Jiaolong Yang

Daichi Horita, Jiaolong Yang, Dong Chen et al.

Image completion techniques have made significant progress in filling missing regions (i.e., holes) in images. However, large-hole completion remains challenging due to limited structural information. In this paper, we address this problem by integrating explicit structural guidance into diffusion-based image completion, forming our structure-guided diffusion model (SGDM). It consists of two cascaded diffusion probabilistic models: structure and texture generators. The structure generator generates an edge image representing plausible structures within the holes, which is then used for guiding the texture generation process. To train both generators jointly, we devise a novel strategy that leverages optimal Bayesian denoising, which denoises the output of the structure generator in a single step and thus allows backpropagation. Our diffusion-based approach enables a diversity of plausible completions, while the editable edges allow for editing parts of an image. Our experiments on natural scene (Places) and face (CelebA-HQ) datasets demonstrate that our method achieves a superior or comparable visual quality compared to state-of-the-art approaches. The code is available for research purposes at https://github.com/UdonDa/Structure_Guided_Diffusion_Model.

Hao Ouyang, Bo Zhang, Pan Zhang et al. · microsoft-research

We propose pose-guided multiplane image (MPI) synthesis which can render an animatable character in real scenes with photorealistic quality. We use a portable camera rig to capture the multi-view images along with the driving signal for the moving subject. Our method generalizes the image-to-image translation paradigm, which translates the human pose to a 3D scene representation -- MPIs that can be rendered in free viewpoints, using the multi-views captures as supervision. To fully cultivate the potential of MPI, we propose depth-adaptive MPI which can be learned using variable exposure images while being robust to inaccurate camera registration. Our method demonstrates advantageous novel-view synthesis quality over the state-of-the-art approaches for characters with challenging motions. Moreover, the proposed method is generalizable to novel combinations of training poses and can be explicitly controlled. Our method achieves such expressive and animatable character rendering all in real time, serving as a promising solution for practical applications.

Jianfeng Xiang, Jiaolong Yang, Yu Deng et al.

Recent works have shown that 3D-aware GANs trained on unstructured single image collections can generate multiview images of novel instances. The key underpinnings to achieve this are a 3D radiance field generator and a volume rendering process. However, existing methods either cannot generate high-resolution images (e.g., up to 256X256) due to the high computation cost of neural volume rendering, or rely on 2D CNNs for image-space upsampling which jeopardizes the 3D consistency across different views. This paper proposes a novel 3D-aware GAN that can generate high resolution images (up to 1024X1024) while keeping strict 3D consistency as in volume rendering. Our motivation is to achieve super-resolution directly in the 3D space to preserve 3D consistency. We avoid the otherwise prohibitively-expensive computation cost by applying 2D convolutions on a set of 2D radiance manifolds defined in the recent generative radiance manifold (GRAM) approach, and apply dedicated loss functions for effective GAN training at high resolution. Experiments on FFHQ and AFHQv2 datasets show that our method can produce high-quality 3D-consistent results that significantly outperform existing methods. It makes a significant step towards closing the gap between traditional 2D image generation and 3D-consistent free-view generation.

Yu Yin, Kamran Ghasedi, HsiangTao Wu et al.

Nerf-based Generative models have shown impressive capacity in generating high-quality images with consistent 3D geometry. Despite successful synthesis of fake identity images randomly sampled from latent space, adopting these models for generating face images of real subjects is still a challenging task due to its so-called inversion issue. In this paper, we propose a universal method to surgically fine-tune these NeRF-GAN models in order to achieve high-fidelity animation of real subjects only by a single image. Given the optimized latent code for an out-of-domain real image, we employ 2D loss functions on the rendered image to reduce the identity gap. Furthermore, our method leverages explicit and implicit 3D regularizations using the in-domain neighborhood samples around the optimized latent code to remove geometrical and visual artifacts. Our experiments confirm the effectiveness of our method in realistic, high-fidelity, and 3D consistent animation of real faces on multiple NeRF-GAN models across different datasets.

Yizhong Zhang, Zhiqi Li, Sicheng Xu et al.

Recent research advance has significantly improved the visual realism of immersive 3D video communication. In this work we present a method to further enhance this immersive experience by adding the hand touch capability ("remote hand clapping"). In our system, each meeting participant sits in front of a large screen with haptic feedback. The local participant can reach his hand out to the screen and perform hand clapping with the remote participant as if the two participants were only separated by a virtual glass. A key challenge in emulating the remote hand touch is the realistic rendering of the participant's hand and arm as the hand touches the screen. When the hand is very close to the screen, the RGBD data required for realistic rendering is no longer available. To tackle this challenge, we present a dual representation of the user's hand. Our dual representation not only preserves the high-quality rendering usually found in recent image-based rendering systems but also allows the hand to reach the screen. This is possible because the dual representation includes both an image-based model and a 3D geometry-based model, with the latter driven by a hand skeleton tracked by a side view camera. In addition, the dual representation provides a distance-based fusion of the image-based and 3D geometry-based models as the hand moves closer to the screen. The result is that the image-based and 3D geometry-based models mutually enhance each other, leading to realistic and seamless rendering. Our experiments demonstrate that our method provides consistent hand contact experience between remote users and improves the immersive experience of 3D video communication.

Yue Wu, Yu Deng, Jiaolong Yang et al.

Although 2D generative models have made great progress in face image generation and animation, they often suffer from undesirable artifacts such as 3D inconsistency when rendering images from different camera viewpoints. This prevents them from synthesizing video animations indistinguishable from real ones. Recently, 3D-aware GANs extend 2D GANs for explicit disentanglement of camera pose by leveraging 3D scene representations. These methods can well preserve the 3D consistency of the generated images across different views, yet they cannot achieve fine-grained control over other attributes, among which facial expression control is arguably the most useful and desirable for face animation. In this paper, we propose an animatable 3D-aware GAN for multiview consistent face animation generation. The key idea is to decompose the 3D representation of the 3D-aware GAN into a template field and a deformation field, where the former represents different identities with a canonical expression, and the latter characterizes expression variations of each identity. To achieve meaningful control over facial expressions via deformation, we propose a 3D-level imitative learning scheme between the generator and a parametric 3D face model during adversarial training of the 3D-aware GAN. This helps our method achieve high-quality animatable face image generation with strong visual 3D consistency, even though trained with only unstructured 2D images. Extensive experiments demonstrate our superior performance over prior works. Project page: https://yuewuhkust.github.io/AniFaceGAN

Yuxuan Han, Ruicheng Wang, Jiaolong Yang

This paper deals with the challenging task of synthesizing novel views for in-the-wild photographs. Existing methods have shown promising results leveraging monocular depth estimation and color inpainting with layered depth representations. However, these methods still have limited capability to handle scenes with complex 3D geometry. We propose a new method based on the multiplane image (MPI) representation. To accommodate diverse scene layouts in the wild and tackle the difficulty in producing high-dimensional MPI contents, we design a network structure that consists of two novel modules, one for plane depth adjustment and another for depth-aware color prediction. The former adjusts the initial plane positions using the RGBD context feature and an attention mechanism. Given adjusted depth values, the latter predicts the color and density for each plane separately with proper inter-plane interactions achieved via a feature masking strategy. To train our method, we construct large-scale stereo training data using only unconstrained single-view image collections by a simple yet effective warp-back strategy. The experiments on both synthetic and real datasets demonstrate that our trained model works remarkably well and achieves state-of-the-art results.

Jianfeng Xiang, Jiaolong Yang, Binbin Huang et al.

In this paper, we introduce a novel 3D-aware image generation method that leverages 2D diffusion models. We formulate the 3D-aware image generation task as multiview 2D image set generation, and further to a sequential unconditional-conditional multiview image generation process. This allows us to utilize 2D diffusion models to boost the generative modeling power of the method. Additionally, we incorporate depth information from monocular depth estimators to construct the training data for the conditional diffusion model using only still images. We train our method on a large-scale dataset, i.e., ImageNet, which is not addressed by previous methods. It produces high-quality images that significantly outperform prior methods. Furthermore, our approach showcases its capability to generate instances with large view angles, even though the training images are diverse and unaligned, gathered from "in-the-wild" real-world environments.

Ziyu Wang, Yu Deng, Jiaolong Yang et al.

3D-aware generative models have demonstrated their superb performance to generate 3D neural radiance fields (NeRF) from a collection of monocular 2D images even for topology-varying object categories. However, these methods still lack the capability to separately control the shape and appearance of the objects in the generated radiance fields. In this paper, we propose a generative model for synthesizing radiance fields of topology-varying objects with disentangled shape and appearance variations. Our method generates deformable radiance fields, which builds the dense correspondence between the density fields of the objects and encodes their appearances in a shared template field. Our disentanglement is achieved in an unsupervised manner without introducing extra labels to previous 3D-aware GAN training. We also develop an effective image inversion scheme for reconstructing the radiance field of an object in a real monocular image and manipulating its shape and appearance. Experiments show that our method can successfully learn the generative model from unstructured monocular images and well disentangle the shape and appearance for objects (e.g., chairs) with large topological variance. The model trained on synthetic data can faithfully reconstruct the real object in a given single image and achieve high-quality texture and shape editing results.

Yue Wu, Sicheng Xu, Jianfeng Xiang et al.

Previous animatable 3D-aware GANs for human generation have primarily focused on either the human head or full body. However, head-only videos are relatively uncommon in real life, and full body generation typically does not deal with facial expression control and still has challenges in generating high-quality results. Towards applicable video avatars, we present an animatable 3D-aware GAN that generates portrait images with controllable facial expression, head pose, and shoulder movements. It is a generative model trained on unstructured 2D image collections without using 3D or video data. For the new task, we base our method on the generative radiance manifold representation and equip it with learnable facial and head-shoulder deformations. A dual-camera rendering and adversarial learning scheme is proposed to improve the quality of the generated faces, which is critical for portrait images. A pose deformation processing network is developed to generate plausible deformations for challenging regions such as long hair. Experiments show that our method, trained on unstructured 2D images, can generate diverse and high-quality 3D portraits with desired control over different properties.

Yucheol Jung, Wonjong Jang, Soongjin Kim et al.

A 3D caricature is an exaggerated 3D depiction of a human face. The goal of this paper is to model the variations of 3D caricatures in a compact parameter space so that we can provide a useful data-driven toolkit for handling 3D caricature deformations. To achieve the goal, we propose an MLP-based framework for building a deformable surface model, which takes a latent code and produces a 3D surface. In the framework, a SIREN MLP models a function that takes a 3D position on a fixed template surface and returns a 3D displacement vector for the input position. We create variations of 3D surfaces by learning a hypernetwork that takes a latent code and produces the parameters of the MLP. Once learned, our deformable model provides a nice editing space for 3D caricatures, supporting label-based semantic editing and point-handle-based deformation, both of which produce highly exaggerated and natural 3D caricature shapes. We also demonstrate other applications of our deformable model, such as automatic 3D caricature creation.

Bowen Zhang, Yiji Cheng, Chunyu Wang et al.

We present RodinHD, which can generate high-fidelity 3D avatars from a portrait image. Existing methods fail to capture intricate details such as hairstyles which we tackle in this paper. We first identify an overlooked problem of catastrophic forgetting that arises when fitting triplanes sequentially on many avatars, caused by the MLP decoder sharing scheme. To overcome this issue, we raise a novel data scheduling strategy and a weight consolidation regularization term, which improves the decoder's capability of rendering sharper details. Additionally, we optimize the guiding effect of the portrait image by computing a finer-grained hierarchical representation that captures rich 2D texture cues, and injecting them to the 3D diffusion model at multiple layers via cross-attention. When trained on 46K avatars with a noise schedule optimized for triplanes, the resulting model can generate 3D avatars with notably better details than previous methods and can generalize to in-the-wild portrait input.

Yangyu Huang, Xi Chen, Jongyoo Kim et al.

Recent years have witnessed significant growth of face alignment. Though dense facial landmark is highly demanded in various scenarios, e.g., cosmetic medicine and facial beautification, most works only consider sparse face alignment. To address this problem, we present a framework that can enrich landmark density by existing sparse landmark datasets, e.g., 300W with 68 points and WFLW with 98 points. Firstly, we observe that the local patches along each semantic contour are highly similar in appearance. Then, we propose a weakly-supervised idea of learning the refinement ability on original sparse landmarks and adapting this ability to enriched dense landmarks. Meanwhile, several operators are devised and organized together to implement the idea. Finally, the trained model is applied as a plug-and-play module to the existing face alignment networks. To evaluate our method, we manually label the dense landmarks on 300W testset. Our method yields state-of-the-art accuracy not only in newly-constructed dense 300W testset but also in the original sparse 300W and WFLW testsets without additional cost.

Yin Yu, Ghasedi Kamran, Wu HsiangTao et al.

Recently, a surge of face editing techniques have been proposed to employ the pretrained StyleGAN for semantic manipulation. To successfully edit a real image, one must first convert the input image into StyleGAN's latent variables. However, it is still challenging to find latent variables, which have the capacity for preserving the appearance of the input subject (e.g., identity, lighting, hairstyles) as well as enabling meaningful manipulations. In this paper, we present a method to expand the latent space of StyleGAN with additional content features to break down the trade-off between low-distortion and high-editability. Specifically, we proposed a two-branch model, where the style branch first tackles the entanglement issue by the sparse manipulation of latent codes, and the content branch then mitigates the distortion issue by leveraging the content and appearance details from the input image. We confirm the effectiveness of our method using extensive qualitative and quantitative experiments on real face editing and reconstruction tasks.

Ronglai Zuo, Fangyun Wei, Zenggui Chen et al.

The objective of this paper is to develop a functional system for translating spoken languages into sign languages, referred to as Spoken2Sign translation. The Spoken2Sign task is orthogonal and complementary to traditional sign language to spoken language (Sign2Spoken) translation. To enable Spoken2Sign translation, we present a simple baseline consisting of three steps: 1) creating a gloss-video dictionary using existing Sign2Spoken benchmarks; 2) estimating a 3D sign for each sign video in the dictionary; 3) training a Spoken2Sign model, which is composed of a Text2Gloss translator, a sign connector, and a rendering module, with the aid of the yielded gloss-3D sign dictionary. The translation results are then displayed through a sign avatar. As far as we know, we are the first to present the Spoken2Sign task in an output format of 3D signs. In addition to its capability of Spoken2Sign translation, we also demonstrate that two by-products of our approach-3D keypoint augmentation and multi-view understanding-can assist in keypoint-based sign language understanding. Code and models are available at https://github.com/FangyunWei/SLRT.

Sicheng Xu, Guojun Chen, Jiaolong Yang et al.

We propose VASA-3D, an audio-driven, single-shot 3D head avatar generator. This research tackles two major challenges: capturing the subtle expression details present in real human faces, and reconstructing an intricate 3D head avatar from a single portrait image. To accurately model expression details, VASA-3D leverages the motion latent of VASA-1, a method that yields exceptional realism and vividness in 2D talking heads. A critical element of our work is translating this motion latent to 3D, which is accomplished by devising a 3D head model that is conditioned on the motion latent. Customization of this model to a single image is achieved through an optimization framework that employs numerous video frames of the reference head synthesized from the input image. The optimization takes various training losses robust to artifacts and limited pose coverage in the generated training data. Our experiment shows that VASA-3D produces realistic 3D talking heads that cannot be achieved by prior art, and it supports the online generation of 512x512 free-viewpoint videos at up to 75 FPS, facilitating more immersive engagements with lifelike 3D avatars.

Jianfeng Xiang, Xiaoxue Chen, Sicheng Xu et al.

Recent advancements in 3D generative modeling have significantly improved the generation realism, yet the field is still hampered by existing representations, which struggle to capture assets with complex topologies and detailed appearance. This paper present an approach for learning a structured latent representation from native 3D data to address this challenge. At its core is a new sparse voxel structure called O-Voxel, an omni-voxel representation that encodes both geometry and appearance. O-Voxel can robustly model arbitrary topology, including open, non-manifold, and fully-enclosed surfaces, while capturing comprehensive surface attributes beyond texture color, such as physically-based rendering parameters. Based on O-Voxel, we design a Sparse Compression VAE which provides a high spatial compression rate and a compact latent space. We train large-scale flow-matching models comprising 4B parameters for 3D generation using diverse public 3D asset datasets. Despite their scale, inference remains highly efficient. Meanwhile, the geometry and material quality of our generated assets far exceed those of existing models. We believe our approach offers a significant advancement in 3D generative modeling.

Jianfeng Xiang, Zelong Lv, Sicheng Xu et al.

We introduce a novel 3D generation method for versatile and high-quality 3D asset creation. The cornerstone is a unified Structured LATent (SLAT) representation which allows decoding to different output formats, such as Radiance Fields, 3D Gaussians, and meshes. This is achieved by integrating a sparsely-populated 3D grid with dense multiview visual features extracted from a powerful vision foundation model, comprehensively capturing both structural (geometry) and textural (appearance) information while maintaining flexibility during decoding. We employ rectified flow transformers tailored for SLAT as our 3D generation models and train models with up to 2 billion parameters on a large 3D asset dataset of 500K diverse objects. Our model generates high-quality results with text or image conditions, significantly surpassing existing methods, including recent ones at similar scales. We showcase flexible output format selection and local 3D editing capabilities which were not offered by previous models. Code, model, and data will be released.

Sicheng Xu, Guojun Chen, Yu-Xiao Guo et al.

We introduce VASA, a framework for generating lifelike talking faces with appealing visual affective skills (VAS) given a single static image and a speech audio clip. Our premiere model, VASA-1, is capable of not only generating lip movements that are exquisitely synchronized with the audio, but also producing a large spectrum of facial nuances and natural head motions that contribute to the perception of authenticity and liveliness. The core innovations include a holistic facial dynamics and head movement generation model that works in a face latent space, and the development of such an expressive and disentangled face latent space using videos. Through extensive experiments including evaluation on a set of new metrics, we show that our method significantly outperforms previous methods along various dimensions comprehensively. Our method not only delivers high video quality with realistic facial and head dynamics but also supports the online generation of 512x512 videos at up to 40 FPS with negligible starting latency. It paves the way for real-time engagements with lifelike avatars that emulate human conversational behaviors.

Qixiu Li, Yaobo Liang, Zeyu Wang et al.

The advancement of large Vision-Language-Action (VLA) models has significantly improved robotic manipulation in terms of language-guided task execution and generalization to unseen scenarios. While existing VLAs adapted from pretrained large Vision-Language-Models (VLM) have demonstrated promising generalizability, their task performance is still unsatisfactory as indicated by the low tasks success rates in different environments. In this paper, we present a new advanced VLA architecture derived from VLM. Unlike previous works that directly repurpose VLM for action prediction by simple action quantization, we propose a omponentized VLA architecture that has a specialized action module conditioned on VLM output. We systematically study the design of the action module and demonstrates the strong performance enhancement with diffusion action transformers for action sequence modeling, as well as their favorable scaling behaviors. We also conduct comprehensive experiments and ablation studies to evaluate the efficacy of our models with varied designs. The evaluation on 5 robot embodiments in simulation and real work shows that our model not only significantly surpasses existing VLAs in task performance and but also exhibits remarkable adaptation to new robots and generalization to unseen objects and backgrounds. It exceeds the average success rates of OpenVLA which has similar model size (7B) with ours by over 35% in simulated evaluation and 55% in real robot experiments. It also outperforms the large RT-2-X model (55B) by 18% absolute success rates in simulation. Code and models can be found on our project page (https://cogact.github.io/).

Zhiying Du, Bei Liu, Yaobo Liang et al.

The development of foundation models for embodied intelligence critically depends on access to large-scale, high-quality robot demonstration data. Recent approaches have sought to address this challenge by training on large collections of heterogeneous robotic datasets. However, unlike vision or language data, robotic demonstrations exhibit substantial heterogeneity across embodiments and action spaces as well as other prominent variations such as senor configurations and action control frequencies. The lack of explicit designs for handling such heterogeneity causes existing methods to struggle with integrating diverse factors, thereby limiting their generalization and leading to degraded performance when transferred to new settings. In this paper, we present HiMoE-VLA, a novel vision-language-action (VLA) framework tailored to effectively handle diverse robotic data with heterogeneity. Specifically, we introduce a Hierarchical Mixture-of-Experts (HiMoE) architecture for the action module which adaptively handles multiple sources of heterogeneity across layers and gradually abstracts them into shared knowledge representations. Through extensive experimentation with simulation benchmarks and real-world robotic platforms, HiMoE-VLA demonstrates a consistent performance boost over existing VLA baselines, achieving higher accuracy and robust generalization across diverse robots and action spaces. The code and models are publicly available at https://github.com/ZhiyingDu/HiMoE-VLA.

Zhiyuan Feng, Zhaolu Kang, Qijie Wang et al.

Vision-language models (VLMs) are essential to Embodied AI, enabling robots to perceive, reason, and act in complex environments. They also serve as the foundation for the recent Vision-Language-Action (VLA) models. Yet most evaluations of VLMs focus on single-view settings, leaving their ability to integrate multi-view information underexplored. At the same time, multi-camera setups are increasingly standard in robotic platforms, as they provide complementary perspectives to mitigate occlusion and depth ambiguity. Whether VLMs can effectively leverage such multi-view inputs for robotic reasoning therefore remains an open question. To bridge this gap, we introduce MV-RoboBench, a benchmark specifically designed to evaluate the multi-view spatial reasoning capabilities of VLMs in robotic manipulation. MV-RoboBench consists of 1.7k manually curated QA items across eight subtasks, divided into two primary categories: spatial understanding and robotic execution. We evaluate a diverse set of existing VLMs, including both open-source and closed-source models, along with enhanced versions incorporating CoT-inspired techniques. The results show that state-of-the-art models remain far below human performance, underscoring the substantial challenges VLMs face in multi-view robotic perception. Additionally, our analysis uncovers two key findings: (i) spatial intelligence and robotic task execution are positively correlated in multi-view robotic scenarios; and (ii) strong performance on existing general-purpose single-view spatial understanding benchmarks does not reliably translate to success in the robotic spatial tasks assessed by our benchmark. We release MV-RoboBench as an open resource to foster progress in spatially grounded VLMs and VLAs, providing not only data but also a standardized evaluation protocol for multi-view embodied reasoning.

Ruicheng Wang, Sicheng Xu, Cassie Dai et al.

We present MoGe, a powerful model for recovering 3D geometry from monocular open-domain images. Given a single image, our model directly predicts a 3D point map of the captured scene with an affine-invariant representation, which is agnostic to true global scale and shift. This new representation precludes ambiguous supervision in training and facilitate effective geometry learning. Furthermore, we propose a set of novel global and local geometry supervisions that empower the model to learn high-quality geometry. These include a robust, optimal, and efficient point cloud alignment solver for accurate global shape learning, and a multi-scale local geometry loss promoting precise local geometry supervision. We train our model on a large, mixed dataset and demonstrate its strong generalizability and high accuracy. In our comprehensive evaluation on diverse unseen datasets, our model significantly outperforms state-of-the-art methods across all tasks, including monocular estimation of 3D point map, depth map, and camera field of view. Code and models can be found on our project page.

Yuxuan Han, Jiaolong Yang, Ying Fu

Recent works have shown that a rich set of semantic directions exist in the latent space of Generative Adversarial Networks (GANs), which enables various facial attribute editing applications. However, existing methods may suffer poor attribute variation disentanglement, leading to unwanted change of other attributes when altering the desired one. The semantic directions used by existing methods are at attribute level, which are difficult to model complex attribute correlations, especially in the presence of attribute distribution bias in GAN's training set. In this paper, we propose a novel framework (IALS) that performs Instance-Aware Latent-Space Search to find semantic directions for disentangled attribute editing. The instance information is injected by leveraging the supervision from a set of attribute classifiers evaluated on the input images. We further propose a Disentanglement-Transformation (DT) metric to quantify the attribute transformation and disentanglement efficacy and find the optimal control factor between attribute-level and instance-specific directions based on it. Experimental results on both GAN-generated and real-world images collectively show that our method outperforms state-of-the-art methods proposed recently by a wide margin. Code is available at https://github.com/yxuhan/IALS.

Haofei Xu, Jiaolong Yang, Jianfei Cai et al.

Optical flow is inherently a 2D search problem, and thus the computational complexity grows quadratically with respect to the search window, making large displacements matching infeasible for high-resolution images. In this paper, we take inspiration from Transformers and propose a new method for high-resolution optical flow estimation with significantly less computation. Specifically, a 1D attention operation is first applied in the vertical direction of the target image, and then a simple 1D correlation in the horizontal direction of the attended image is able to achieve 2D correspondence modeling effect. The directions of attention and correlation can also be exchanged, resulting in two 3D cost volumes that are concatenated for optical flow estimation. The novel 1D formulation empowers our method to scale to very high-resolution input images while maintaining competitive performance. Extensive experiments on Sintel, KITTI and real-world 4K ($2160 \times 3840$) resolution images demonstrated the effectiveness and superiority of our proposed method. Code and models are available at \url{https://github.com/haofeixu/flow1d}.

Qingnan Fan, Jiaolong Yang, David Wipf et al.

Image smoothing represents a fundamental component of many disparate computer vision and graphics applications. In this paper, we present a unified unsupervised (label-free) learning framework that facilitates generating flexible and high-quality smoothing effects by directly learning from data using deep convolutional neural networks (CNNs). The heart of the design is the training signal as a novel energy function that includes an edge-preserving regularizer which helps maintain important yet potentially vulnerable image structures, and a spatially-adaptive Lp flattening criterion which imposes different forms of regularization onto different image regions for better smoothing quality. We implement a diverse set of image smoothing solutions employing the unified framework targeting various applications such as, image abstraction, pencil sketching, detail enhancement, texture removal and content-aware image manipulation, and obtain results comparable with or better than previous methods. Moreover, our method is extremely fast with a modern GPU (e.g, 200 fps for 1280x720 images). Our codes and model are released in https://github.com/fqnchina/ImageSmoothing.

Dongqing Zhang, Jiaolong Yang, Dongqiangzi Ye et al.

Although weight and activation quantization is an effective approach for Deep Neural Network (DNN) compression and has a lot of potentials to increase inference speed leveraging bit-operations, there is still a noticeable gap in terms of prediction accuracy between the quantized model and the full-precision model. To address this gap, we propose to jointly train a quantized, bit-operation-compatible DNN and its associated quantizers, as opposed to using fixed, handcrafted quantization schemes such as uniform or logarithmic quantization. Our method for learning the quantizers applies to both network weights and activations with arbitrary-bit precision, and our quantizers are easy to train. The comprehensive experiments on CIFAR-10 and ImageNet datasets show that our method works consistently well for various network structures such as AlexNet, VGG-Net, GoogLeNet, ResNet, and DenseNet, surpassing previous quantization methods in terms of accuracy by an appreciable margin. Code available at https://github.com/Microsoft/LQ-Nets

Shuyu Lei, Lingen Liu, Jiaolong Yang et al.

Existing auto-regressive language models have demonstrated a remarkable capability to perform a new task with just a few examples in prompt, without requiring any additional training. In order to extend this capability to a multi-modal setting (i.e. speech and language), this paper introduces the Seal model, an abbreviation for speech language model. It incorporates a novel alignment method, in which Kullback-Leibler divergence loss is performed to train a projector that bridges a frozen speech encoder with a frozen language model decoder. The resulting Seal model exhibits robust performance as a few-shot learner on two speech understanding tasks. Additionally, consistency experiments are conducted to validate its robustness on different pre-trained language models.

Sunghwan Hong, Jaewoo Jung, Heeseong Shin et al.

We consider the problem of novel view synthesis from unposed images in a single feed-forward. Our framework capitalizes on fast speed, scalability, and high-quality 3D reconstruction and view synthesis capabilities of 3DGS, where we further extend it to offer a practical solution that relaxes common assumptions such as dense image views, accurate camera poses, and substantial image overlaps. We achieve this through identifying and addressing unique challenges arising from the use of pixel-aligned 3DGS: misaligned 3D Gaussians across different views induce noisy or sparse gradients that destabilize training and hinder convergence, especially when above assumptions are not met. To mitigate this, we employ pre-trained monocular depth estimation and visual correspondence models to achieve coarse alignments of 3D Gaussians. We then introduce lightweight, learnable modules to refine depth and pose estimates from the coarse alignments, improving the quality of 3D reconstruction and novel view synthesis. Furthermore, the refined estimates are leveraged to estimate geometry confidence scores, which assess the reliability of 3D Gaussian centers and condition the prediction of Gaussian parameters accordingly. Extensive evaluations on large-scale real-world datasets demonstrate that PF3plat sets a new state-of-the-art across all benchmarks, supported by comprehensive ablation studies validating our design choices. project page: https://cvlab-kaist.github.io/PF3plat/

Sunghwan Hong, Jaewoo Jung, Heeseong Shin et al.

This work delves into the task of pose-free novel view synthesis from stereo pairs, a challenging and pioneering task in 3D vision. Our innovative framework, unlike any before, seamlessly integrates 2D correspondence matching, camera pose estimation, and NeRF rendering, fostering a synergistic enhancement of these tasks. We achieve this through designing an architecture that utilizes a shared representation, which serves as a foundation for enhanced 3D geometry understanding. Capitalizing on the inherent interplay between the tasks, our unified framework is trained end-to-end with the proposed training strategy to improve overall model accuracy. Through extensive evaluations across diverse indoor and outdoor scenes from two real-world datasets, we demonstrate that our approach achieves substantial improvement over previous methodologies, especially in scenarios characterized by extreme viewpoint changes and the absence of accurate camera poses.

Changhao Wang, Yunfei Yu, Xinhao Yao et al.

The scaling of Large Language Models (LLMs) is increasingly limited by data quality. Most methods handle data mixing and sample selection separately, which can break the structure in code corpora. We introduce \textbf{UniGeM}, a framework that unifies mixing and selection by treating data curation as a \textit{manifold approximation} problem without training proxy models or relying on external reference datasets. UniGeM operates hierarchically: \textbf{Macro-Exploration} learns mixing weights with stability-based clustering; \textbf{Micro-Mining} filters high-quality instances by their geometric distribution to ensure logical consistency. Validated by training 8B and 16B MoE models on 100B tokens, UniGeM achieves \textbf{2.0$\times$ data efficiency} over a random baseline and further improves overall performance compared to SOTA methods in reasoning-heavy evaluations and multilingual generalization.

Bowen Zhang, Yiji Cheng, Jiaolong Yang et al.

We introduce a radiance representation that is both structured and fully explicit and thus greatly facilitates 3D generative modeling. Existing radiance representations either require an implicit feature decoder, which significantly degrades the modeling power of the representation, or are spatially unstructured, making them difficult to integrate with mainstream 3D diffusion methods. We derive GaussianCube by first using a novel densification-constrained Gaussian fitting algorithm, which yields high-accuracy fitting using a fixed number of free Gaussians, and then rearranging these Gaussians into a predefined voxel grid via Optimal Transport. Since GaussianCube is a structured grid representation, it allows us to use standard 3D U-Net as our backbone in diffusion modeling without elaborate designs. More importantly, the high-accuracy fitting of the Gaussians allows us to achieve a high-quality representation with orders of magnitude fewer parameters than previous structured representations for comparable quality, ranging from one to two orders of magnitude. The compactness of GaussianCube greatly eases the difficulty of 3D generative modeling. Extensive experiments conducted on unconditional and class-conditioned object generation, digital avatar creation, and text-to-3D synthesis all show that our model achieves state-of-the-art generation results both qualitatively and quantitatively, underscoring the potential of GaussianCube as a highly accurate and versatile radiance representation for 3D generative modeling. Project page: https://gaussiancube.github.io/.

Ruicheng Wang, Jianfeng Xiang, Jiaolong Yang et al.

We propose a novel image editing technique that enables 3D manipulations on single images, such as object rotation and translation. Existing 3D-aware image editing approaches typically rely on synthetic multi-view datasets for training specialized models, thus constraining their effectiveness on open-domain images featuring significantly more varied layouts and styles. In contrast, our method directly leverages powerful image diffusion models trained on a broad spectrum of text-image pairs and thus retain their exceptional generalization abilities. This objective is realized through the development of an iterative novel view synthesis and geometry alignment algorithm. The algorithm harnesses diffusion models for dual purposes: they provide appearance prior by predicting novel views of the selected object using estimated depth maps, and they act as a geometry critic by correcting misalignments in 3D shapes across the sampled views. Our method can generate high-quality 3D-aware image edits with large viewpoint transformations and high appearance and shape consistency with the input image, pushing the boundaries of what is possible with single-image 3D-aware editing.

Bowen Zhang, Sicheng Xu, Chuxin Wang et al.

In this paper, we present a novel framework for video-to-4D generation that creates high-quality dynamic 3D content from single video inputs. Direct 4D diffusion modeling is extremely challenging due to costly data construction and the high-dimensional nature of jointly representing 3D shape, appearance, and motion. We address these challenges by introducing a Direct 4DMesh-to-GS Variation Field VAE that directly encodes canonical Gaussian Splats (GS) and their temporal variations from 3D animation data without per-instance fitting, and compresses high-dimensional animations into a compact latent space. Building upon this efficient representation, we train a Gaussian Variation Field diffusion model with temporal-aware Diffusion Transformer conditioned on input videos and canonical GS. Trained on carefully-curated animatable 3D objects from the Objaverse dataset, our model demonstrates superior generation quality compared to existing methods. It also exhibits remarkable generalization to in-the-wild video inputs despite being trained exclusively on synthetic data, paving the way for generating high-quality animated 3D content. Project page: https://gvfdiffusion.github.io/.

Qixiu Li, Yu Deng, Yaobo Liang et al.

This paper presents a novel approach for pretraining robotic manipulation Vision-Language-Action (VLA) models using a large corpus of unscripted real-life video recordings of human hand activities. Treating human hand as dexterous robot end-effector, we show that "in-the-wild" egocentric human videos without any annotations can be transformed into data formats fully aligned with existing robotic V-L-A training data in terms of task granularity and labels. This is achieved by the development of a fully-automated holistic human activity analysis approach for arbitrary human hand videos. This approach can generate atomic-level hand activity segments and their language descriptions, each accompanied with framewise 3D hand motion and camera motion. We process a large volume of egocentric videos and create a hand-VLA training dataset containing 1M episodes and 26M frames. This training data covers a wide range of objects and concepts, dexterous manipulation tasks, and environment variations in real life, vastly exceeding the coverage of existing robot data. We design a dexterous hand VLA model architecture and pretrain the model on this dataset. The model exhibits strong zero-shot capabilities on completely unseen real-world observations. Additionally, fine-tuning it on a small amount of real robot action data significantly improves task success rates and generalization to novel objects in real robotic experiments. We also demonstrate the appealing scaling behavior of the model's task performance with respect to pretraining data scale. We believe this work lays a solid foundation for scalable VLA pretraining, advancing robots toward truly generalizable embodied intelligence.

Xiangjun Gao, Jiaolong Yang, Jongyoo Kim et al.

There has been rapid progress recently on 3D human rendering, including novel view synthesis and pose animation, based on the advances of neural radiance fields (NeRF). However, most existing methods focus on person-specific training and their training typically requires multi-view videos. This paper deals with a new challenging task -- rendering novel views and novel poses for a person unseen in training, using only multiview images as input. For this task, we propose a simple yet effective method to train a generalizable NeRF with multiview images as conditional input. The key ingredient is a dedicated representation combining a canonical NeRF and a volume deformation scheme. Using a canonical space enables our method to learn shared properties of human and easily generalize to different people. Volume deformation is used to connect the canonical space with input and target images and query image features for radiance and density prediction. We leverage the parametric 3D human model fitted on the input images to derive the deformation, which works quite well in practice when combined with our canonical NeRF. The experiments on both real and synthetic data with the novel view synthesis and pose animation tasks collectively demonstrate the efficacy of our method.

Yu Deng, Jiaolong Yang, Jianfeng Xiang et al.

3D-aware image generative modeling aims to generate 3D-consistent images with explicitly controllable camera poses. Recent works have shown promising results by training neural radiance field (NeRF) generators on unstructured 2D images, but still can not generate highly-realistic images with fine details. A critical reason is that the high memory and computation cost of volumetric representation learning greatly restricts the number of point samples for radiance integration during training. Deficient sampling not only limits the expressive power of the generator to handle fine details but also impedes effective GAN training due to the noise caused by unstable Monte Carlo sampling. We propose a novel approach that regulates point sampling and radiance field learning on 2D manifolds, embodied as a set of learned implicit surfaces in the 3D volume. For each viewing ray, we calculate ray-surface intersections and accumulate their radiance generated by the network. By training and rendering such radiance manifolds, our generator can produce high quality images with realistic fine details and strong visual 3D consistency.

Yizhong Zhang, Jiaolong Yang, Zhen Liu et al.

The VirtualCube system is a 3D video conference system that attempts to overcome some limitations of conventional technologies. The key ingredient is VirtualCube, an abstract representation of a real-world cubicle instrumented with RGBD cameras for capturing the 3D geometry and texture of a user. We design VirtualCube so that the task of data capturing is standardized and significantly simplified, and everything can be built using off-the-shelf hardware. We use VirtualCubes as the basic building blocks of a virtual conferencing environment, and we provide each VirtualCube user with a surrounding display showing life-size videos of remote participants. To achieve real-time rendering of remote participants, we develop the V-Cube View algorithm, which uses multi-view stereo for more accurate depth estimation and Lumi-Net rendering for better rendering quality. The VirtualCube system correctly preserves the mutual eye gaze between participants, allowing them to establish eye contact and be aware of who is visually paying attention to them. The system also allows a participant to have side discussions with remote participants as if they were in the same room. Finally, the system sheds lights on how to support the shared space of work items (e.g., documents and applications) and track the visual attention of participants to work items.

Kaixuan Wei, Ying Fu, Yinqiang Zheng et al.

Enhancing the visibility in extreme low-light environments is a challenging task. Under nearly lightless condition, existing image denoising methods could easily break down due to significantly low SNR. In this paper, we systematically study the noise statistics in the imaging pipeline of CMOS photosensors, and formulate a comprehensive noise model that can accurately characterize the real noise structures. Our novel model considers the noise sources caused by digital camera electronics which are largely overlooked by existing methods yet have significant influence on raw measurement in the dark. It provides a way to decouple the intricate noise structure into different statistical distributions with physical interpretations. Moreover, our noise model can be used to synthesize realistic training data for learning-based low-light denoising algorithms. In this regard, although promising results have been shown recently with deep convolutional neural networks, the success heavily depends on abundant noisy clean image pairs for training, which are tremendously difficult to obtain in practice. Generalizing their trained models to images from new devices is also problematic. Extensive experiments on multiple low-light denoising datasets -- including a newly collected one in this work covering various devices -- show that a deep neural network trained with our proposed noise formation model can reach surprisingly-high accuracy. The results are on par with or sometimes even outperform training with paired real data, opening a new door to real-world extreme low-light photography.

Wonjong Jang, Gwangjin Ju, Yucheol Jung et al.

We present a caricature generation framework based on shape and style manipulation using StyleGAN. Our framework, dubbed StyleCariGAN, automatically creates a realistic and detailed caricature from an input photo with optional controls on shape exaggeration degree and color stylization type. The key component of our method is shape exaggeration blocks that are used for modulating coarse layer feature maps of StyleGAN to produce desirable caricature shape exaggerations. We first build a layer-mixed StyleGAN for photo-to-caricature style conversion by swapping fine layers of the StyleGAN for photos to the corresponding layers of the StyleGAN trained to generate caricatures. Given an input photo, the layer-mixed model produces detailed color stylization for a caricature but without shape exaggerations. We then append shape exaggeration blocks to the coarse layers of the layer-mixed model and train the blocks to create shape exaggerations while preserving the characteristic appearances of the input. Experimental results show that our StyleCariGAN generates realistic and detailed caricatures compared to the current state-of-the-art methods. We demonstrate StyleCariGAN also supports other StyleGAN-based image manipulations, such as facial expression control.

Yu Deng, Jiaolong Yang, Xin Tong

We propose a novel Deformed Implicit Field (DIF) representation for modeling 3D shapes of a category and generating dense correspondences among shapes. With DIF, a 3D shape is represented by a template implicit field shared across the category, together with a 3D deformation field and a correction field dedicated for each shape instance. Shape correspondences can be easily established using their deformation fields. Our neural network, dubbed DIF-Net, jointly learns a shape latent space and these fields for 3D objects belonging to a category without using any correspondence or part label. The learned DIF-Net can also provides reliable correspondence uncertainty measurement reflecting shape structure discrepancy. Experiments show that DIF-Net not only produces high-fidelity 3D shapes but also builds high-quality dense correspondences across different shapes. We also demonstrate several applications such as texture transfer and shape editing, where our method achieves compelling results that cannot be achieved by previous methods.

Yu Deng, Jiaolong Yang, Dong Chen et al.

We propose DiscoFaceGAN, an approach for face image generation of virtual people with disentangled, precisely-controllable latent representations for identity of non-existing people, expression, pose, and illumination. We embed 3D priors into adversarial learning and train the network to imitate the image formation of an analytic 3D face deformation and rendering process. To deal with the generation freedom induced by the domain gap between real and rendered faces, we further introduce contrastive learning to promote disentanglement by comparing pairs of generated images. Experiments show that through our imitative-contrastive learning, the factor variations are very well disentangled and the properties of a generated face can be precisely controlled. We also analyze the learned latent space and present several meaningful properties supporting factor disentanglement. Our method can also be used to embed real images into the disentangled latent space. We hope our method could provide new understandings of the relationship between physical properties and deep image synthesis.

Sicheng Xu, Jiaolong Yang, Dong Chen et al.

In this paper, we present a learning-based approach for recovering the 3D geometry of human head from a single portrait image. Our method is learned in an unsupervised manner without any ground-truth 3D data. We represent the head geometry with a parametric 3D face model together with a depth map for other head regions including hair and ear. A two-step geometry learning scheme is proposed to learn 3D head reconstruction from in-the-wild face images, where we first learn face shape on single images using self-reconstruction and then learn hair and ear geometry using pairs of images in a stereo-matching fashion. The second step is based on the output of the first to not only improve the accuracy but also ensure the consistency of overall head geometry. We evaluate the accuracy of our method both in 3D and with pose manipulation tasks on 2D images. We alter pose based on the recovered geometry and apply a refinement network trained with adversarial learning to ameliorate the reprojected images and translate them to the real image domain. Extensive evaluations and comparison with previous methods show that our new method can produce high-fidelity 3D head geometry and head pose manipulation results.

Kaixuan Wei, Ying Fu, Jiaolong Yang et al.

Lacking rich and realistic data, learned single image denoising algorithms generalize poorly to real raw images that do not resemble the data used for training. Although the problem can be alleviated by the heteroscedastic Gaussian model for noise synthesis, the noise sources caused by digital camera electronics are still largely overlooked, despite their significant effect on raw measurement, especially under extremely low-light condition. To address this issue, we present a highly accurate noise formation model based on the characteristics of CMOS photosensors, thereby enabling us to synthesize realistic samples that better match the physics of image formation process. Given the proposed noise model, we additionally propose a method to calibrate the noise parameters for available modern digital cameras, which is simple and reproducible for any new device. We systematically study the generalizability of a neural network trained with existing schemes, by introducing a new low-light denoising dataset that covers many modern digital cameras from diverse brands. Extensive empirical results collectively show that by utilizing our proposed noise formation model, a network can reach the capability as if it had been trained with rich real data, which demonstrates the effectiveness of our noise formation model.

Kaixuan Wei, Jiaolong Yang, Ying Fu et al.

Removing undesirable reflections from a single image captured through a glass window is of practical importance to visual computing systems. Although state-of-the-art methods can obtain decent results in certain situations, performance declines significantly when tackling more general real-world cases. These failures stem from the intrinsic difficulty of single image reflection removal -- the fundamental ill-posedness of the problem, and the insufficiency of densely-labeled training data needed for resolving this ambiguity within learning-based neural network pipelines. In this paper, we address these issues by exploiting targeted network enhancements and the novel use of misaligned data. For the former, we augment a baseline network architecture by embedding context encoding modules that are capable of leveraging high-level contextual clues to reduce indeterminacy within areas containing strong reflections. For the latter, we introduce an alignment-invariant loss function that facilitates exploiting misaligned real-world training data that is much easier to collect. Experimental results collectively show that our method outperforms the state-of-the-art with aligned data, and that significant improvements are possible when using additional misaligned data.

Yu Deng, Jiaolong Yang, Sicheng Xu et al.

Recently, deep learning based 3D face reconstruction methods have shown promising results in both quality and efficiency.However, training deep neural networks typically requires a large volume of data, whereas face images with ground-truth 3D face shapes are scarce. In this paper, we propose a novel deep 3D face reconstruction approach that 1) leverages a robust, hybrid loss function for weakly-supervised learning which takes into account both low-level and perception-level information for supervision, and 2) performs multi-image face reconstruction by exploiting complementary information from different images for shape aggregation. Our method is fast, accurate, and robust to occlusion and large pose. We provide comprehensive experiments on three datasets, systematically comparing our method with fifteen recent methods and demonstrating its state-of-the-art performance.

Hanqing Wang, Jiaolong Yang, Wei Liang et al.

3D object reconstruction is a fundamental task of many robotics and AI problems. With the aid of deep convolutional neural networks (CNNs), 3D object reconstruction has witnessed a significant progress in recent years. However, possibly due to the prohibitively high dimension of the 3D object space, the results from deep CNNs are often prone to missing some shape details. In this paper, we present an approach which aims to preserve more shape details and improve the reconstruction quality. The key idea of our method is to leverage object mask and pose estimation from CNNs to assist the 3D shape learning by constructing a probabilistic single-view visual hull inside of the network. Our method works by first predicting a coarse shape as well as the object pose and silhouette using CNNs, followed by a novel 3D refinement CNN which refines the coarse shapes using the constructed probabilistic visual hulls. Experiment on both synthetic data and real images show that embedding a single-view visual hull for shape refinement can significantly improve the reconstruction quality by recovering more shapes details and improving shape consistency with the input image.

Chen Zhou, Jiaolong Yang, Chunshui Zhao et al.

Safety is paramount for mobile robotic platforms such as self-driving cars and unmanned aerial vehicles. This work is devoted to a task that is indispensable for safety yet was largely overlooked in the past -- detecting obstacles that are of very thin structures, such as wires, cables and tree branches. This is a challenging problem, as thin objects can be problematic for active sensors such as lidar and sonar and even for stereo cameras. In this work, we propose to use video sequences for thin obstacle detection. We represent obstacles with edges in the video frames, and reconstruct them in 3D using efficient edge-based visual odometry techniques. We provide both a monocular camera solution and a stereo camera solution. The former incorporates Inertial Measurement Unit (IMU) data to solve scale ambiguity, while the latter enjoys a novel, purely vision-based solution. Experiments demonstrated that the proposed methods are fast and able to detect thin obstacles robustly and accurately under various conditions.

Qingnan Fan, Jiaolong Yang, Gang Hua et al.

This paper proposes a deep neural network structure that exploits edge information in addressing representative low-level vision tasks such as layer separation and image filtering. Unlike most other deep learning strategies applied in this context, our approach tackles these challenging problems by estimating edges and reconstructing images using only cascaded convolutional layers arranged such that no handcrafted or application-specific image-processing components are required. We apply the resulting transferrable pipeline to two different problem domains that are both sensitive to edges, namely, single image reflection removal and image smoothing. For the former, using a mild reflection smoothness assumption and a novel synthetic data generation method that acts as a type of weak supervision, our network is able to solve much more difficult reflection cases that cannot be handled by previous methods. For the latter, we also exceed the state-of-the-art quantitative and qualitative results by wide margins. In all cases, the proposed framework is simple, fast, and easy to transfer across disparate domains.

Qingnan Fan, Jiaolong Yang, Gang Hua et al.

While invaluable for many computer vision applications, decomposing a natural image into intrinsic reflectance and shading layers represents a challenging, underdetermined inverse problem. As opposed to strict reliance on conventional optimization or filtering solutions with strong prior assumptions, deep learning based approaches have also been proposed to compute intrinsic image decompositions when granted access to sufficient labeled training data. The downside is that current data sources are quite limited, and broadly speaking fall into one of two categories: either dense fully-labeled images in synthetic/narrow settings, or weakly-labeled data from relatively diverse natural scenes. In contrast to many previous learning-based approaches, which are often tailored to the structure of a particular dataset (and may not work well on others), we adopt core network structures that universally reflect loose prior knowledge regarding the intrinsic image formation process and can be largely shared across datasets. We then apply flexibly supervised loss layers that are customized for each source of ground truth labels. The resulting deep architecture achieves state-of-the-art results on all of the major intrinsic image benchmarks, and runs considerably faster than most at test time.