Image and video colorization are among the most common problems in image restoration. This is an ill-posed problem and a wide variety of methods have been proposed, ranging from more traditional computer vision strategies to most recent development with transformer-based or generative neural network models. In this work we show how a latent diffusion model, pre-trained on text-to-image synthesis, can be finetuned for image colorization and provide a flexible solution for a wide variety of scenarios: high quality direct colorization with diverse results, user guided colorization through colors hints, text prompts or reference image and finally video colorization. Some works already investigated using diffusion models for colorization, however the proposed solutions are often more complex and require training a side model guiding the denoising process (à la ControlNet). Not only is this approach increasing the number of parameters and compute time, it also results in sub optimal colorization as we show. Our evaluation demonstrates that our model is the only approach that offers a wide flexibility while either matching or outperforming existing methods specialized in each sub-task, by proposing a group of universal, architecture-agnostic mechanisms which could be applied to any pre-trained diffusion model.
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
We introduce GEM3D 1 – a new deep, topology-aware generative model of 3D shapes. The key ingredient of our method is a neural skeleton-based representation encoding information on both shape topology and geometry. Through a denoising diffusion probabilistic model, our method first generates skeleton-based representations following the Medial Axis Transform (MAT), then generates surfaces through a skeleton-driven neural implicit formulation. The neural implicit takes into account the topological and geometric information stored in the generated skeleton representations to yield surfaces that are more topologically and geometrically accurate compared to previous neural field formulations. We discuss applications of our method in shape synthesis and point cloud reconstruction tasks, and evaluate our method both qualitatively and quantitatively. We demonstrate significantly more faithful surface reconstruction and diverse shape generation results compared to the state-of-the-art, also involving challenging scenarios of reconstructing and synthesizing structurally complex, high-genus shape surfaces from Thingi10K and ShapeNet.
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 extensive pre-trained knowledge, to regularize the matting process. We present novel architectural innovations that empower our model to produce mattes with superior resolution and detail. The proposed method is versatile and can perform both guidance-free and guidance-based image matting, accommodating a variety of additional cues. Our comprehensive evaluation across three benchmark datasets demonstrates the superior performance of our approach, both quantitatively and qualitatively. The results not only reflect our method’s robust effectiveness but also highlight its ability to generate visually compelling mattes that approach photorealistic quality. The code for this paper is available at https://github.com/lightChaserX/alphaLDM.
The three areas of realistic forward rendering, per-pixel inverse rendering, and generative image synthesis may seem like separate and unrelated sub-fields of graphics and vision. However, recent work has demonstrated improved estimation of per-pixel intrinsic channels (albedo, roughness, metallicity) based on a diffusion architecture; we call this the RGB → X problem. We further show that the reverse problem of synthesizing realistic images given intrinsic channels, X → RGB, can also be addressed in a diffusion framework. Focusing on the image domain of interior scenes, we introduce an improved diffusion model for RGB → X, which also estimates lighting, as well as the first diffusion X → RGB model capable of synthesizing realistic images from (full or partial) intrinsic channels. Our X → RGB model explores a middle ground between traditional rendering and generative models: We can specify only certain appearance properties that should be followed, and give freedom to the model to hallucinate a plausible version of the rest. This flexibility allows using a mix of heterogeneous training datasets that differ in the available channels. We use multiple existing datasets and extend them with our own synthetic and real data, resulting in a model capable of extracting scene properties better than previous work and of generating highly realistic images of interior scenes.
Reasoning about the intrinsic properties of an image, such as albedo, illumination, and surface geometry, is a long-standing problem with many applications in image editing and compositing. Existing solutions to this ill-posed problem either heavily rely on manually designed priors or learn priors from limited datasets that lack diversity. Hence, they fall short in generalizing to in-the-wild test scenarios. In this paper, we show that a large-scale text-to-image generation model trained on a massive amount of visual data can implicitly learn intrinsic image priors. In particular, we introduce a novel conditioning mechanism built on top of a pre-trained foundational image generation model to jointly predict multiple intrinsic modalities from an input image. We demonstrate that predicting different modalities in a collaborative manner improves the overall quality. This design also enables mixing datasets with annotations of only a subset of the modalities during training, contributing to the generalizability of our approach. Our method achieves state-of-the-art performance in intrinsic image decomposition, both qualitatively and quantitatively. We also demonstrate downstream image editing applications, such as relighting and retexturing.
This paper presents a novel method for exerting fine-grained lighting control during text-driven diffusion-based image generation. While existing diffusion models already have the ability to generate images under any lighting condition, without additional guidance these models tend to correlate image content and lighting. Moreover, text prompts lack the necessary expressional power to describe detailed lighting setups. To provide the content creator with fine-grained control over the lighting during image generation, we augment the text-prompt with detailed lighting information in the form of radiance hints, i.e., visualizations of the scene geometry with a homogeneous canonical material under the target lighting. However, the scene geometry needed to produce the radiance hints is unknown. Our key observation is that we only need to guide the diffusion process, hence exact radiance hints are not necessary; we only need to point the diffusion model in the right direction. Based on this observation, we introduce a three stage method for controlling the lighting during image generation. In the first stage, we leverage a standard pretrained diffusion model to generate a provisional image under uncontrolled lighting. Next, in the second stage, we resynthesize and refine the foreground object in the generated image by passing the target lighting to a refined diffusion model, named DiLightNet, using radiance hints computed on a coarse shape of the foreground object inferred from the provisional image. To retain the texture details, we multiply the radiance hints with a neural encoding of the provisional synthesized image before passing it to DiLightNet. Finally, in the third stage, we resynthesize the background to be consistent with the lighting on the foreground object. We demonstrate and validate our lighting controlled diffusion model on a variety of text prompts and lighting conditions.
Text-to-motion diffusion models can generate realistic animations from text prompts, but do not support fine-grained motion editing controls. In this paper, we present a method for using natural language to iteratively specify local edits to existing character animations, a task that is common in most computer animation workflows. Our key idea is to represent a space of motion edits using a set of kinematic motion editing operators (MEOs) whose effects on the source motion is well-aligned with user expectations. We provide an algorithm that leverages pre-existing language models to translate textual descriptions of motion edits into source code for programs that define and execute sequences of MEOs on a source animation. We execute MEOs by first translating them into keyframe constraints, and then use diffusion-based motion models to generate output motions that respect these constraints. Through a user study and quantitative evaluation, we demonstrate that our system can perform motion edits that respect the animator’s editing intent, remain faithful to the original animation (it edits the original animation, but does not dramatically change it), and yield realistic character animation results.
Motion in-betweening, a fundamental task in character animation, consists of generating motion sequences that plausibly interpolate user-provided keyframe constraints. It has long been recognized as a labor-intensive and challenging process. We investigate the potential of diffusion models in generating diverse human motions guided by keyframes. Unlike previous inbetweening methods, we propose a simple unified model capable of generating precise and diverse motions that conform to a flexible range of user-specified spatial constraints, as well as text conditioning. To this end, we propose Conditional Motion Diffusion In-betweening (CondMDI) which allows for arbitrary dense-or-sparse keyframe placement and partial keyframe constraints while generating high-quality motions that are diverse and coherent with the given keyframes. We evaluate the performance of CondMDI on the text-conditioned HumanML3D dataset and demonstrate the versatility and efficacy of diffusion models for keyframe in-betweening. We further explore the use of guidance and imputation-based approaches for inference-time keyframing and compare CondMDI against these methods.
The gradual nature of a diffusion process that synthesizes samples in small increments constitutes a key ingredient of Denoising Diffusion Probabilistic Models (DDPM), which have presented unprecedented quality in image synthesis and been recently explored in the motion domain. In this work, we propose to adapt the gradual diffusion concept (operating along a diffusion time-axis) into the temporal-axis of the motion sequence. Our key idea is to extend the DDPM framework to support temporally varying denoising, thereby entangling the two axes. Using our special formulation, we iteratively denoise a motion buffer that contains a set of increasingly-noised poses, which auto-regressively produces an arbitrarily long stream of frames. With a stationary diffusion time-axis, in each diffusion step we increment only the temporal-axis of the motion such that the framework produces a new, clean frame which is removed from the beginning of the buffer, followed by a newly drawn noise vector that is appended to it. This new mechanism paves the way towards a new framework for long-term motion synthesis with applications to character animation and other domains.
We present a novel character control framework that effectively utilizes motion diffusion probabilistic models to generate high-quality and diverse character animations, responding in real-time to a variety of dynamic user-supplied control signals. At the heart of our method lies a transformer-based Conditional Autoregressive Motion Diffusion Model (CAMDM), which takes as input the character’s historical motion and can generate a range of diverse potential future motions conditioned on high-level, coarse user control. To meet the demands for diversity, controllability, and computational efficiency required by a real-time controller, we incorporate several key algorithmic designs. These include separate condition tokenization, classifier-free guidance on past motion, and heuristic future trajectory extension, all designed to address the challenges associated with taming motion diffusion probabilistic models for character control. As a result, our work represents the first model that enables real-time generation of high-quality, diverse character animations based on user interactive control, supporting animating the character in multiple styles with a single unified model. We evaluate our method on a diverse set of locomotion skills, demonstrating the merits of our method over existing character controllers. The code and model are available at https://aiganimation.github.io/CAMDM/.
In this paper, we introduce LGTM, a novel Local-to-Global pipeline for Text-to-Motion generation. LGTM utilizes a diffusion-based architecture and aims to address the challenge of accurately translating textual descriptions into semantically coherent human motion in computer animation. Specifically, traditional methods often struggle with semantic discrepancies, particularly in aligning specific motions to the correct body parts. To address this issue, we propose a two-stage pipeline to overcome this challenge: it first employs large language models (LLMs) to decompose global motion descriptions into part-specific narratives, which are then processed by independent body-part motion encoders to ensure precise local semantic alignment. Finally, an attention-based full-body optimizer refines the motion generation results and guarantees the overall coherence. Our experiments demonstrate that LGTM gains significant improvements in generating locally accurate, semantically-aligned human motion, marking a notable advancement in text-to-motion applications. Code and data for this paper are available at https://github.com/L-Sun/LGTM
Most of the existing diffusion models use Gaussian noise for training and sampling across all time steps, which may not optimally account for the frequency contents reconstructed by the denoising network. Despite the diverse applications of correlated noise in computer graphics, its potential for improving the training process has been underexplored. In this paper, we introduce a novel and general class of diffusion models taking correlated noise within and across images into account. More specifically, we propose a time-varying noise model to incorporate correlated noise into the training process, as well as a method for fast generation of correlated noise mask. Our model is built upon deterministic diffusion models and utilizes blue noise to help improve the generation quality compared to using Gaussian white (random) noise only. Further, our framework allows introducing correlation across images within a single mini-batch to improve gradient flow. We perform both qualitative and quantitative evaluations on a variety of datasets using our method, achieving improvements on different tasks over existing deterministic diffusion models in terms of FID metric. Code will be available at https://github.com/xchhuang/bndm.
We present a method for generating Streetscapes—long sequences of views through an on-the-fly synthesized city-scale scene. Our generation is conditioned by language input (e.g., city name, weather), as well as an underlying map/layout hosting the desired trajectory. Compared to recent models for video generation or 3D view synthesis, our method can scale to much longer-range camera trajectories, spanning several city blocks, while maintaining visual quality and consistency. To achieve this goal, we build on recent work on video diffusion, used within an autoregressive framework that can easily scale to long sequences. In particular, we introduce a new temporal imputation method that prevents our autoregressive approach from drifting from the distribution of realistic city imagery. We train our Streetscapes system on a compelling source of data—posed imagery from Google Street View, along with contextual map data—which allows users to generate city views conditioned on any desired city layout, with controllable camera pose.
Recent advances in text-to-image generation models have unlocked vast potential for visual creativity. However, the users that use these models struggle with the generation of consistent characters, a crucial aspect for numerous real-world applications such as story visualization, game development, asset design, advertising, and more. Current methods typically rely on multiple pre-existing images of the target character or involve labor-intensive manual processes. In this work, we propose a fully automated solution for consistent character generation, with the sole input being a text prompt. We introduce an iterative procedure that, at each stage, identifies a coherent set of images sharing a similar identity and extracts a more consistent identity from this set. Our quantitative analysis demonstrates that our method strikes a better balance between prompt alignment and identity consistency compared to the baseline methods, and these findings are reinforced by a user study. To conclude, we showcase several practical applications of our approach.
Subject-Diffusion: Open Domain Personalized Text-to-Image Generation without Test-time Fine-tuning
PDF ↗Recent progress in personalized image generation using diffusion models has been significant. However, development in the area of open-domain and test-time fine-tuning-free personalized image generation is proceeding rather slowly. In this paper, we propose Subject-Diffusion, a novel open-domain personalized image generation model that, in addition to not requiring test-time fine-tuning, also only requires a single reference image to support personalized generation of single- or two-subjects in any domain. Firstly, we construct an automatic data labeling tool and use the LAION-Aesthetics dataset to construct a large-scale dataset consisting of 76M images and their corresponding subject detection bounding boxes, segmentation masks, and text descriptions. Secondly, we design a new unified framework that combines text and image semantics by incorporating coarse location and fine-grained reference image control to maximize subject fidelity and generalization. Furthermore, we also adopt an attention control mechanism to support two-subject generation. Extensive qualitative and quantitative results demonstrate that our method have certain advantages over other frameworks in single, multiple, and human-customized image generation.
Recently, the emergence of diffusion models has opened up new opportunities for single-view reconstruction. However, all the existing methods represent the target object as a closed mesh devoid of any structural information, thus neglecting the part-based structure, which is crucial for many downstream applications, of the reconstructed shape. Moreover, the generated meshes usually suffer from large noises, unsmooth surfaces, and blurry textures, making it challenging to obtain satisfactory part segments using 3D segmentation techniques. In this paper, we present Part123, a novel framework for part-aware 3D reconstruction from a single-view image. We first use diffusion models to generate multiview-consistent images from a given image, and then leverage Segment Anything Model (SAM), which demonstrates powerful generalization ability on arbitrary objects, to generate multiview segmentation masks. To effectively incorporate 2D part-based information into 3D reconstruction and handle inconsistency, we introduce contrastive learning into a neural rendering framework to learn a part-aware feature space based on the multiview segmentation masks. A clustering-based algorithm is also developed to automatically derive 3D part segmentation results from the reconstructed models. Experiments show that our method can generate 3D models with high-quality segmented parts on various objects. Compared to existing unstructured reconstruction methods, the part-aware 3D models from our method benefit some important applications, including feature-preserving reconstruction, primitive fitting, and 3D shape editing.
Multiview diffusion (MVD) has emerged as a prominent 3D generation technique, acclaimed for its generalizability, quality, and efficiency. MVD models finetune image diffusion models with 3D data to generate multiple views of a 3D object from an image or text prompt, followed by a multiview 3D reconstruction process. However, the sparsity of views and inconsistent details in the generated multiview images pose challenges for 3D reconstruction. We present MVD2, an efficient 3D reconstruction method tailored for MVD images. MVD2 integrates multiview image features into a 3D feature volume, then transforms this volume into a textureless 3D mesh, onto which the MVD images are mapped as textures. It employs a simple-yet-efficient view-dependent training scheme to mitigate discrepancies between MVD images and ground-truth views of 3D shapes, effectively improving 3D generation quality and robustness. MVD2 is trained with 3D collections and MVD images, and the trained MVD2 efficiently reconstructs 3D meshes from multiview images within one second and exhibits great model generalizability in dealing with images generated by various MVD methods. Our code and the pretrained model are available at: https://zhengxinyang.github.io/projects/MVD_square.html.
The synthesis of 3D facial animations from speech has garnered considerable attention. Due to the scarcity of high-quality 4D facial data and well-annotated abundant multi-modality labels, previous methods often suffer from limited realism and a lack of flexible conditioning. We address this challenge through a trilogy. We first introduce Generalized Neural Parametric Facial Asset (GNPFA), an efficient variational auto-encoder mapping facial geometry and images to a highly generalized expression latent space, decoupling expressions and identities. Then, we utilize GNPFA to extract high-quality expressions and accurate head poses from a large array of videos. This presents the M2F-D dataset, a large, diverse, and scan-level co-speech 3D facial animation dataset with well-annotated emotion and style labels. Finally, we propose Media2Face, a diffusion model in GNPFA latent space for co-speech facial animation generation, accepting rich multi-modality guidances from audio, text, and image. Extensive experiments demonstrate that our model not only achieves high fidelity in facial animation synthesis but also broadens the scope of expressiveness and style adaptability in 3D facial animation.
We are witnessing rapid progress in automatically generating and manipulating 3D assets due to the availability of pretrained text-to-image diffusion models. However, time-consuming optimization procedures are required for synthesizing each sample, hindering their potential for democratizing 3D content creation. Conversely, 3D diffusion models now train on million-scale 3D datasets, yielding high-quality text-conditional 3D samples within seconds. In this work, we present Spice · E – a neural network that adds structural guidance to 3D diffusion models, extending their usage beyond text-conditional generation. At its core, our framework introduces a cross-entity attention mechanism that allows for multiple entities—in particular, paired input and guidance 3D shapes—to interact via their internal representations within the denoising network. We utilize this mechanism for learning task-specific structural priors in 3D diffusion models from auxiliary guidance shapes. We show that our approach supports a variety of applications, including 3D stylization, semantic shape editing and text-conditional abstraction-to-3D, which transforms primitive-based abstractions into highly-expressive shapes. Extensive experiments demonstrate that Spice · E achieves SOTA performance over these tasks while often being considerably faster than alternative methods. Importantly, this is accomplished without tailoring our approach for any specific task. We will release our code and trained models.
As humans, we aspire to create media content that is both freely willed and readily controlled. Thanks to the prominent development of generative techniques, we now can easily utilize 2D diffusion methods to synthesize images controlled by raw sketch or designated human poses, and even progressively edit/regenerate local regions with masked inpainting. However, similar workflows in 3D modeling tasks are still unavailable due to the lack of controllability and efficiency in 3D generation. In this paper, we present a novel controllable and interactive 3D assets modeling framework, named Coin3D. Coin3D allows users to control the 3D generation using a coarse geometry proxy assembled from basic shapes, and introduces an interactive generation workflow to support seamless local part editing while delivering responsive 3D object previewing within a few seconds. To this end, we develop several techniques, including the 3D adapter that applies volumetric coarse shape control to the diffusion model, proxy-bounded editing strategy for precise part editing, progressive volume cache to support responsive preview, and volume-SDS to ensure consistent mesh reconstruction. Extensive experiments of interactive generation and editing on diverse shape proxies demonstrate that our method achieves superior controllability and flexibility in the 3D assets generation task. Code and data are available on the project webpage: https://zju3dv.github.io/coin3d/.