论文检索

Hao-Yang Peng, Jia-Peng Zhang, Meng-Hao Guo 0001, Yan-Pei Cao 0001, Shi-Min Hu 0001

BNRist, Department of Computer Science and Technology, Tsinghua University, China In the field of digital content creation, generating high-quality 3D characters from single images is challenging, especially given the complexities of various body poses and the issues of self-occlusion and pose ambiguity. In this paper, we present CharacterGen, a framework developed to efficiently generate 3D characters. CharacterGen introduces a streamlined generation pipeline along with an image-conditioned multi-view diffusion model. This model effectively calibrates input poses to a canonical form while retaining key attributes of the input image, thereby addressing the challenges posed by diverse poses. A transformer-based, generalizable sparse-view reconstruction model is the other core component of our approach, facilitating the creation of detailed 3D models from multi-view images. We also adopt a texture-back-projection strategy to produce high-quality texture maps. Additionally, we have curated a dataset of anime characters, rendered in multiple poses and views, to train and evaluate our model. Our approach has been thoroughly evaluated through quantitative and qualitative experiments, showing its proficiency in generating 3D characters with high-quality shapes and textures, ready for downstream applications such as rigging and animation.

Kai He, Kaixin Yao, Qixuan Zhang, Jingyi Yu 0001, Lingjie Liu, Lan Xu 0003

Apparel's significant role in human appearance underscores the importance of garment digitalization for digital human creation. Recent advances in 3D content creation are pivotal for digital human creation. Nonetheless, garment generation from text guidance is still nascent. We introduce a text-driven 3D garment generation framework, DressCode, which aims to democratize design for novices and offer immense potential in fashion design, virtual try-on, and digital human creation. We first introduce SewingGPT, a GPT-based architecture integrating cross-attention with text-conditioned embedding to generate sewing patterns with text guidance. We then tailor a pre-trained Stable Diffusion to generate tile-based Physically-based Rendering (PBR) textures for the garments. By leveraging a large language model, our framework generates CG-friendly garments through natural language interaction. It also facilitates pattern completion and texture editing, streamlining the design process through user-friendly interaction. This framework fosters innovation by allowing creators to freely experiment with designs and incorporate unique elements into their work. With comprehensive evaluations and comparisons with other state-of-the-art methods, our method showcases superior quality and alignment with input prompts. User studies further validate our high-quality rendering results, highlighting its practical utility and potential in production settings. Our project page is https://IHe-KaiI.github.io/DressCode/.

Wei Li 0112, Kui Wu 0003, Mathieu Desbrun

Despite its visual appeal, the simulation of separated multiphase flows (i.e., streams of fluids separated by interfaces) faces numerous challenges in accurately reproducing complex behaviors such as guggling, wetting, or bubbling. These difficulties are especially pronounced for high Reynolds numbers and large density variations between fluids, most likely explaining why they have received comparatively little attention in Computer Graphics compared to single- or two-phase flows. In this paper, we present a full LBM solver for multifluid simulation. We derive a conservative phase field model with which the spatial presence of each fluid or phase is encoded to allow for the simulation of miscible, immiscible and even partially-miscible fluids, while the temporal evolution of the phases is performed using a D3Q7 lattice-Boltzmann discretization. The velocity field, handled through the recent high-order moment-encoded LBM (HOME-LBM) framework to minimize its memory footprint, is simulated via a velocity-based distribution stored on a D3Q27 or D3Q19 discretization to offer accuracy and stability to large density ratios even in turbulent scenarios, while coupling with the phases through pressure, viscosity, and interfacial forces is achieved by leveraging the diffuse encoding of interfaces. The resulting solver addresses a number of limitations of kinetic methods in both computational fluid dynamics and computer graphics: it offers a fast, accurate, and low-memory fluid solver enabling efficient turbulent multiphase simulations free of the typical oscillatory pressure behavior near boundaries. We present several numerical benchmarks, examples and comparisons of multiphase flows to demonstrate our solver's visual complexity, accuracy, and realism.

Zhiyao Sun, Tian Lv, Sheng Ye, Matthieu Gaetan Lin, Jenny Sheng, Yu-Hui Wen, Minjing Yu, Yong-Jin Liu 0001

The generation of stylistic 3D facial animations driven by speech presents a significant challenge as it requires learning a many-to-many mapping between speech, style, and the corresponding natural facial motion. However, existing methods either employ a deterministic model for speech-to-motion mapping or encode the style using a one-hot encoding scheme. Notably, the one-hot encoding approach fails to capture the complexity of the style and thus limits generalization ability. In this paper, we propose DiffPoseTalk, a generative framework based on the diffusion model combined with a style encoder that extracts style embeddings from short reference videos. During inference, we employ classifier-free guidance to guide the generation process based on the speech and style. In particular, our style includes the generation of head poses, thereby enhancing user perception. Additionally, we address the shortage of scanned 3D talking face data by training our model on reconstructed 3DMM parameters from a high-quality, in-the-wild audio-visual dataset. Extensive experiments and user study demonstrate that our approach outperforms state-of-the-art methods. The code and dataset are at https://diffposetalk.github.io.

Yiqian Wu, Hao Xu 0049, Xiangjun Tang, Xien Chen, Siyu Tang 0001, Zhebin Zhang, Chen Li 0062, Xiaogang Jin 0001

Existing neural rendering-based text-to-3D-portrait generation methods typically make use of human geometry prior and diffusion models to obtain guidance. However, relying solely on geometry information introduces issues such as the Janus problem, over-saturation, and over-smoothing. We present Portrait3D, a novel neural rendering-based framework with a novel joint geometry-appearance prior to achieve text-to-3D-portrait generation that overcomes the aforementioned issues. To accomplish this, we train a 3D portrait generator, 3DPortraitGAN, as a robust prior. This generator is capable of producing 360° canonical 3D portraits, serving as a starting point for the subsequent diffusion-based generation process. To mitigate the "grid-like" artifact caused by the high-frequency information in the feature-map-based 3D representation commonly used by most 3D-aware GANs, we integrate a novel pyramid tri-grid 3D representation into 3DPortraitGAN. To generate 3D portraits from text, we first project a randomly generated image aligned with the given prompt into the pre-trained 3DPortraitGAN's latent space. The resulting latent code is then used to synthesize a pyramid tri-grid. Beginning with the obtained pyramid tri-grid, we use score distillation sampling to distill the diffusion model's knowledge into the pyramid tri-grid. Following that, we utilize the diffusion model to refine the rendered images of the 3D portrait and then use these refined images as training data to further optimize the pyramid tri-grid, effectively eliminating issues with unrealistic color and unnatural artifacts. Our experimental results show that Portrait3D can produce realistic, high-quality, and canonical 3D portraits that align with the prompt.

Feng-Lin Liu, Hongbo Fu 0001, Yu-Kun Lai, Lin Gao 0004

Existing text-based 3D generation methods generate attractive results but lack detailed geometry control. Sketches, known for their conciseness and expressiveness, have contributed to intuitive 3D modeling but are confined to producing texture-less mesh models within predefined categories. Integrating sketch and text simultaneously for 3D generation promises enhanced control over geometry and appearance but faces challenges from 2D-to-3D translation ambiguity and multi-modal condition integration. Moreover, further editing of 3D models in arbitrary views will give users more freedom to customize their models. However, it is difficult to achieve high generation quality, preserve unedited regions, and manage proper interactions between shape components. To solve the above issues, we propose a text-driven 3D content generation and editing method, SketchDream, which supports NeRF generation from given hand-drawn sketches and achieves free-view sketch-based local editing. To tackle the 2D-to-3D ambiguity challenge, we introduce a sketch-based multi-view image generation diffusion model, which leverages depth guidance to establish spatial correspondence. A 3D ControlNet with a 3D attention module is utilized to control multi-view images and ensure their 3D consistency. To support local editing, we further propose a coarse-to-fine editing approach: the coarse phase analyzes component interactions and provides 3D masks to label edited regions, while the fine stage generates realistic results with refined details by local enhancement. Extensive experiments validate that our method generates higher-quality results compared with a combination of 2D ControlNet and image-to-3D generation techniques and achieves detailed control compared with existing diffusion-based 3D editing approaches.

Zhennan Wu, Yang Li 0193, Han Yan 0004, Taizhang Shang, Weixuan Sun, Senbo Wang, Ruikai Cui, Weizhe Liu, Hiroyuki Sato 0002, Hongdong Li 等

We present BlockFusion, a diffusion-based model that generates 3D scenes as unit blocks and seamlessly incorporates new blocks to extend the scene. BlockFusion is trained using datasets of 3D blocks that are randomly cropped from complete 3D scene meshes. Through per-block fitting, all training blocks are converted into the hybrid neural fields: with a tri-plane containing the geometry features, followed by a Multi-layer Perceptron (MLP) for decoding the signed distance values. A variational auto-encoder is employed to compress the tri-planes into the latent tri-plane space, on which the denoising diffusion process is performed. Diffusion applied to the latent representations allows for high-quality and diverse 3D scene generation. To expand a scene during generation, one needs only to append empty blocks to overlap with the current scene and extrapolate existing latent tri-planes to populate new blocks. The extrapolation is done by conditioning the generation process with the feature samples from the overlapping tri-planes during the denoising iterations. Latent tri-plane extrapolation produces semantically and geometrically meaningful transitions that harmoniously blend with the existing scene. A 2D layout conditioning mechanism is used to control the placement and arrangement of scene elements. Experimental results indicate that BlockFusion is capable of generating diverse, geometrically consistent and unbounded large 3D scenes with unprecedented high-quality shapes in both indoor and outdoor scenarios.

Sai Raj Kishore Perla, Yizhi Wang 0006, Ali Mahdavi-Amiri, Hao Zhang 0002

We present a novel approach for single-image mesh texturing, which employs a diffusion model with judicious conditioning to seamlessly transfer an object's texture from a single RGB image to a given 3D mesh object. We do not assume that the two objects belong to the same category, and even if they do, there can be significant discrepancies in their geometry and part proportions. Our method aims to rectify the discrepancies by conditioning a pre-trained Stable Diffusion generator with edges describing the mesh through ControlNet, and features extracted from the input image using IP-Adapter to generate textures that respect the underlying geometry of the mesh and the input texture without any optimization or training. We also introduce Image Inversion, a novel technique to quickly personalize the diffusion model for a single concept using a single image, for cases where the pre-trained IP-Adapter falls short in capturing all the details from the input image faithfully. Experimental results demonstrate the efficiency and effectiveness of our edge-aware single-image mesh texturing approach, coined EASI-Tex, in preserving the details of the input texture on diverse 3D objects, while respecting their geometry. Code: https://github.com/sairajk/easi-tex

Yuqing Zhang 0005, Yuan Liu 0025, Zhiyu Xie 0004, Lei Yang 0048, Zhongyuan Liu, Mengzhou Yang, Runze Zhang, Qilong Kou, Cheng Lin 0001, Wenping Wang 0001 等

Recent advancements in 2D diffusion models allow appearance generation on untextured raw meshes. These methods create RGB textures by distilling a 2D diffusion model, which often contains unwanted baked-in shading effects and results in unrealistic rendering effects in the downstream applications. Generating Physically Based Rendering (PBR) materials instead of just RGB textures would be a promising solution. However, directly distilling the PBR material parameters from 2D diffusion models still suffers from incorrect material decomposition, such as baked-in shading effects in albedo. We introduce DreamMat, an innovative approach to resolve the aforementioned problem, to generate high-quality PBR materials from text descriptions. We find out that the main reason for the incorrect material distillation is that large-scale 2D diffusion models are only trained to generate final shading colors, resulting in insufficient constraints on material decomposition during distillation. To tackle this problem, we first finetune a new light-aware 2D diffusion model to condition on a given lighting environment and generate the shading results on this specific lighting condition. Then, by applying the same environment lights in the material distillation, DreamMat can generate high-quality PBR materials that are not only consistent with the given geometry but also free from any baked-in shading effects in albedo. Extensive experiments demonstrate that the materials produced through our methods exhibit greater visual appeal to users and achieve significantly superior rendering quality compared to baseline methods, which are preferable for downstream tasks such as game and film production.

Peiying Zhang 0002, Nanxuan Zhao, Jing Liao 0001

Vector graphics are widely used in digital art and highly favored by designers due to their scalability and layer-wise properties. However, the process of creating and editing vector graphics requires creativity and design expertise, making it a time-consuming task. Recent advancements in text-to-vector (T2V) generation have aimed to make this process more accessible. However, existing T2V methods directly optimize control points of vector graphics paths, often resulting in intersecting or jagged paths due to the lack of geometry constraints. To overcome these limitations, we propose a novel neural path representation by designing a dual-branch Variational Autoencoder (VAE) that learns the path latent space from both sequence and image modalities. By optimizing the combination of neural paths, we can incorporate geometric constraints while preserving expressivity in generated SVGs. Furthermore, we introduce a two-stage path optimization method to improve the visual and topological quality of generated SVGs. In the first stage, a pre-trained text-to-image diffusion model guides the initial generation of complex vector graphics through the Variational Score Distillation (VSD) process. In the second stage, we refine the graphics using a layer-wise image vectorization strategy to achieve clearer elements and structure. We demonstrate the effectiveness of our method through extensive experiments and showcase various applications. The project page is https://intchous.github.io/T2V-NPR.

Noam Aigerman, Thibault Groueix

This paper proposes a fully-automatic, text-guided generative method for producing perfectly-repeating, periodic, tile-able 2D imagery, such as the one seen on floors, mosaics, ceramics, and the work of M.C. Escher. In contrast to square texture images that are seamless when tiled, our method generates non-square tilings which comprise solely of repeating copies of the same object. It achieves this by optimizing both geometry and texture of a 2D mesh, yielding a non-square tile in the shape and appearance of the desired object, with close to no additional background details, that can tile the plane without gaps nor overlaps. We enable optimization of the tile’s shape by an unconstrained, differentiable parameterization of the space of all valid tileable meshes for given boundary conditions stemming from a symmetry group. Namely, we construct a differentiable family of linear systems derived from a 2D mesh-mapping technique - Orbifold Tutte Embedding - by considering the mesh’s Laplacian matrix as differentiable parameters. We prove that the solution space of these linear systems is exactly all possible valid tiling configurations, thereby providing an end-to-end differentiable representation for the entire space of valid tiles. We render the textured mesh via a differentiable renderer, and leverage a pre-trained image diffusion model to induce a loss on the resulting image, updating the mesh’s parameters so as to make its appearance match the text prompt. We show our method is able to produce plausible, appealing results, with non-trivial tiles, for a variety of different periodic tiling patterns.

Ryan D. Burgert, Xiang Li 0109, Abe Leite, Kanchana Ranasinghe, Michael S. Ryoo

We explore the problem of computationally generating special images that produce multi-arrangement optical illusions when physically arranged and viewed in a certain way, which we call ‘prime’ images. First, we propose a formal definition for this problem. Next, we introduce Diffusion Illusions, the first comprehensive pipeline designed to automatically generate a wide range of these multi-arrangement illusions. Specifically, we both adapt the existing ‘score distillation loss’ and propose a new ‘dream target loss’ to optimize a group of differentially parametrized prime images, using a frozen text-to-image diffusion model. We study three types of illusions, each where the prime images are arranged in different ways and optimized using the aforementioned losses such that images derived from them align with user-chosen text prompts or images. We conduct comprehensive experiments on these illusions and verify the effectiveness of our proposed method qualitatively and quantitatively. Additionally, we showcase the successful physical fabrication of our illusions — as they are all designed to work in the real world. Code and examples are publicly available at our interactive project website: https://diffusionillusion.github.io/

You Xie, Hongyi Xu, Guoxian Song, Chao Wang 0088, Yichun Shi, Linjie Luo

We propose X-Portrait, an innovative conditional diffusion model tailored for generating expressive and temporally coherent portrait animation. Specifically, given a single portrait as appearance reference, we aim to animate it with motion derived from a driving video, capturing both highly dynamic and subtle facial expressions along with wide-range head movements. As its core, we leverage the generative prior of a pre-trained diffusion model as the rendering backbone, while achieve fine-grained head pose and expression control with novel controlling signals within the framework of ControlNet. In contrast to conventional coarse explicit controls such as facial landmarks, our motion control module is learned to interpret the dynamics directly from the original driving RGB inputs. The motion accuracy is further enhanced with a patch-based local control module that effectively enhance the motion attention to small-scale nuances like eyeball positions. Notably, to mitigate the identity leakage from the driving signals, we train our motion control modules with scaling-augmented cross-identity images, ensuring maximized disentanglement from the appearance reference modules. Experimental results demonstrate the universal effectiveness of X-Portrait across a diverse range of facial portraits and expressive driving sequences, and showcase its proficiency in generating captivating portrait animations with consistently maintained identity characteristics.

Shiyuan Yang, Liang Hou, Haibin Huang, Chongyang Ma, Pengfei Wan 0001, Di Zhang 0026, Xiaodong Chen 0009, Jing Liao 0001

Recent text-to-video diffusion models have achieved impressive progress. In practice, users often desire the ability to control object motion and camera movement independently for customized video creation. However, current methods lack the focus on separately controlling object motion and camera movement in a decoupled manner, which limits the controllability and flexibility of text-to-video models. In this paper, we introduce Direct-a-Video, a system that allows users to independently specify motions for multiple objects as well as camera’s pan and zoom movements, as if directing a video. We propose a simple yet effective strategy for the decoupled control of object motion and camera movement. Object motion is controlled through spatial cross-attention modulation using the model’s inherent priors, requiring no additional optimization. For camera movement, we introduce new temporal cross-attention layers to interpret quantitative camera movement parameters. We further employ an augmentation-based approach to train these layers in a self-supervised manner on a small-scale dataset, eliminating the need for explicit motion annotation. Both components operate independently, allowing individual or combined control, and can generalize to open-domain scenarios. Extensive experiments demonstrate the superiority and effectiveness of our method. Project page and code are available at https://direct-a-video.github.io/.

Xun Guo 0001, Mingwu Zheng, Liang Hou, Yuan Gao 0015, Yufan Deng, Pengfei Wan 0001, Di Zhang 0026, Yufan Liu 0001, Weiming Hu 0004, Zhengjun Zha 等

Text-guided image-to-video (I2V) generation aims to generate a coherent video that preserves the identity of the input image and semantically aligns with the input prompt. Existing methods typically augment pretrained text-to-video (T2V) models by either concatenating the image with noised video frames channel-wise before being fed into the model or injecting the image embedding produced by pretrained image encoders in cross-attention modules. However, the former approach often necessitates altering the fundamental weights of pretrained T2V models, thus restricting the model’s compatibility within the open-source communities and disrupting the model’s prior knowledge. Meanwhile, the latter typically fails to preserve the identity of the input image. We present I2V-Adapter to overcome such limitations. I2V-Adapter adeptly propagates the unnoised input image to subsequent noised frames through a cross-frame attention mechanism, maintaining the identity of the input image without any changes to the pretrained T2V model. Notably, I2V-Adapter only introduces a few trainable parameters, significantly alleviating the training cost and also ensures compatibility with existing community-driven personalized models and control tools. Moreover, we propose a novel Frame Similarity Prior to balance the motion amplitude and the stability of generated videos through two adjustable control coefficients. Our experimental results demonstrate that I2V-Adapter is capable of producing high-quality videos. This performance, coupled with its agility and adaptability, represents a substantial advancement in the field of I2V, particularly for personalized and controllable applications.

Xiaoyu Shi 0002, Zhaoyang Huang, Fu-Yun Wang, Weikang Bian, Dasong Li, Yi Zhang 0108, Manyuan Zhang, Ka Chun Cheung, Simon See, Hongwei Qin 等

We introduce Motion-I2V, a novel framework for consistent and controllable text-guided image-to-video generation (I2V). In contrast to previous methods that directly learn the complicated image-to-video mapping, Motion-I2V factorizes I2V into two stages with explicit motion modeling. For the first stage, we propose a diffusion-based motion field predictor, which focuses on deducing the trajectories of the reference image’s pixels. For the second stage, we propose motion-augmented temporal attention to enhance the limited 1-D temporal attention in video latent diffusion models. This module can effectively propagate reference image features to synthesized frames with the guidance of predicted trajectories from the first stage. Compared with existing methods, Motion-I2V can generate more consistent videos even in the presence of large motion and viewpoint variation. By training a sparse trajectory ControlNet for the first stage, Motion-I2V can support users to precisely control motion trajectories and motion regions with sparse trajectory and region. This offers more controllability of the I2V process than solely relying on textual instructions. Additionally, Motion-I2V’s second stage naturally supports zero-shot video-to-video translation. Both qualitative and quantitative comparisons demonstrate the advantages of Motion-I2V over prior approaches in consistent and controllable image-to-video generation. Please see our project page at https://xiaoyushi97.github.io/Motion-I2V/.

Xuebo Ji, Zherong Pan, Xifeng Gao, Jia Pan 0001

Creating vivid crowd animations is core to immersive virtual environments in digital games. This work focuses on tackling the challenges of the crowd behavior generation problem. Existing approaches are labor-intensive, relying on practitioners to manually craft the complex behavior systems. We propose a machine learning approach to synthesize diversified dynamic crowd animation scenarios for a given environment based on a text description input. We first train two conditional diffusion models that generate text-guided agent distribution fields and velocity fields. Assisted by local navigation algorithms, the fields are then used to control multiple groups of agents. We further employ Large-Language Model (LLM) to canonicalize the general script into a structured sentence for more stable training and better scalability. To train our diffusion models, we devise a constructive method to generate random environments and crowd animations. We show that our trained diffusion models can generate crowd animations for both unseen environments and novel scenario descriptions. Our method paves the way towards automatic generating of crowd behaviors for virtual environments. Code and data for this paper are available at: https://github.com/MLZG/Text-Crowd.git.

Zhengzhe Liu, Qing Liu 0017, Chirui Chang, Jianming Zhang 0001, Daniil Pakhomov, Haitian Zheng, Zhe Lin 0001, Daniel Cohen-Or, Chi-Wing Fu

Deoccluding the hidden portions of objects in a scene is a formidable task, particularly when addressing real-world scenes. In this paper, we present a new self-supervised PArallel visible-to-COmplete diffusion framework, named PACO, a foundation model for object-level scene deocclusion. Leveraging the rich prior of pre-trained models, we first design the parallel variational autoencoder, which produces a full-view feature map that simultaneously encodes multiple complete objects, and the visible-to-complete latent generator, which learns to implicitly predict the full-view feature map from partial-view feature map and text prompts extracted from the incomplete objects in the input image. To train PACO, we create a large-scale dataset with 500k samples to enable self-supervised learning, avoiding tedious annotations of the amodal masks and occluded regions. At inference, we devise a layer-wise deocclusion strategy to improve efficiency while maintaining the deocclusion quality. Extensive experiments on COCOA and various real-world scenes demonstrate the superior capability of PACO for scene deocclusion, surpassing the state of the arts by a large margin. Our method can also be extended to cross-domain scenes and novel categories that are not covered by the training set. Further, we demonstrate the deocclusion applicability of PACO in single-view 3D scene reconstruction and object recomposition. Project page: https://liuzhengzhe.github.io/Deocclude-Any-Object.github.io/.

Zhipeng Bao, Yijun Li 0001, Krishna Kumar Singh, Yu-Xiong Wang, Martial Hebert

Despite recent significant strides achieved by diffusion-based Text-to-Image (T2I) models, current systems are still less capable of ensuring decent compositional generation aligned with text prompts, particularly for the multi-object generation. In this work, we first show the fundamental reasons for such misalignment by identifying issues related to low attention activation and mask overlaps. Then we propose a compositional finetuning framework with two novel objectives, the Separate loss and the Enhance loss, that reduce object mask overlaps and maximize attention scores, respectively. Unlike conventional test-time adaptation methods, our model, once finetuned on critical parameters, is able to directly perform inference given an arbitrary multi-object prompt, which enhances the scalability and generalizability. Through comprehensive evaluations, our model demonstrates superior performance in image realism, text-image alignment, and adaptability, significantly surpassing established baselines. Furthermore, we show that training our model with a diverse range of concepts enables it to generalize effectively to novel concepts, exhibiting enhanced performance compared to models trained on individual concept pairs.

Zeqi Gu, Ethan Yang, Abe Davis

Recent advances in diffusion-based generative models have shown incredible promise for zero shot image-to-image translation and editing. Most of these approaches work by combining or replacing network-specific features used in the generation of new images with those taken from the inversion of some guide image. Methods of this type are considered the current state-of-the-art in training-free approaches, but have some notable limitations: they tend to be costly in runtime and memory, and often depend on deterministic sampling that limits variation in generated results. We propose Filter-Guided Diffusion (FGD), an alternative approach that leverages fast filtering operations during the diffusion process to support finer control over the strength and frequencies of guidance and can work with non-deterministic samplers to produce greater variety. With its efficiency, FGD can be sampled over multiple seeds and hyperparameters in less time than a single run of other SOTA methods to produce superior results based on structural and semantic metrics. We conduct extensive quantitative and qualitative experiments to evaluate the performance of FGD in translation tasks and also demonstrate its potential in localized editing when used with masks.