the real-world result in a domain shift and sub-optimal performance. In this paper, we introduces SEDiff which leverages a diffusion-based generative model to extract essential structural information for accurate depth estimation. SEDiff wipes out the domain-specific components in the synthetic data and enables structural-consistent image transfer to mitigate the performance degradation due to the domain gap. Extensive experiments demonstrate the superiority of SEDiff over state-of-the-art methods in various scenarios for domain-adaptive depth estimation.
Stochastic Human Motion Prediction (HMP) aims to predict multiple possible future pose sequences from observed ones. Most prior works learn motion distributions through encoding-decoding in latent space, which does not preserve motion’s spatial-temporal structure. While effective, these methods often require complex, multi-stage training and yield predictions that are inconsistent with the provided history and can be physically unrealistic. To address these issues, we propose CoMusion, a single-stage, end-to-end diffusion-based stochastic HMP framework. CoMusion is inspired from the insight that a smooth future pose initialization improves prediction performance, a strategy not previously utilized in stochastic models but evidenced in deterministic works. To generate such initialization, CoMusion's motion predictor starts with a Transformer-based network for initial reconstruction of corrupted motion. Then, a graph convolutional network (GCN) is employed to refine the prediction considering past observations in the discrete cosine transformation (DCT) space. Our method, facilitated by the Transformer-GCN module design and a proposed variance scheduler, excels in predicting accurate, realistic, and consistent motion, while maintaining an appropriate level of diversity. Experimental results on benchmark datasets demonstrate that CoMusion surpasses prior methods in both accuracy and fidelity, achieving at least a 35% relative improvement in fidelity metrics, while demonstrating superior robustness. Our method, facilitated by the Transformer-GCN module design and a proposed variance scheduler, excels in predicting accurate, realistic, and consistent motions, while maintaining an appropriate level of diversity. Experimental results on benchmark datasets demonstrate that CoMusion surpasses prior methods in both accuracy and fidelity, achieving at least a 35% relative improvement in fidelity metrics, while demonstrating superior robustness.
Diffusion models achieve remarkable quality in image generation, but at a cost. Iterative denoising requires many time steps to produce high fidelity images. We argue that the denoising process is crucially limited by an accumulation of the reconstruction error due to an initial inaccurate reconstruction of the target data. This leads to lower quality outputs, and slower convergence. To address these issues, we propose compensation sampling to guide the generation towards the target domain. We introduce a compensation term, implemented as a U-Net, which adds negligible computation overhead during training. Our approach is flexible and we demonstrate its application in unconditional generation, face inpainting, and face de-occlusion on benchmark datasets CIFAR-10, CelebA, CelebA-HQ, FFHQ-256, and FSG. Our approach consistently yields state-of-the-art results in terms of image quality, while accelerating the denoising process to converge during training by up to an order of magnitude.
The concept of negative prompts, emerging from conditional generation models like Stable Diffusion, allows users to specify what to exclude from the generated images. Despite the widespread use of negative prompts, their intrinsic mechanisms remain largely unexplored. This paper presents the first comprehensive study to uncover how and when negative prompts take effect. Our extensive empirical analysis identifies two primary behaviors of negative prompts. Delayed Effect: The impact of negative prompts is observed after positive prompts render corresponding content. Deletion Through Neutralization: Negative prompts delete concepts from the generated image through a mutual cancellation effect in latent space with positive prompts. These insights reveal significant potential real-world applications; for example, we demonstrate that negative prompts can facilitate object inpainting with minimal alterations to the background via a simple adaptive algorithm. We believe our findings will offer valuable insights for the community in capitalizing on the potential of negative prompts.
Weather forecasting requires both deterministic outcomes for immediate decision-making and probabilistic results for assessing uncertainties. However, deterministic models may not fully capture the spectrum of weather possibilities, and probabilistic forecasting can lack the precision needed for specific planning, presenting significant challenges as the field aims for enhance accuracy and reliability. In this paper, we propose the Deterministic Guidance-based Diffusion Model (DGDM) to exploit the benefits of both deterministic and probabilistic weather forecasting models. DGDM integrates a deterministic branch and a diffusion model as a probabilistic branch to improve forecasting accuracy while providing probabilistic forecasting. In addition, we introduce a sequential variance schedule that predicts from the near future to the distant future. Moreover, we present a truncated diffusion by using the result of the deterministic branch to truncate the reverse process of the diffusion model to control uncertainties. We conduct extensive analyses of DGDM on the Moving MNIST. Furthermore, we evaluate the effectiveness of DGDM on the Pacific Northwest Windstorm (PNW)-Typhoon satellite dataset for regional extreme weather forecasting, as well as on the WeatherBench dataset for global weather forecasting dataset. Experimental results show that DGDM achieves state-of-the-art performance not only in global forecasting but also in regional forecasting scenarios. The code is available at: https://github.com/DongGeun-Yoon/DGDM.
In the realm of 3D computer vision, parametric models have emerged as a ground-breaking methodology for the creation of realistic and expressive 3D avatars. Traditionally, they rely on Principal Component Analysis (PCA), given its ability to decompose data to an orthonormal space that maximally captures shape variations. However, due to the orthogonality constraints and the global nature of PCA's decomposition, these models struggle to perform localized and disentangled editing of 3D shapes, which severely affects their use in applications requiring fine control such as face sculpting. In this paper, we leverage diffusion models to enable diverse and fully localized edits on 3D meshes, while completely preserving the un-edited regions. We propose an effective diffusion masking training strategy that, by design, facilitates localized manipulation of any shape region, without being limited to predefined regions or to sparse sets of predefined control vertices. Following our framework, a user can explicitly set their manipulation region of choice and define an arbitrary set of vertices as handles to edit a 3D mesh. Compared to the current state-of-the-art our method leads to more interpretable shape manipulations than methods relying on latent code state, greater localization and generation diversity while offering faster inference than optimization based approaches. Code has been included in the supplementary material.
CloudFixer: Test-Time Adaptation for 3D Point Clouds via Diffusion-Guided Geometric Transformation
PDF ↗3D point clouds captured from real-world sensors frequently encompass noisy points due to various obstacles, such as occlusion, limited resolution, and variations in scale. This poses challenges when deploying pre-trained point cloud recognition models trained on clean point clouds, leading to significant performance degradation. While test-time adaptation (TTA) strategies have shown promising results in addressing this issue in the 2D domain, its application to 3D point clouds remains under-explored. Among TTA methods, an input adaptation approach, which directly converts test instances to the source domain using a pre-trained diffusion model, has been proposed in the 2D domain. Despite its robust TTA performance in practical situations, naively adopting this into the 3D domain may be suboptimal due to the neglect of inherent properties of point clouds, and its prohibitive computational cost. Motivated by such limitations, we propose CloudFixer, a test-time input adaptation method tailored for 3D point clouds, employing pre-trained diffusion model. Specifically, CloudFixer optimizes geometric transformation parameters with carefully designed objectives that leverage the geometric properties of point clouds. We also substantially improve computational efficiency by avoiding backpropagation through the diffusion model or extensive generation process. Furthermore, we propose an online model adaptation strategy by aligning the original model prediction with that of the adapted input. Extensive experiments showcase the superiority of CloudFixer over various TTA baselines, excelling in handling common corruptions and natural distribution shifts across diverse real-world scenarios.
Long-term action anticipation has become an important task for many applications such as autonomous driving and human-robot interaction. Unlike short-term anticipation, predicting more actions into the future imposes a real challenge with the increasing uncertainty in longer horizons. While there has been a significant progress in predicting more actions into the future, most of the proposed methods address the task in a deterministic setup and ignore the underlying uncertainty. In this paper, we propose a novel temporal diffusion network that models the uncertainty of both the observation and the future predictions. As generator, we introduce a Gated Anticipation Network (GTAN) to model both observed and unobserved frames of a video in a mutual representation. On the one hand, using a mutual representation for past and future allows us to jointly model ambiguities in the observation and future, while on the other hand by design GTAN can intrinsically treat the observed and unobserved parts differently and steer the information flow between them. Our model achieves state-of-the-art results on the Breakfast, Assembly101 and 50Salads datasets in both stochastic and deterministic settings.
When deploying a semantic segmentation model into the real world, it will inevitably encounter semantic classes that were not seen during training. Therefore, to ensure a safe deployment of such systems, it is crucial to accurately evaluate and improve their anomaly segmentation capabilities. However, acquiring and labelling semantic segmentation data is expensive and unanticipated conditions are long-tail and potentially hazardous. Indeed, existing anomaly segmentation datasets capture a limited number of anomalies, lack realism or have strong domain shifts. In this paper, we propose the Placing Objects in Context (POC) pipeline to realistically add any object into any image via diffusion models. POC can be used to easily extend any dataset with an arbitrary number of objects. In our experiments, we present different anomaly segmentation datasets based on POC-generated data and show that POC can improve the performance of recent state-of-the-art anomaly fine-tuning methods across several standardized benchmarks. POC is also effective for learning new classes. For example, we utilize it to augment Cityscapes samples by incorporating a subset of Pascal classes and demonstrate that models trained on such data achieve comparable performance to the Pascal-trained baseline. This corroborates the low synth2real gap of models trained on POC-generated images.
We introduce a novel diffusion-based video generation method, generating a video showing multiple events given multiple individual sentences from the user. Our method does not require a large-scale video dataset since our method uses a pre-trained diffusion-based text-to-video generative model without a fine-tuning process. Specifically, we propose a last frame-aware diffusion process to preserve visual coherence between consecutive videos where each video consists of different events by initializing the latent and simultaneously adjusting noise in the latent to enhance the motion dynamic in a generated video. Furthermore, we find that the iterative update of latent vectors by referring to all the preceding frames maintains the global appearance across the frames in a video clip. To handle dynamic text input for video generation, we utilize a novel prompt generator that transfers course text messages from the user into the multiple optimal prompts for the text-to-video diffusion model. Extensive experiments and user studies show that our proposed method is superior to other video-generative models in terms of temporal coherency of content and semantics.
We revisit Tree-Ring Watermarking, a recent diffusion model watermarking method that demonstrates great robustness to various attacks. We conduct an in-depth study of its framework and reveal that the distribution shift unintentionally introduced by the watermarking process, apart from watermark pattern matching, contributes to its exceptional robustness. Our investigation further exposes inherent flaws in the original design, particularly in its ability to identify multiple distinct watermark keys, where distribution shift offers no advantage. Based on the preceding analysis, we propose RingID. It consists of a novel multi-channel heterogeneous watermarking approach designed to seamlessly amalgamate distinctive advantages from diverse watermarks. Moreover, coupled with a series of suggested enhancements, RingID exhibits substantial advancements in both robustness and capacity for multi-key identification.
Text-to-image diffusion models (SD) exhibit significant advancements while requiring extensive computational resources. Existing acceleration methods usually require extensive training and are not universally applicable. LCM-LoRA, trainable once for diverse models, offers universality but rarely considers ensuring the consistency of generated content before and after acceleration. This paper proposes SpeedUpNet (SUN), an innovative acceleration module, to address the challenges of universality and consistency. Exploiting the role of cross-attention layers in U-Net for SD models, we introduce an adapter specifically designed for these layers, quantifying the offset in image generation caused by negative prompts relative to positive prompts. This learned offset demonstrates stability across a range of models, enhancing SUN's universality. To improve output consistency, we propose a Multi-Step Consistent (MSC) loss, which stabilizes the offset and ensures fidelity in accelerated content. Experiments on SD v1.5 show that SUN leads to an overall speedup of more than 10 times compared to the baseline 25-step DPM-solver++, and offers two extra advantages: (1) training-free integration into various fine-tuned Stable-Diffusion models and (2) state-of-the-art FIDs of the generated data set before and after acceleration guided by random combinations of positive and negative prompts.
UDiffText: A Unified Framework for High-quality Text Synthesis in Arbitrary Images via Character-aware Diffusion Models
PDF ↗Text-to-Image (T2I) generation methods based on diffusion model have garnered significant attention in the last few years. Although these image synthesis methods produce visually appealing results, they frequently exhibit spelling errors when rendering text within the generated images. Such errors manifest as missing, incorrect or extraneous characters, thereby severely constraining the performance of text image generation based on diffusion models. To address the aforementioned issue, this paper proposes a novel approach for text image generation, utilizing a pre-trained diffusion model (i.e., Stable Diffusion [27]). Our approach involves the design and training of a light-weight character-level text encoder, which replaces the original CLIP encoder and provides more robust text embeddings as conditional guidance. Then, we fine-tune the diffusion model using a large-scale dataset, incorporating local attention control under the supervision of character-level segmentation maps. Finally, by employing an inference stage refinement process, we achieve a notably high sequence accuracy when synthesizing text in arbitrarily given images. Both qualitative and quantitative results demonstrate the superiority of our method to the state of the art. Furthermore, we showcase several potential applications of the proposed UDiffText, including text-centric image synthesis, scene text inpainting, etc. Code and model will be available at ***.