Menglei Chai

Ye Zhu, Kyle Olszewski, Yu Wu et al.

We present Dance2Music-GAN (D2M-GAN), a novel adversarial multi-modal framework that generates complex musical samples conditioned on dance videos. Our proposed framework takes dance video frames and human body motions as input, and learns to generate music samples that plausibly accompany the corresponding input. Unlike most existing conditional music generation works that generate specific types of mono-instrumental sounds using symbolic audio representations (e.g., MIDI), and that usually rely on pre-defined musical synthesizers, in this work we generate dance music in complex styles (e.g., pop, breaking, etc.) by employing a Vector Quantized (VQ) audio representation, and leverage both its generality and high abstraction capacity of its symbolic and continuous counterparts. By performing an extensive set of experiments on multiple datasets, and following a comprehensive evaluation protocol, we assess the generative qualities of our proposal against alternatives. The attained quantitative results, which measure the music consistency, beats correspondence, and music diversity, demonstrate the effectiveness of our proposed method. Last but not least, we curate a challenging dance-music dataset of in-the-wild TikTok videos, which we use to further demonstrate the efficacy of our approach in real-world applications -- and which we hope to serve as a starting point for relevant future research.

Can Wang, Ruixiang Jiang, Menglei Chai et al.

As a powerful representation of 3D scenes, the neural radiance field (NeRF) enables high-quality novel view synthesis from multi-view images. Stylizing NeRF, however, remains challenging, especially on simulating a text-guided style with both the appearance and the geometry altered simultaneously. In this paper, we present NeRF-Art, a text-guided NeRF stylization approach that manipulates the style of a pre-trained NeRF model with a simple text prompt. Unlike previous approaches that either lack sufficient geometry deformations and texture details or require meshes to guide the stylization, our method can shift a 3D scene to the target style characterized by desired geometry and appearance variations without any mesh guidance. This is achieved by introducing a novel global-local contrastive learning strategy, combined with the directional constraint to simultaneously control both the trajectory and the strength of the target style. Moreover, we adopt a weight regularization method to effectively suppress cloudy artifacts and geometry noises which arise easily when the density field is transformed during geometry stylization. Through extensive experiments on various styles, we demonstrate that our method is effective and robust regarding both single-view stylization quality and cross-view consistency. The code and more results can be found in our project page: https://cassiepython.github.io/nerfart/.

Yinghao Xu, Menglei Chai, Zifan Shi et al.

Existing 3D-aware image synthesis approaches mainly focus on generating a single canonical object and show limited capacity in composing a complex scene containing a variety of objects. This work presents DisCoScene: a 3Daware generative model for high-quality and controllable scene synthesis. The key ingredient of our method is a very abstract object-level representation (i.e., 3D bounding boxes without semantic annotation) as the scene layout prior, which is simple to obtain, general to describe various scene contents, and yet informative to disentangle objects and background. Moreover, it serves as an intuitive user control for scene editing. Based on such a prior, the proposed model spatially disentangles the whole scene into object-centric generative radiance fields by learning on only 2D images with the global-local discrimination. Our model obtains the generation fidelity and editing flexibility of individual objects while being able to efficiently compose objects and the background into a complete scene. We demonstrate state-of-the-art performance on many scene datasets, including the challenging Waymo outdoor dataset. Project page: https://snap-research.github.io/discoscene/

Chieh Hubert Lin, Hsin-Ying Lee, Willi Menapace et al.

Toward infinite-scale 3D city synthesis, we propose a novel framework, InfiniCity, which constructs and renders an unconstrainedly large and 3D-grounded environment from random noises. InfiniCity decomposes the seemingly impractical task into three feasible modules, taking advantage of both 2D and 3D data. First, an infinite-pixel image synthesis module generates arbitrary-scale 2D maps from the bird's-eye view. Next, an octree-based voxel completion module lifts the generated 2D map to 3D octrees. Finally, a voxel-based neural rendering module texturizes the voxels and renders 2D images. InfiniCity can thus synthesize arbitrary-scale and traversable 3D city environments, and allow flexible and interactive editing from users. We quantitatively and qualitatively demonstrate the efficacy of the proposed framework. Project page: https://hubert0527.github.io/infinicity/

Ruixiang Jiang, Can Wang, Jingbo Zhang et al.

Neural implicit fields are powerful for representing 3D scenes and generating high-quality novel views, but it remains challenging to use such implicit representations for creating a 3D human avatar with a specific identity and artistic style that can be easily animated. Our proposed method, AvatarCraft, addresses this challenge by using diffusion models to guide the learning of geometry and texture for a neural avatar based on a single text prompt. We carefully design the optimization framework of neural implicit fields, including a coarse-to-fine multi-bounding box training strategy, shape regularization, and diffusion-based constraints, to produce high-quality geometry and texture. Additionally, we make the human avatar animatable by deforming the neural implicit field with an explicit warping field that maps the target human mesh to a template human mesh, both represented using parametric human models. This simplifies animation and reshaping of the generated avatar by controlling pose and shape parameters. Extensive experiments on various text descriptions show that AvatarCraft is effective and robust in creating human avatars and rendering novel views, poses, and shapes. Our project page is: https://avatar-craft.github.io/.

Thanh-Tung Le, Yunhan Zhao, Menglei Chai et al.

Video diffusion transformers have achieved state-of-the-art visual quality, but their high inference cost remains a major bottleneck for real-time applications. Recent distillation frameworks produce autoregressive video diffusion models with reduced latency, yet these models still use a fixed number of denoising steps per frame, wasting computation on predictable frames and under-refining challenging ones. We present DSA, a confidence-guided adaptive computation framework for AR video diffusion. DSA introduces a lightweight confidence head, trained jointly with the generator under a distribution-matching distillation objective, to estimate per-frame denoising reliability. At inference, this confidence signal dynamically adjusts the number of diffusion steps: simple frames terminate early for speed, while complex frames receive additional refinement. Our method requires no extra video data, no heuristics, and little architectural modification. Experiments show that DSA achieves real-time autoregressive video generation, reaching 22.63 FPS with sub-second latency on H100 GPUs, while maintaining competitive or superior VBench quality compared to recent autoregressive and bidirectional video diffusion models. Our results demonstrate that confidence-guided adaptive sampling provides an effective and practical path toward interactive video generation.

Rameen Abdal, Hsin-Ying Lee, Peihao Zhu et al.

Modern 3D-GANs synthesize geometry and texture by training on large-scale datasets with a consistent structure. Training such models on stylized, artistic data, with often unknown, highly variable geometry, and camera information has not yet been shown possible. Can we train a 3D GAN on such artistic data, while maintaining multi-view consistency and texture quality? To this end, we propose an adaptation framework, where the source domain is a pre-trained 3D-GAN, while the target domain is a 2D-GAN trained on artistic datasets. We then distill the knowledge from a 2D generator to the source 3D generator. To do that, we first propose an optimization-based method to align the distributions of camera parameters across domains. Second, we propose regularizations necessary to learn high-quality texture, while avoiding degenerate geometric solutions, such as flat shapes. Third, we show a deformation-based technique for modeling exaggerated geometry of artistic domains, enabling -- as a byproduct -- personalized geometric editing. Finally, we propose a novel inversion method for 3D-GANs linking the latent spaces of the source and the target domains. Our contributions -- for the first time -- allow for the generation, editing, and animation of personalized artistic 3D avatars on artistic datasets.

Yinghao Xu, Wang Yifan, Alexander W. Bergman et al.

Access to high-quality and diverse 3D articulated digital human assets is crucial in various applications, ranging from virtual reality to social platforms. Generative approaches, such as 3D generative adversarial networks (GANs), are rapidly replacing laborious manual content creation tools. However, existing 3D GAN frameworks typically rely on scene representations that leverage either template meshes, which are fast but offer limited quality, or volumes, which offer high capacity but are slow to render, thereby limiting the 3D fidelity in GAN settings. In this work, we introduce layered surface volumes (LSVs) as a new 3D object representation for articulated digital humans. LSVs represent a human body using multiple textured mesh layers around a conventional template. These layers are rendered using alpha compositing with fast differentiable rasterization, and they can be interpreted as a volumetric representation that allocates its capacity to a manifold of finite thickness around the template. Unlike conventional single-layer templates that struggle with representing fine off-surface details like hair or accessories, our surface volumes naturally capture such details. LSVs can be articulated, and they exhibit exceptional efficiency in GAN settings, where a 2D generator learns to synthesize the RGBA textures for the individual layers. Trained on unstructured, single-view 2D image datasets, our LSV-GAN generates high-quality and view-consistent 3D articulated digital humans without the need for view-inconsistent 2D upsampling networks.

Zezhou Cheng, Menglei Chai, Jian Ren et al.

Creating and editing the shape and color of 3D objects require tremendous human effort and expertise. Compared to direct manipulation in 3D interfaces, 2D interactions such as sketches and scribbles are usually much more natural and intuitive for the users. In this paper, we propose a generic multi-modal generative model that couples the 2D modalities and implicit 3D representations through shared latent spaces. With the proposed model, versatile 3D generation and manipulation are enabled by simply propagating the editing from a specific 2D controlling modality through the latent spaces. For example, editing the 3D shape by drawing a sketch, re-colorizing the 3D surface via painting color scribbles on the 2D rendering, or generating 3D shapes of a certain category given one or a few reference images. Unlike prior works, our model does not require re-training or fine-tuning per editing task and is also conceptually simple, easy to implement, robust to input domain shifts, and flexible to diverse reconstruction on partial 2D inputs. We evaluate our framework on two representative 2D modalities of grayscale line sketches and rendered color images, and demonstrate that our method enables various shape manipulation and generation tasks with these 2D modalities.

Yadi Cao, Menglei Chai, Minchen Li et al.

Learning the physical simulation on large-scale meshes with flat Graph Neural Networks (GNNs) and stacking Message Passings (MPs) is challenging due to the scaling complexity w.r.t. the number of nodes and over-smoothing. There has been growing interest in the community to introduce \textit{multi-scale} structures to GNNs for physical simulation. However, current state-of-the-art methods are limited by their reliance on the labor-intensive drawing of coarser meshes or building coarser levels based on spatial proximity, which can introduce wrong edges across geometry boundaries. Inspired by the bipartite graph determination, we propose a novel pooling strategy, \textit{bi-stride} to tackle the aforementioned limitations. Bi-stride pools nodes on every other frontier of the breadth-first search (BFS), without the need for the manual drawing of coarser meshes and avoiding the wrong edges by spatial proximity. Additionally, it enables a one-MP scheme per level and non-parametrized pooling and unpooling by interpolations, resembling U-Nets, which significantly reduces computational costs. Experiments show that the proposed framework, \textit{BSMS-GNN}, significantly outperforms existing methods in terms of both accuracy and computational efficiency in representative physical simulations.

Aliaksandr Siarohin, Willi Menapace, Ivan Skorokhodov et al.

We propose a novel approach for unsupervised 3D animation of non-rigid deformable objects. Our method learns the 3D structure and dynamics of objects solely from single-view RGB videos, and can decompose them into semantically meaningful parts that can be tracked and animated. Using a 3D autodecoder framework, paired with a keypoint estimator via a differentiable PnP algorithm, our model learns the underlying object geometry and parts decomposition in an entirely unsupervised manner. This allows it to perform 3D segmentation, 3D keypoint estimation, novel view synthesis, and animation. We primarily evaluate the framework on two video datasets: VoxCeleb $256^2$ and TEDXPeople $256^2$. In addition, on the Cats $256^2$ image dataset, we show it even learns compelling 3D geometry from still images. Finally, we show our model can obtain animatable 3D objects from a single or few images. Code and visual results available on our project website, see https://snap-research.github.io/unsupervised-volumetric-animation .

Yash Kant, Aliaksandr Siarohin, Riza Alp Guler et al.

Building animatable and editable models of clothed humans from raw 3D scans and poses is a challenging problem. Existing reposing methods suffer from the limited expressiveness of Linear Blend Skinning (LBS), require costly mesh extraction to generate each new pose, and typically do not preserve surface correspondences across different poses. In this work, we introduce Invertible Neural Skinning (INS) to address these shortcomings. To maintain correspondences, we propose a Pose-conditioned Invertible Network (PIN) architecture, which extends the LBS process by learning additional pose-varying deformations. Next, we combine PIN with a differentiable LBS module to build an expressive and end-to-end Invertible Neural Skinning (INS) pipeline. We demonstrate the strong performance of our method by outperforming the state-of-the-art reposing techniques on clothed humans and preserving surface correspondences, while being an order of magnitude faster. We also perform an ablation study, which shows the usefulness of our pose-conditioning formulation, and our qualitative results display that INS can rectify artefacts introduced by LBS well. See our webpage for more details: https://yashkant.github.io/invertible-neural-skinning/

Huan Wang, Feitong Tan, Ziqian Bai et al.

Recent works have shown that neural radiance fields (NeRFs) on top of parametric models have reached SOTA quality to build photorealistic head avatars from a monocular video. However, one major limitation of the NeRF-based avatars is the slow rendering speed due to the dense point sampling of NeRF, preventing them from broader utility on resource-constrained devices. We introduce LightAvatar, the first head avatar model based on neural light fields (NeLFs). LightAvatar renders an image from 3DMM parameters and a camera pose via a single network forward pass, without using mesh or volume rendering. The proposed approach, while being conceptually appealing, poses a significant challenge towards real-time efficiency and training stability. To resolve them, we introduce dedicated network designs to obtain proper representations for the NeLF model and maintain a low FLOPs budget. Meanwhile, we tap into a distillation-based training strategy that uses a pretrained avatar model as teacher to synthesize abundant pseudo data for training. A warping field network is introduced to correct the fitting error in the real data so that the model can learn better. Extensive experiments suggest that our method can achieve new SOTA image quality quantitatively or qualitatively, while being significantly faster than the counterparts, reporting 174.1 FPS (512x512 resolution) on a consumer-grade GPU (RTX3090) with no customized optimization.

Can Wang, Hongliang Zhong, Menglei Chai et al.

Automatic furniture layout is long desired for convenient interior design. Leveraging the remarkable visual reasoning capabilities of multimodal large language models (MLLMs), recent methods address layout generation in a static manner, lacking the feedback-driven refinement essential for interactive user engagement. We introduce Chat2Layout, a novel interactive furniture layout generation system that extends the functionality of MLLMs into the realm of interactive layout design. To achieve this, we establish a unified vision-question paradigm for in-context learning, enabling seamless communication with MLLMs to steer their behavior without altering model weights. Within this framework, we present a novel training-free visual prompting mechanism. This involves a visual-text prompting technique that assist MLLMs in reasoning about plausible layout plans, followed by an Offline-to-Online search (O2O-Search) method, which automatically identifies the minimal set of informative references to provide exemplars for visual-text prompting. By employing an agent system with MLLMs as the core controller, we enable bidirectional interaction. The agent not only comprehends the 3D environment and user requirements through linguistic and visual perception but also plans tasks and reasons about actions to generate and arrange furniture within the virtual space. Furthermore, the agent iteratively updates based on visual feedback from execution results. Experimental results demonstrate that our approach facilitates language-interactive generation and arrangement for diverse and complex 3D furniture.

Selim Emir Can, Jan Ackermann, Kiyohiro Nakayama et al.

Estimating physically accurate, simulation-ready garments from a single image is challenging due to the absence of image-to-physics datasets and the ill-posed nature of this problem. Prior methods either require multi-view capture and expensive differentiable simulation or predict only garment geometry without the material properties required for realistic simulation. We propose a feed-forward framework that sidesteps these limitations by first fine-tuning a vision-language model to infer material composition and fabric attributes from real images, and then training a lightweight predictor that maps these attributes to the corresponding physical fabric parameters using a small dataset of material-physics measurements. Our approach introduces two new datasets (FTAG and T2P) and delivers simulation-ready garments from a single image without iterative optimization. Experiments show that our estimator achieves superior accuracy in material composition estimation and fabric attribute prediction, and by passing them through our physics parameter estimator, we further achieve higher-fidelity simulations compared to state-of-the-art image-to-garment methods.

Can Wang, Menglei Chai, Mingming He et al.

We present CLIP-NeRF, a multi-modal 3D object manipulation method for neural radiance fields (NeRF). By leveraging the joint language-image embedding space of the recent Contrastive Language-Image Pre-Training (CLIP) model, we propose a unified framework that allows manipulating NeRF in a user-friendly way, using either a short text prompt or an exemplar image. Specifically, to combine the novel view synthesis capability of NeRF and the controllable manipulation ability of latent representations from generative models, we introduce a disentangled conditional NeRF architecture that allows individual control over both shape and appearance. This is achieved by performing the shape conditioning via applying a learned deformation field to the positional encoding and deferring color conditioning to the volumetric rendering stage. To bridge this disentangled latent representation to the CLIP embedding, we design two code mappers that take a CLIP embedding as input and update the latent codes to reflect the targeted editing. The mappers are trained with a CLIP-based matching loss to ensure the manipulation accuracy. Furthermore, we propose an inverse optimization method that accurately projects an input image to the latent codes for manipulation to enable editing on real images. We evaluate our approach by extensive experiments on a variety of text prompts and exemplar images and also provide an intuitive interface for interactive editing. Our implementation is available at https://cassiepython.github.io/clipnerf/

Yu Tian, Jian Ren, Menglei Chai et al.

Image and video synthesis are closely related areas aiming at generating content from noise. While rapid progress has been demonstrated in improving image-based models to handle large resolutions, high-quality renderings, and wide variations in image content, achieving comparable video generation results remains problematic. We present a framework that leverages contemporary image generators to render high-resolution videos. We frame the video synthesis problem as discovering a trajectory in the latent space of a pre-trained and fixed image generator. Not only does such a framework render high-resolution videos, but it also is an order of magnitude more computationally efficient. We introduce a motion generator that discovers the desired trajectory, in which content and motion are disentangled. With such a representation, our framework allows for a broad range of applications, including content and motion manipulation. Furthermore, we introduce a new task, which we call cross-domain video synthesis, in which the image and motion generators are trained on disjoint datasets belonging to different domains. This allows for generating moving objects for which the desired video data is not available. Extensive experiments on various datasets demonstrate the advantages of our methods over existing video generation techniques. Code will be released at https://github.com/snap-research/MoCoGAN-HD.

Zhentao Tan, Menglei Chai, Dongdong Chen et al.

Semantic image synthesis, translating semantic layouts to photo-realistic images, is a one-to-many mapping problem. Though impressive progress has been recently made, diverse semantic synthesis that can efficiently produce semantic-level multimodal results, still remains a challenge. In this paper, we propose a novel diverse semantic image synthesis framework from the perspective of semantic class distributions, which naturally supports diverse generation at semantic or even instance level. We achieve this by modeling class-level conditional modulation parameters as continuous probability distributions instead of discrete values, and sampling per-instance modulation parameters through instance-adaptive stochastic sampling that is consistent across the network. Moreover, we propose prior noise remapping, through linear perturbation parameters encoded from paired references, to facilitate supervised training and exemplar-based instance style control at test time. Extensive experiments on multiple datasets show that our method can achieve superior diversity and comparable quality compared to state-of-the-art methods. Code will be available at \url{https://github.com/tzt101/INADE.git}

Zhentao Tan, Dongdong Chen, Qi Chu et al.

Spatially-adaptive normalization (SPADE) is remarkably successful recently in conditional semantic image synthesis \cite{park2019semantic}, which modulates the normalized activation with spatially-varying transformations learned from semantic layouts, to prevent the semantic information from being washed away. Despite its impressive performance, a more thorough understanding of the advantages inside the box is still highly demanded to help reduce the significant computation and parameter overhead introduced by this novel structure. In this paper, from a return-on-investment point of view, we conduct an in-depth analysis of the effectiveness of this spatially-adaptive normalization and observe that its modulation parameters benefit more from semantic-awareness rather than spatial-adaptiveness, especially for high-resolution input masks. Inspired by this observation, we propose class-adaptive normalization (CLADE), a lightweight but equally-effective variant that is only adaptive to semantic class. In order to further improve spatial-adaptiveness, we introduce intra-class positional map encoding calculated from semantic layouts to modulate the normalization parameters of CLADE and propose a truly spatially-adaptive variant of CLADE, namely CLADE-ICPE.Through extensive experiments on multiple challenging datasets, we demonstrate that the proposed CLADE can be generalized to different SPADE-based methods while achieving comparable generation quality compared to SPADE, but it is much more efficient with fewer extra parameters and lower computational cost. The code and pretrained models are available at \url{https://github.com/tzt101/CLADE.git}.

Zhentao Tan, Menglei Chai, Dongdong Chen et al.

Despite the recent success of face image generation with GANs, conditional hair editing remains challenging due to the under-explored complexity of its geometry and appearance. In this paper, we present MichiGAN (Multi-Input-Conditioned Hair Image GAN), a novel conditional image generation method for interactive portrait hair manipulation. To provide user control over every major hair visual factor, we explicitly disentangle hair into four orthogonal attributes, including shape, structure, appearance, and background. For each of them, we design a corresponding condition module to represent, process, and convert user inputs, and modulate the image generation pipeline in ways that respect the natures of different visual attributes. All these condition modules are integrated with the backbone generator to form the final end-to-end network, which allows fully-conditioned hair generation from multiple user inputs. Upon it, we also build an interactive portrait hair editing system that enables straightforward manipulation of hair by projecting intuitive and high-level user inputs such as painted masks, guiding strokes, or reference photos to well-defined condition representations. Through extensive experiments and evaluations, we demonstrate the superiority of our method regarding both result quality and user controllability. The code is available at https://github.com/tzt101/MichiGAN.

Zhen Wang, Qiangeng Xu, Feitong Tan et al.

Denoising diffusion models have demonstrated outstanding results in 2D image generation, yet it remains a challenge to replicate its success in 3D shape generation. In this paper, we propose leveraging multi-view depth, which represents complex 3D shapes in a 2D data format that is easy to denoise. We pair this representation with a diffusion model, MVDD, that is capable of generating high-quality dense point clouds with 20K+ points with fine-grained details. To enforce 3D consistency in multi-view depth, we introduce an epipolar line segment attention that conditions the denoising step for a view on its neighboring views. Additionally, a depth fusion module is incorporated into diffusion steps to further ensure the alignment of depth maps. When augmented with surface reconstruction, MVDD can also produce high-quality 3D meshes. Furthermore, MVDD stands out in other tasks such as depth completion, and can serve as a 3D prior, significantly boosting many downstream tasks, such as GAN inversion. State-of-the-art results from extensive experiments demonstrate MVDD's excellent ability in 3D shape generation, depth completion, and its potential as a 3D prior for downstream tasks.

Can Wang, Mingming He, Menglei Chai et al.

Neural implicit fields have emerged as a powerful 3D representation for reconstructing and rendering photo-realistic views, yet they possess limited editability. Conversely, explicit 3D representations, such as polygonal meshes, offer ease of editing but may not be as suitable for rendering high-quality novel views. To harness the strengths of both representations, we propose a new approach that employs a mesh as a guiding mechanism in editing the neural radiance field. We first introduce a differentiable method using marching tetrahedra for polygonal mesh extraction from the neural implicit field and then design a differentiable color extractor to assign colors obtained from the volume renderings to this extracted mesh. This differentiable colored mesh allows gradient back-propagation from the explicit mesh to the implicit fields, empowering users to easily manipulate the geometry and color of neural implicit fields. To enhance user control from coarse-grained to fine-grained levels, we introduce an octree-based structure into its optimization. This structure prioritizes the edited regions and the surface part, making our method achieve fine-grained edits to the neural implicit field and accommodate various user modifications, including object additions, component removals, specific area deformations, and adjustments to local and global colors. Through extensive experiments involving diverse scenes and editing operations, we have demonstrated the capabilities and effectiveness of our method. Our project page is: \url{https://cassiepython.github.io/MNeuEdit/}

Yang Zheng, Menglei Chai, Delio Vicini et al.

We present GroomLight, a novel method for relightable hair appearance modeling from multi-view images. Existing hair capture methods struggle to balance photorealistic rendering with relighting capabilities. Analytical material models, while physically grounded, often fail to fully capture appearance details. Conversely, neural rendering approaches excel at view synthesis but generalize poorly to novel lighting conditions. GroomLight addresses this challenge by combining the strengths of both paradigms. It employs an extended hair BSDF model to capture primary light transport and a light-aware residual model to reconstruct the remaining details. We further propose a hybrid inverse rendering pipeline to optimize both components, enabling high-fidelity relighting, view synthesis, and material editing. Extensive evaluations on real-world hair data demonstrate state-of-the-art performance of our method.

Armand Comas-Massagué, Di Qiu, Menglei Chai et al.

We introduce a novel framework for 3D human avatar generation and personalization, leveraging text prompts to enhance user engagement and customization. Central to our approach are key innovations aimed at overcoming the challenges in photo-realistic avatar synthesis. Firstly, we utilize a conditional Neural Radiance Fields (NeRF) model, trained on a large-scale unannotated multi-view dataset, to create a versatile initial solution space that accelerates and diversifies avatar generation. Secondly, we develop a geometric prior, leveraging the capabilities of Text-to-Image Diffusion Models, to ensure superior view invariance and enable direct optimization of avatar geometry. These foundational ideas are complemented by our optimization pipeline built on Variational Score Distillation (VSD), which mitigates texture loss and over-saturation issues. As supported by our extensive experiments, these strategies collectively enable the creation of custom avatars with unparalleled visual quality and better adherence to input text prompts. You can find more results and videos in our website: https://syntec-research.github.io/MagicMirror

Huan Wang, Jian Ren, Zeng Huang et al.

Recent research explosion on Neural Radiance Field (NeRF) shows the encouraging potential to represent complex scenes with neural networks. One major drawback of NeRF is its prohibitive inference time: Rendering a single pixel requires querying the NeRF network hundreds of times. To resolve it, existing efforts mainly attempt to reduce the number of required sampled points. However, the problem of iterative sampling still exists. On the other hand, Neural Light Field (NeLF) presents a more straightforward representation over NeRF in novel view synthesis -- the rendering of a pixel amounts to one single forward pass without ray-marching. In this work, we present a deep residual MLP network (88 layers) to effectively learn the light field. We show the key to successfully learning such a deep NeLF network is to have sufficient data, for which we transfer the knowledge from a pre-trained NeRF model via data distillation. Extensive experiments on both synthetic and real-world scenes show the merits of our method over other counterpart algorithms. On the synthetic scenes, we achieve 26-35x FLOPs reduction (per camera ray) and 28-31x runtime speedup, meanwhile delivering significantly better (1.4-2.8 dB average PSNR improvement) rendering quality than NeRF without any customized parallelism requirement.

Zhengfei Kuang, Kyle Olszewski, Menglei Chai et al.

We present a novel method to acquire object representations from online image collections, capturing high-quality geometry and material properties of arbitrary objects from photographs with varying cameras, illumination, and backgrounds. This enables various object-centric rendering applications such as novel-view synthesis, relighting, and harmonized background composition from challenging in-the-wild input. Using a multi-stage approach extending neural radiance fields, we first infer the surface geometry and refine the coarsely estimated initial camera parameters, while leveraging coarse foreground object masks to improve the training efficiency and geometry quality. We also introduce a robust normal estimation technique which eliminates the effect of geometric noise while retaining crucial details. Lastly, we extract surface material properties and ambient illumination, represented in spherical harmonics with extensions that handle transient elements, e.g. sharp shadows. The union of these components results in a highly modular and efficient object acquisition framework. Extensive evaluations and comparisons demonstrate the advantages of our approach in capturing high-quality geometry and appearance properties useful for rendering applications.

Sitao Xiang, Yuming Gu, Pengda Xiang et al.

Disentangling data into interpretable and independent factors is critical for controllable generation tasks. With the availability of labeled data, supervision can help enforce the separation of specific factors as expected. However, it is often expensive or even impossible to label every single factor to achieve fully-supervised disentanglement. In this paper, we adopt a general setting where all factors that are hard to label or identify are encapsulated as a single unknown factor. Under this setting, we propose a flexible weakly-supervised multi-factor disentanglement framework DisUnknown, which Distills Unknown factors for enabling multi-conditional generation regarding both labeled and unknown factors. Specifically, a two-stage training approach is adopted to first disentangle the unknown factor with an effective and robust training method, and then train the final generator with the proper disentanglement of all labeled factors utilizing the unknown distillation. To demonstrate the generalization capacity and scalability of our method, we evaluate it on multiple benchmark datasets qualitatively and quantitatively and further apply it to various real-world applications on complicated datasets.

Jian Ren, Menglei Chai, Oliver J. Woodford et al.

Human motion retargeting aims to transfer the motion of one person in a "driving" video or set of images to another person. Existing efforts leverage a long training video from each target person to train a subject-specific motion transfer model. However, the scalability of such methods is limited, as each model can only generate videos for the given target subject, and such training videos are labor-intensive to acquire and process. Few-shot motion transfer techniques, which only require one or a few images from a target, have recently drawn considerable attention. Methods addressing this task generally use either 2D or explicit 3D representations to transfer motion, and in doing so, sacrifice either accurate geometric modeling or the flexibility of an end-to-end learned representation. Inspired by the Transformable Bottleneck Network, which renders novel views and manipulations of rigid objects, we propose an approach based on an implicit volumetric representation of the image content, which can then be spatially manipulated using volumetric flow fields. We address the challenging question of how to aggregate information across different body poses, learning flow fields that allow for combining content from the appropriate regions of input images of highly non-rigid human subjects performing complex motions into a single implicit volumetric representation. This allows us to learn our 3D representation solely from videos of moving people. Armed with both 3D object understanding and end-to-end learned rendering, this categorically novel representation delivers state-of-the-art image generation quality, as shown by our quantitative and qualitative evaluations.

Fangzhou Han, Shuquan Ye, Mingming He et al.

Exemplar-based portrait stylization is widely attractive and highly desired. Despite recent successes, it remains challenging, especially when considering both texture and geometric styles. In this paper, we present the first framework for one-shot 3D portrait style transfer, which can generate 3D face models with both the geometry exaggerated and the texture stylized while preserving the identity from the original content. It requires only one arbitrary style image instead of a large set of training examples for a particular style, provides geometry and texture outputs that are fully parameterized and disentangled, and enables further graphics applications with the 3D representations. The framework consists of two stages. In the first geometric style transfer stage, we use facial landmark translation to capture the coarse geometry style and guide the deformation of the dense 3D face geometry. In the second texture style transfer stage, we focus on performing style transfer on the canonical texture by adopting a differentiable renderer to optimize the texture in a multi-view framework. Experiments show that our method achieves robustly good results on different artistic styles and outperforms existing methods. We also demonstrate the advantages of our method via various 2D and 3D graphics applications. Project page is https://halfjoe.github.io/projs/3DPS/index.html.

Aliaksandr Siarohin, Oliver J. Woodford, Jian Ren et al.

We propose novel motion representations for animating articulated objects consisting of distinct parts. In a completely unsupervised manner, our method identifies object parts, tracks them in a driving video, and infers their motions by considering their principal axes. In contrast to the previous keypoint-based works, our method extracts meaningful and consistent regions, describing locations, shape, and pose. The regions correspond to semantically relevant and distinct object parts, that are more easily detected in frames of the driving video. To force decoupling of foreground from background, we model non-object related global motion with an additional affine transformation. To facilitate animation and prevent the leakage of the shape of the driving object, we disentangle shape and pose of objects in the region space. Our model can animate a variety of objects, surpassing previous methods by a large margin on existing benchmarks. We present a challenging new benchmark with high-resolution videos and show that the improvement is particularly pronounced when articulated objects are considered, reaching 96.6% user preference vs. the state of the art.

Can Wang, Menglei Chai, Mingming He et al.

Face image manipulation via three-dimensional guidance has been widely applied in various interactive scenarios due to its semantically-meaningful understanding and user-friendly controllability. However, existing 3D-morphable-model-based manipulation methods are not directly applicable to out-of-domain faces, such as non-photorealistic paintings, cartoon portraits, or even animals, mainly due to the formidable difficulties in building the model for each specific face domain. To overcome this challenge, we propose, as far as we know, the first method to manipulate faces in arbitrary domains using human 3DMM. This is achieved through two major steps: 1) disentangled mapping from 3DMM parameters to the latent space embedding of a pre-trained StyleGAN2 that guarantees disentangled and precise controls for each semantic attribute; and 2) cross-domain adaptation that bridges domain discrepancies and makes human 3DMM applicable to out-of-domain faces by enforcing a consistent latent space embedding. Experiments and comparisons demonstrate the superiority of our high-quality semantic manipulation method on a variety of face domains with all major 3D facial attributes controllable-pose, expression, shape, albedo, and illumination. Moreover, we develop an intuitive editing interface to support user-friendly control and instant feedback. Our project page is https://cassiepython.github.io/cddfm3d/index.html

Ondřej Texler, David Futschik, Michal Kučera et al.

In this paper, we present a learning-based method to the keyframe-based video stylization that allows an artist to propagate the style from a few selected keyframes to the rest of the sequence. Its key advantage is that the resulting stylization is semantically meaningful, i.e., specific parts of moving objects are stylized according to the artist's intention. In contrast to previous style transfer techniques, our approach does not require any lengthy pre-training process nor a large training dataset. We demonstrate how to train an appearance translation network from scratch using only a few stylized exemplars while implicitly preserving temporal consistency. This leads to a video stylization framework that supports real-time inference, parallel processing, and random access to an arbitrary output frame. It can also merge the content from multiple keyframes without the need to perform an explicit blending operation. We demonstrate its practical utility in various interactive scenarios, where the user paints over a selected keyframe and sees her style transferred to an existing recorded sequence or a live video stream.

Menglei Chai, Jian Ren, Sergey Tulyakov

In this paper, we propose a generic neural-based hair rendering pipeline that can synthesize photo-realistic images from virtual 3D hair models. Unlike existing supervised translation methods that require model-level similarity to preserve consistent structure representation for both real images and fake renderings, our method adopts an unsupervised solution to work on arbitrary hair models. The key component of our method is a shared latent space to encode appearance-invariant structure information of both domains, which generates realistic renderings conditioned by extra appearance inputs. This is achieved by domain-specific pre-disentangled structure representation, partially shared domain encoder layers and a structure discriminator. We also propose a simple yet effective temporal conditioning method to enforce consistency for video sequence generation. We demonstrate the superiority of our method by testing it on a large number of portraits and comparing it with alternative baselines and state-of-the-art unsupervised image translation methods.

Jian Ren, Menglei Chai, Sergey Tulyakov et al.

In this paper, we tackle the problem of human motion transfer, where we synthesize novel motion video for a target person that imitates the movement from a reference video. It is a video-to-video translation task in which the estimated poses are used to bridge two domains. Despite substantial progress on the topic, there exist several problems with the previous methods. First, there is a domain gap between training and testing pose sequences--the model is tested on poses it has not seen during training, such as difficult dancing moves. Furthermore, pose detection errors are inevitable, making the job of the generator harder. Finally, generating realistic pixels from sparse poses is challenging in a single step. To address these challenges, we introduce a novel pose-to-video translation framework for generating high-quality videos that are temporally coherent even for in-the-wild pose sequences unseen during training. We propose a pose augmentation method to minimize the training-test gap, a unified paired and unpaired learning strategy to improve the robustness to detection errors, and two-stage network architecture to achieve superior texture quality. To further boost research on the topic, we build two human motion datasets. Finally, we show the superiority of our approach over the state-of-the-art studies through extensive experiments and evaluations on different datasets.

Zhentao Tan, Dongdong Chen, Qi Chu et al.

Spatially-adaptive normalization is remarkably successful recently in conditional semantic image synthesis, which modulates the normalized activation with spatially-varying transformations learned from semantic layouts, to preserve the semantic information from being washed away. Despite its impressive performance, a more thorough understanding of the true advantages inside the box is still highly demanded, to help reduce the significant computation and parameter overheads introduced by these new structures. In this paper, from a return-on-investment point of view, we present a deep analysis of the effectiveness of SPADE and observe that its advantages actually come mainly from its semantic-awareness rather than the spatial-adaptiveness. Inspired by this point, we propose class-adaptive normalization (CLADE), a lightweight variant that is not adaptive to spatial positions or layouts. Benefited from this design, CLADE greatly reduces the computation cost while still being able to preserve the semantic information during the generation. Extensive experiments on multiple challenging datasets demonstrate that while the resulting fidelity is on par with SPADE, its overhead is much cheaper than SPADE. Take the generator for ADE20k dataset as an example, the extra parameter and computation cost introduced by CLADE are only 4.57% and 0.07% while that of SPADE are 39.21% and 234.73% respectively.

Kekai Sheng, Weiming Dong, Menglei Chai et al.

Visual aesthetic assessment has been an active research field for decades. Although latest methods have achieved promising performance on benchmark datasets, they typically rely on a large number of manual annotations including both aesthetic labels and related image attributes. In this paper, we revisit the problem of image aesthetic assessment from the self-supervised feature learning perspective. Our motivation is that a suitable feature representation for image aesthetic assessment should be able to distinguish different expert-designed image manipulations, which have close relationships with negative aesthetic effects. To this end, we design two novel pretext tasks to identify the types and parameters of editing operations applied to synthetic instances. The features from our pretext tasks are then adapted for a one-layer linear classifier to evaluate the performance in terms of binary aesthetic classification. We conduct extensive quantitative experiments on three benchmark datasets and demonstrate that our approach can faithfully extract aesthetics-aware features and outperform alternative pretext schemes. Moreover, we achieve comparable results to state-of-the-art supervised methods that use 10 million labels from ImageNet.

Seonghyeon Nam, Chongyang Ma, Menglei Chai et al.

Time-lapse videos usually contain visually appealing content but are often difficult and costly to create. In this paper, we present an end-to-end solution to synthesize a time-lapse video from a single outdoor image using deep neural networks. Our key idea is to train a conditional generative adversarial network based on existing datasets of time-lapse videos and image sequences. We propose a multi-frame joint conditional generation framework to effectively learn the correlation between the illumination change of an outdoor scene and the time of the day. We further present a multi-domain training scheme for robust training of our generative models from two datasets with different distributions and missing timestamp labels. Compared to alternative time-lapse video synthesis algorithms, our method uses the timestamp as the control variable and does not require a reference video to guide the synthesis of the final output. We conduct ablation studies to validate our algorithm and compare with state-of-the-art techniques both qualitatively and quantitatively.