Fangneng Zhan

Hansen Jin Lillemark, Benhao Huang, Fangneng Zhan et al. · cmu

Embodied systems experience the world as 'a symphony of flows': a combination of many continuous streams of sensory input coupled to self-motion, interwoven with the dynamics of external objects. These sensory streams and the underlying dynamics of the world obey smooth, time-parameterized symmetries which existing world models ignore. Without a memory that respects this structure, partial observability presents a major obstacle to existing methods: each observation reveals only a fraction of the world, while unobserved regions continue to evolve. In this work, we introduce Flow Equivariant World Modeling, a framework that leverages time-parameterized symmetries within a latent memory for stable and accurate dynamics prediction over long horizons. The latent memory shifts and transforms equivariantly with self-motion and inferred external object motion, keeping information about out-of-view regions aligned as time progresses. We demonstrate the advantage of this framework over state-of-the-art diffusion, memory-augmented, and recurrent world model architectures on 2D and 3D partially observed video world modeling benchmarks. More broadly, our results suggest that predictive representations become more powerful when they are organized in line with the temporal and dynamical structure of the world they model. Project page: https://flowequivariantworldmodels.github.io/

Fangneng Zhan, Jiahui Zhang, Yingchen Yu et al.

Perceiving the similarity between images has been a long-standing and fundamental problem underlying various visual generation tasks. Predominant approaches measure the inter-image distance by computing pointwise absolute deviations, which tends to estimate the median of instance distributions and leads to blurs and artifacts in the generated images. This paper presents MoNCE, a versatile metric that introduces image contrast to learn a calibrated metric for the perception of multifaceted inter-image distances. Unlike vanilla contrast which indiscriminately pushes negative samples from the anchor regardless of their similarity, we propose to re-weight the pushing force of negative samples adaptively according to their similarity to the anchor, which facilitates the contrastive learning from informative negative samples. Since multiple patch-level contrastive objectives are involved in image distance measurement, we introduce optimal transport in MoNCE to modulate the pushing force of negative samples collaboratively across multiple contrastive objectives. Extensive experiments over multiple image translation tasks show that the proposed MoNCE outperforms various prevailing metrics substantially. The code is available at https://github.com/fnzhan/MoNCE.

Zuhao Yang, Fangneng Zhan, Kunhao Liu et al.

The advancement of visual intelligence is intrinsically tethered to the availability of large-scale data. In parallel, generative Artificial Intelligence (AI) has unlocked the potential to create synthetic images that closely resemble real-world photographs. This prompts a compelling inquiry: how much visual intelligence could benefit from the advance of generative AI? This paper explores the innovative concept of harnessing these AI-generated images as new data sources, reshaping traditional modeling paradigms in visual intelligence. In contrast to real data, AI-generated data exhibit remarkable advantages, including unmatched abundance and scalability, the rapid generation of vast datasets, and the effortless simulation of edge cases. Built on the success of generative AI models, we examine the potential of their generated data in a range of applications, from training machine learning models to simulating scenarios for computational modeling, testing, and validation. We probe the technological foundations that support this groundbreaking use of generative AI, engaging in an in-depth discussion on the ethical, legal, and practical considerations that accompany this transformative paradigm shift. Through an exhaustive survey of current technologies and applications, this paper presents a comprehensive view of the synthetic era in visual intelligence. A project associated with this paper can be found at https://github.com/mwxely/AIGS .

Kunhao Liu, Fangneng Zhan, Yiwen Chen et al.

3D style transfer aims to render stylized novel views of a 3D scene with multi-view consistency. However, most existing work suffers from a three-way dilemma over accurate geometry reconstruction, high-quality stylization, and being generalizable to arbitrary new styles. We propose StyleRF (Style Radiance Fields), an innovative 3D style transfer technique that resolves the three-way dilemma by performing style transformation within the feature space of a radiance field. StyleRF employs an explicit grid of high-level features to represent 3D scenes, with which high-fidelity geometry can be reliably restored via volume rendering. In addition, it transforms the grid features according to the reference style which directly leads to high-quality zero-shot style transfer. StyleRF consists of two innovative designs. The first is sampling-invariant content transformation that makes the transformation invariant to the holistic statistics of the sampled 3D points and accordingly ensures multi-view consistency. The second is deferred style transformation of 2D feature maps which is equivalent to the transformation of 3D points but greatly reduces memory footprint without degrading multi-view consistency. Extensive experiments show that StyleRF achieves superior 3D stylization quality with precise geometry reconstruction and it can generalize to various new styles in a zero-shot manner.

Jiahui Zhang, Fangneng Zhan, Christian Theobalt et al.

Quantizing images into discrete representations has been a fundamental problem in unified generative modeling. Predominant approaches learn the discrete representation either in a deterministic manner by selecting the best-matching token or in a stochastic manner by sampling from a predicted distribution. However, deterministic quantization suffers from severe codebook collapse and misalignment with inference stage while stochastic quantization suffers from low codebook utilization and perturbed reconstruction objective. This paper presents a regularized vector quantization framework that allows to mitigate above issues effectively by applying regularization from two perspectives. The first is a prior distribution regularization which measures the discrepancy between a prior token distribution and the predicted token distribution to avoid codebook collapse and low codebook utilization. The second is a stochastic mask regularization that introduces stochasticity during quantization to strike a good balance between inference stage misalignment and unperturbed reconstruction objective. In addition, we design a probabilistic contrastive loss which serves as a calibrated metric to further mitigate the perturbed reconstruction objective. Extensive experiments show that the proposed quantization framework outperforms prevailing vector quantization methods consistently across different generative models including auto-regressive models and diffusion models.

Muyu Xu, Fangneng Zhan, Jiahui Zhang et al.

Neural Radiance Field (NeRF) has shown impressive performance in novel view synthesis via implicit scene representation. However, it usually suffers from poor scalability as requiring densely sampled images for each new scene. Several studies have attempted to mitigate this problem by integrating Multi-View Stereo (MVS) technique into NeRF while they still entail a cumbersome fine-tuning process for new scenes. Notably, the rendering quality will drop severely without this fine-tuning process and the errors mainly appear around the high-frequency features. In the light of this observation, we design WaveNeRF, which integrates wavelet frequency decomposition into MVS and NeRF to achieve generalizable yet high-quality synthesis without any per-scene optimization. To preserve high-frequency information when generating 3D feature volumes, WaveNeRF builds Multi-View Stereo in the Wavelet domain by integrating the discrete wavelet transform into the classical cascade MVS, which disentangles high-frequency information explicitly. With that, disentangled frequency features can be injected into classic NeRF via a novel hybrid neural renderer to yield faithful high-frequency details, and an intuitive frequency-guided sampling strategy can be designed to suppress artifacts around high-frequency regions. Extensive experiments over three widely studied benchmarks show that WaveNeRF achieves superior generalizable radiance field modeling when only given three images as input.

Yingchen Yu, Fangneng Zhan, Rongliang Wu et al.

Leveraging StyleGAN's expressivity and its disentangled latent codes, existing methods can achieve realistic editing of different visual attributes such as age and gender of facial images. An intriguing yet challenging problem arises: Can generative models achieve counterfactual editing against their learnt priors? Due to the lack of counterfactual samples in natural datasets, we investigate this problem in a text-driven manner with Contrastive-Language-Image-Pretraining (CLIP), which can offer rich semantic knowledge even for various counterfactual concepts. Different from in-domain manipulation, counterfactual manipulation requires more comprehensive exploitation of semantic knowledge encapsulated in CLIP as well as more delicate handling of editing directions for avoiding being stuck in local minimum or undesired editing. To this end, we design a novel contrastive loss that exploits predefined CLIP-space directions to guide the editing toward desired directions from different perspectives. In addition, we design a simple yet effective scheme that explicitly maps CLIP embeddings (of target text) to the latent space and fuses them with latent codes for effective latent code optimization and accurate editing. Extensive experiments show that our design achieves accurate and realistic editing while driving by target texts with various counterfactual concepts.

Chuhui Xue, Zichen Tian, Fangneng Zhan et al.

State-of-the-art document dewarping techniques learn to predict 3-dimensional information of documents which are prone to errors while dealing with documents with irregular distortions or large variations in depth. This paper presents FDRNet, a Fourier Document Restoration Network that can restore documents with different distortions and improve document recognition in a reliable and simpler manner. FDRNet focuses on high-frequency components in the Fourier space that capture most structural information but are largely free of degradation in appearance. It dewarps documents by a flexible Thin-Plate Spline transformation which can handle various deformations effectively without requiring deformation annotations in training. These features allow FDRNet to learn from a small amount of simply labeled training images, and the learned model can dewarp documents with complex geometric distortion and recognize the restored texts accurately. To facilitate document restoration research, we create a benchmark dataset consisting of over one thousand camera documents with different types of geometric and photometric distortion. Extensive experiments show that FDRNet outperforms the state-of-the-art by large margins on both dewarping and text recognition tasks. In addition, FDRNet requires a small amount of simply labeled training data and is easy to deploy.

Fangneng Zhan, Yingchen Yu, Rongliang Wu et al.

Exemplar-based image translation establishes dense correspondences between a conditional input and an exemplar (from two different domains) for leveraging detailed exemplar styles to achieve realistic image translation. Existing work builds the cross-domain correspondences implicitly by minimizing feature-wise distances across the two domains. Without explicit exploitation of domain-invariant features, this approach may not reduce the domain gap effectively which often leads to sub-optimal correspondences and image translation. We design a Marginal Contrastive Learning Network (MCL-Net) that explores contrastive learning to learn domain-invariant features for realistic exemplar-based image translation. Specifically, we design an innovative marginal contrastive loss that guides to establish dense correspondences explicitly. Nevertheless, building correspondence with domain-invariant semantics alone may impair the texture patterns and lead to degraded texture generation. We thus design a Self-Correlation Map (SCM) that incorporates scene structures as auxiliary information which improves the built correspondences substantially. Quantitative and qualitative experiments on multifarious image translation tasks show that the proposed method outperforms the state-of-the-art consistently.

Jiahui Zhang, Fangneng Zhan, Rongliang Wu et al.

Neural Radiance Fields (NeRF) have demonstrated very impressive performance in novel view synthesis via implicitly modelling 3D representations from multi-view 2D images. However, most existing studies train NeRF models with either reasonable camera pose initialization or manually-crafted camera pose distributions which are often unavailable or hard to acquire in various real-world data. We design VMRF, an innovative view matching NeRF that enables effective NeRF training without requiring prior knowledge in camera poses or camera pose distributions. VMRF introduces a view matching scheme, which exploits unbalanced optimal transport to produce a feature transport plan for mapping a rendered image with randomly initialized camera pose to the corresponding real image. With the feature transport plan as the guidance, a novel pose calibration technique is designed which rectifies the initially randomized camera poses by predicting relative pose transformations between the pair of rendered and real images. Extensive experiments over a number of synthetic and real datasets show that the proposed VMRF outperforms the state-of-the-art qualitatively and quantitatively by large margins.

Kaiwen Cui, Rongliang Wu, Fangneng Zhan et al.

Face swapping aims to generate swapped images that fuse the identity of source faces and the attributes of target faces. Most existing works address this challenging task through 3D modelling or generation using generative adversarial networks (GANs), but 3D modelling suffers from limited reconstruction accuracy and GANs often struggle in preserving subtle yet important identity details of source faces (e.g., skin colors, face features) and structural attributes of target faces (e.g., face shapes, facial expressions). This paper presents Face Transformer, a novel face swapping network that can accurately preserve source identities and target attributes simultaneously in the swapped face images. We introduce a transformer network for the face swapping task, which learns high-quality semantic-aware correspondence between source and target faces and maps identity features of source faces to the corresponding region in target faces. The high-quality semantic-aware correspondence enables smooth and accurate transfer of source identity information with minimal modification of target shapes and expressions. In addition, our Face Transformer incorporates a multi-scale transformation mechanism for preserving the rich fine facial details. Extensive experiments show that our Face Transformer achieves superior face swapping performance qualitatively and quantitatively.

Fangneng Zhan, Yingchen Yu, Rongliang Wu et al.

Deep generative models have achieved conspicuous progress in realistic image synthesis with multifarious conditional inputs, while generating diverse yet high-fidelity images remains a grand challenge in conditional image generation. This paper presents a versatile framework for conditional image generation which incorporates the inductive bias of CNNs and powerful sequence modeling of auto-regression that naturally leads to diverse image generation. Instead of independently quantizing the features of multiple domains as in prior research, we design an integrated quantization scheme with a variational regularizer that mingles the feature discretization in multiple domains, and markedly boosts the auto-regressive modeling performance. Notably, the variational regularizer enables to regularize feature distributions in incomparable latent spaces by penalizing the intra-domain variations of distributions. In addition, we design a Gumbel sampling strategy that allows to incorporate distribution uncertainty into the auto-regressive training procedure. The Gumbel sampling substantially mitigates the exposure bias that often incurs misalignment between the training and inference stages and severely impairs the inference performance. Extensive experiments over multiple conditional image generation tasks show that our method achieves superior diverse image generation performance qualitatively and quantitatively as compared with the state-of-the-art.

Jiahui Zhang, Fangneng Zhan, Yingchen Yu et al.

Pose-free neural radiance fields (NeRF) aim to train NeRF with unposed multi-view images and it has achieved very impressive success in recent years. Most existing works share the pipeline of training a coarse pose estimator with rendered images at first, followed by a joint optimization of estimated poses and neural radiance field. However, as the pose estimator is trained with only rendered images, the pose estimation is usually biased or inaccurate for real images due to the domain gap between real images and rendered images, leading to poor robustness for the pose estimation of real images and further local minima in joint optimization. We design IR-NeRF, an innovative pose-free NeRF that introduces implicit pose regularization to refine pose estimator with unposed real images and improve the robustness of the pose estimation for real images. With a collection of 2D images of a specific scene, IR-NeRF constructs a scene codebook that stores scene features and captures the scene-specific pose distribution implicitly as priors. Thus, the robustness of pose estimation can be promoted with the scene priors according to the rationale that a 2D real image can be well reconstructed from the scene codebook only when its estimated pose lies within the pose distribution. Extensive experiments show that IR-NeRF achieves superior novel view synthesis and outperforms the state-of-the-art consistently across multiple synthetic and real datasets.

Rongliang Wu, Yingchen Yu, Fangneng Zhan et al.

Audio-driven talking face generation, which aims to synthesize talking faces with realistic facial animations (including accurate lip movements, vivid facial expression details and natural head poses) corresponding to the audio, has achieved rapid progress in recent years. However, most existing work focuses on generating lip movements only without handling the closely correlated facial expressions, which degrades the realism of the generated faces greatly. This paper presents DIRFA, a novel method that can generate talking faces with diverse yet realistic facial animations from the same driving audio. To accommodate fair variation of plausible facial animations for the same audio, we design a transformer-based probabilistic mapping network that can model the variational facial animation distribution conditioned upon the input audio and autoregressively convert the audio signals into a facial animation sequence. In addition, we introduce a temporally-biased mask into the mapping network, which allows to model the temporal dependency of facial animations and produce temporally smooth facial animation sequence. With the generated facial animation sequence and a source image, photo-realistic talking faces can be synthesized with a generic generation network. Extensive experiments show that DIRFA can generate talking faces with realistic facial animations effectively.

Kaiwen Cui, Yingchen Yu, Fangneng Zhan et al.

Generative Adversarial Networks (GANs) rely heavily on large-scale training data for training high-quality image generation models. With limited training data, the GAN discriminator often suffers from severe overfitting which directly leads to degraded generation especially in generation diversity. Inspired by the recent advances in knowledge distillation (KD), we propose KD-DLGAN, a knowledge-distillation based generation framework that introduces pre-trained vision-language models for training effective data-limited generation models. KD-DLGAN consists of two innovative designs. The first is aggregated generative KD that mitigates the discriminator overfitting by challenging the discriminator with harder learning tasks and distilling more generalizable knowledge from the pre-trained models. The second is correlated generative KD that improves the generation diversity by distilling and preserving the diverse image-text correlation within the pre-trained models. Extensive experiments over multiple benchmarks show that KD-DLGAN achieves superior image generation with limited training data. In addition, KD-DLGAN complements the state-of-the-art with consistent and substantial performance gains.

Rongliang Wu, Yingchen Yu, Fangneng Zhan et al.

Facial expression editing has attracted increasing attention with the advance of deep neural networks in recent years. However, most existing methods suffer from compromised editing fidelity and limited usability as they either ignore pose variations (unrealistic editing) or require paired training data (not easy to collect) for pose controls. This paper presents POCE, an innovative pose-controllable expression editing network that can generate realistic facial expressions and head poses simultaneously with just unpaired training images. POCE achieves the more accessible and realistic pose-controllable expression editing by mapping face images into UV space, where facial expressions and head poses can be disentangled and edited separately. POCE has two novel designs. The first is self-supervised UV completion that allows to complete UV maps sampled under different head poses, which often suffer from self-occlusions and missing facial texture. The second is weakly-supervised UV editing that allows to generate new facial expressions with minimal modification of facial identity, where the synthesized expression could be controlled by either an expression label or directly transplanted from a reference UV map via feature transfer. Extensive experiments show that POCE can learn from unpaired face images effectively, and the learned model can generate realistic and high-fidelity facial expressions under various new poses.

Pramod Rao, Gereon Fox, Abhimitra Meka et al.

Achieving photorealistic 3D view synthesis and relighting of human portraits is pivotal for advancing AR/VR applications. Existing methodologies in portrait relighting demonstrate substantial limitations in terms of generalization and 3D consistency, coupled with inaccuracies in physically realistic lighting and identity preservation. Furthermore, personalization from a single view is difficult to achieve and often requires multiview images during the testing phase or involves slow optimization processes. This paper introduces Lite2Relight, a novel technique that can predict 3D consistent head poses of portraits while performing physically plausible light editing at interactive speed. Our method uniquely extends the generative capabilities and efficient volumetric representation of EG3D, leveraging a lightstage dataset to implicitly disentangle face reflectance and perform relighting under target HDRI environment maps. By utilizing a pre-trained geometry-aware encoder and a feature alignment module, we map input images into a relightable 3D space, enhancing them with a strong face geometry and reflectance prior. Through extensive quantitative and qualitative evaluations, we show that our method outperforms the state-of-the-art methods in terms of efficacy, photorealism, and practical application. This includes producing 3D-consistent results of the full head, including hair, eyes, and expressions. Lite2Relight paves the way for large-scale adoption of photorealistic portrait editing in various domains, offering a robust, interactive solution to a previously constrained problem. Project page: https://vcai.mpi-inf.mpg.de/projects/Lite2Relight/

Jiahui Zhang, Fangneng Zhan, Yingchen Yu et al.

Recently, single image super-resolution (SR) under large scaling factors has witnessed impressive progress by introducing pre-trained generative adversarial networks (GANs) as priors. However, most GAN-Priors based SR methods are constrained by an attribute disentanglement problem in inverted latent codes which directly leads to mismatches of visual attributes in the generator layers and further degraded reconstruction. In addition, stochastic noises fed to the generator are employed for unconditional detail generation, which tends to produce unfaithful details that compromise the fidelity of the generated SR image. We design LAREN, a LAtent multi-Relation rEasoNing technique that achieves superb large-factor SR through graph-based multi-relation reasoning in latent space. LAREN consists of two innovative designs. The first is graph-based disentanglement that constructs a superior disentangled latent space via hierarchical multi-relation reasoning. The second is graph-based code generation that produces image-specific codes progressively via recursive relation reasoning which enables prior GANs to generate desirable image details. Extensive experiments show that LAREN achieves superior large-factor image SR and outperforms the state-of-the-art consistently across multiple benchmarks.

Junaid Wahid, Fangneng Zhan, Pramod Rao et al.

Face aging is the process of converting an individual's appearance to a younger or older version of themselves. Existing face aging techniques have been limited to 2D settings, which often weaken their applications as there is a growing demand for 3D face modeling. Moreover, existing aging methods struggle to perform faithful aging, maintain identity, and retain the fine details of the input images. Given these limitations and the need for a 3D-aware aging method, we propose DiffAge3D, the first 3D-aware aging framework that not only performs faithful aging and identity preservation but also operates in a 3D setting. Our aging framework allows to model the aging and camera pose separately by only taking a single image with a target age. Our framework includes a robust 3D-aware aging dataset generation pipeline by utilizing a pre-trained 3D GAN and the rich text embedding capabilities within CLIP model. Notably, we do not employ any inversion bottleneck in dataset generation. Instead, we randomly generate training samples from the latent space of 3D GAN, allowing us to manipulate the rich latent space of GAN to generate ages even with large gaps. With the generated dataset, we train a viewpoint-aware diffusion-based aging model to control the camera pose and facial age. Through quantitative and qualitative evaluations, we demonstrate that DiffAge3D outperforms existing methods, particularly in multiview-consistent aging and fine details preservation.

Muyu Xu, Fangneng Zhan, Xiaoqin Zhang et al.

Sparse-view 3D Gaussian splatting seeks to render high-quality novel views of 3D scenes from a limited set of input images. While recent pose-free feed-forward methods leveraging pre-trained 3D priors have achieved impressive results, most of them rely on full fine-tuning of large Vision Transformer (ViT) backbones and incur substantial GPU costs. In this work, we introduce MuSASplat, a novel framework that dramatically reduces the computational burden of training pose-free feed-forward 3D Gaussian splats models with little compromise of rendering quality. Central to our approach is a lightweight Multi-Scale Adapter that enables efficient fine-tuning of ViT-based architectures with only a small fraction of training parameters. This design avoids the prohibitive GPU overhead associated with previous full-model adaptation techniques while maintaining high fidelity in novel view synthesis, even with very sparse input views. In addition, we introduce a Feature Fusion Aggregator that integrates features across input views effectively and efficiently. Unlike widely adopted memory banks, the Feature Fusion Aggregator ensures consistent geometric integration across input views and meanwhile mitigates the memory usage, training complexity, and computational costs significantly. Extensive experiments across diverse datasets show that MuSASplat achieves state-of-the-art rendering quality but has significantly reduced parameters and training resource requirements as compared with existing methods.

Yue Ma, Xu Ye, Qinghe Wang et al.

Generating high-fidelity visual effects (VFX) typically demands massive datasets and prohibitive computational power due to the intricate coupling of spatial textures and temporal dynamics. In this paper, we introduce EasyVFX, a resource-efficient framework that achieves realistic VFX synthesis under stringent constraints. Our core philosophy lies in frequency-domain decomposition: we observe that the complexity of VFX can be significantly mitigated by decoupling high-frequency components, which represent intricate spatial appearances, from low-frequency components that encapsulate global motion dynamics. This spectral disentanglement transforms a high-dimensional learning problem into manageable sub-tasks, thereby lowering the optimization barrier and reducing data dependency. Building upon this insight, we propose a two-stage training paradigm. First, we design a Frequency-aware Mixture-of-Experts (Freq-MoE) architecture. By utilizing a soft routing mechanism, our model assigns specialized experts to distinct spectral bands, enabling them to cultivate robust priors for appearance and motion dynamics. This specialization allows the model to acquire foundational VFX knowledge with fewer GPU resources. Second, we introduce a Test-Time Training strategy powered by a novel Frequency-constraint Loss. This allows the pre-trained model to swiftly adapt to specific, unseen effects through localized optimizations, requiring only about 100 steps on a single GPU. Experimental results demonstrate that EasyVFX produces structurally consistent and visually stunning effects, proving that frequency-aware learning is a key catalyst for democratizing professional-grade VFX.

Freeman Cheng, Botao Ye, Xueting Li et al.

Online novel view synthesis remains challenging, requiring robust scene reconstruction from sequential, often unposed, observations. We present ReCoSplat, an autoregressive feed-forward Gaussian Splatting model supporting posed or unposed inputs, with or without camera intrinsics. While assembling local Gaussians using camera poses scales better than canonical-space prediction, it creates a dilemma during training: using ground-truth poses ensures stability but causes a distribution mismatch when predicted poses are used at inference. To address this, we introduce a Render-and-Compare (ReCo) module. ReCo renders the current reconstruction from the predicted viewpoint and compares it with the incoming observation, providing a stable conditioning signal that compensates for pose errors. To support long sequences, we propose a hybrid KV cache compression strategy combining early-layer truncation with chunk-level selective retention, reducing the KV cache size by over 90% for 100+ frames. ReCoSplat achieves state-of-the-art performance across different input settings on both in- and out-of-distribution benchmarks. Code and pretrained models will be released. Our project page is at https://freemancheng.com/ReCoSplat .

Kaichen Zhou, Yuzhen Chen, Fangneng Zhan et al.

Video world models can generate realistic futures from a single instruction, but they often fail to preserve consistent point-level motion over time. As a result, the generated videos appear plausible, yet lack the physical grounding required for reliable action execution, such as robot manipulation. We present GEM-4D, a geometry-grounded video world model that resolves this limitation by injecting dense 4D correspondence supervision, distilled from a pretrained geometry foundation model, into the video generative backbone during training. This supervision enables the model to jointly capture appearance and geometric structure while retaining a single-stream architecture with no additional inference cost. We further introduce an inverse dynamics module that converts correspondence-consistent video rollouts into executable robot trajectories, enabling direct deployment in both real-world and simulated manipulation. GEM-4D achieves state-of-the-art performance on both video prediction and geometric consistency across simulation and realistic scenarios and improves real-world manipulation success from 61% to 81%. Additional results are available at the project page: https://anonymous-submission-20.github.io/gem.github.io/.

Kaichen Zhou, Zeyang Bai, Xinhai Chang et al.

View-conditioned 3D generators such as SAM 3D, TRELLIS and Hunyuan3D produce high-quality object reconstructions from a single view, but real-world visual observation often arrives as long monocular streams. Naively applying these generators to each streaming frame independently leads to severe temporal inconsistency in the generated results. To address this problem, we propose Stream3D, the first training-free streaming mechanism that turns a frozen view-conditioned 3D generator into a streaming generator with constant cross-chunk memory. Stream3D achieves this by maintaining a compact evidential memory, which selectively caches the most informative historical frames based on a proposed evidence score mechanism. As the stream progresses, the memory dynamically updates to retain a fixed number of informative frames, preventing the memory footprint from growing linearly with sequence length. This also prevents degradation over long sequences and keeps the underlying generator completely unchanged without retraining, architectural modifications, or auxiliary losses. Evaluated on both realistic and synthetic streaming benchmarks, Stream3D outperforms latent-transport baselines, including KV-cache reuse and flow-based feature editing, across both photometric and geometric metrics. More details can be found at: https://anonymous-submission-20.github.io/streaming3D.github.io/.

Leslie Gu, Junhwa Hur, Charles Herrmann et al.

We introduce GeCo, a geometry-grounded metric for jointly detecting geometric deformation and occlusion-inconsistency artifacts in static scenes. By fusing residual motion and depth priors, GeCo produces interpretable, dense consistency maps that reveal these artifacts. We use GeCo to systematically benchmark recent video generation models, uncovering common failure modes, and further employ it as a training-free guidance loss to reduce deformation artifacts during video generation.

Yu Chi, Fangneng Zhan, Sibo Wu et al.

Progress in 3D computer vision tasks demands a huge amount of data, yet annotating multi-view images with 3D-consistent annotations, or point clouds with part segmentation is both time-consuming and challenging. This paper introduces DatasetNeRF, a novel approach capable of generating infinite, high-quality 3D-consistent 2D annotations alongside 3D point cloud segmentations, while utilizing minimal 2D human-labeled annotations. Specifically, we leverage the strong semantic prior within a 3D generative model to train a semantic decoder, requiring only a handful of fine-grained labeled samples. Once trained, the decoder efficiently generalizes across the latent space, enabling the generation of infinite data. The generated data is applicable across various computer vision tasks, including video segmentation and 3D point cloud segmentation. Our approach not only surpasses baseline models in segmentation quality, achieving superior 3D consistency and segmentation precision on individual images, but also demonstrates versatility by being applicable to both articulated and non-articulated generative models. Furthermore, we explore applications stemming from our approach, such as 3D-aware semantic editing and 3D inversion.

Yifan Liu, Fangneng Zhan, Wanhua Li et al.

Estimating robot pose from a monocular RGB image is a challenge in robotics and computer vision. Existing methods typically build networks on top of 2D visual backbones and depend heavily on labeled data for training, which is often scarce in real-world scenarios, causing a sim-to-real gap. Moreover, these approaches reduce the 3D-based problem to 2D domain, neglecting the 3D priors. To address these, we propose Robot Topological Alignment Graph (RoboTAG), which incorporates a 3D branch to inject 3D priors while enabling co-evolution of the 2D and 3D representations, alleviating the reliance on labels. Specifically, the RoboTAG consists of a 3D branch and a 2D branch, where nodes represent the states of the camera and robot system, and edges capture the dependencies between these variables or denote alignments between them. Closed loops are then defined in the graph, on which a consistency supervision across branches can be applied. This design allows us to utilize in-the-wild images as training data without annotations. Experimental results demonstrate that our method is effective across robot types, highlighting its potential to alleviate the data bottleneck in robotics.

Yifan Liu, Fangneng Zhan, Kaichen Zhou et al.

Vision-language models (VLMs) struggle with 3D-related tasks such as spatial cognition and physical understanding, which are crucial for real-world applications like robotics and embodied agents. We attribute this to a modality gap between the 3D tasks and the 2D training of VLM, which led to inefficient retrieval of 3D information from 2D input. To bridge this gap, we introduce SandboxVLM, a simple yet effective framework that leverages abstract bounding boxes to encode geometric structure and physical kinematics for VLM. Specifically, we design a 3D Sandbox reconstruction and perception pipeline comprising four stages: generating multi-view priors with abstract control, proxy elevation, multi-view voting and clustering, and 3D-aware reasoning. Evaluated in zero-shot settings across multiple benchmarks and VLM backbones, our approach consistently improves spatial intelligence, achieving an 8.3\% gain on SAT Real compared with baseline methods for instance. These results demonstrate that equipping VLMs with a 3D abstraction substantially enhances their 3D reasoning ability without additional training, suggesting new possibilities for general-purpose embodied intelligence.

Tianling Xu, Shengzhe Gan, Leslie Gu et al.

Active 3D reconstruction enables an agent to autonomously select viewpoints to efficiently obtain accurate and complete scene geometry, rather than passively reconstructing scenes from pre-collected images. However, existing active reconstruction methods often rely on hand-crafted geometric heuristics, which can lead to redundant observations without substantially improving reconstruction quality. To address this limitation, we propose AREA3D, an active reconstruction agent that leverages feed-forward 3D reconstruction models and vision-language guidance. Our framework decouples view-uncertainty modeling from the underlying feed-forward reconstructor, enabling precise uncertainty estimation without expensive online optimization. In addition, an integrated vision-language model provides high-level semantic guidance, encouraging informative and diverse viewpoints beyond purely geometric cues. Extensive experiments on both scene-level and object-level benchmarks demonstrate that AREA3D achieves state-of-the-art reconstruction accuracy, particularly in the sparse-view regime. Code will be made available at: https://github.com/TianlingXu/AREA3D .

Kunhao Liu, Fangneng Zhan, Jiahui Zhang et al.

Open-vocabulary segmentation of 3D scenes is a fundamental function of human perception and thus a crucial objective in computer vision research. However, this task is heavily impeded by the lack of large-scale and diverse 3D open-vocabulary segmentation datasets for training robust and generalizable models. Distilling knowledge from pre-trained 2D open-vocabulary segmentation models helps but it compromises the open-vocabulary feature as the 2D models are mostly finetuned with close-vocabulary datasets. We tackle the challenges in 3D open-vocabulary segmentation by exploiting pre-trained foundation models CLIP and DINO in a weakly supervised manner. Specifically, given only the open-vocabulary text descriptions of the objects in a scene, we distill the open-vocabulary multimodal knowledge and object reasoning capability of CLIP and DINO into a neural radiance field (NeRF), which effectively lifts 2D features into view-consistent 3D segmentation. A notable aspect of our approach is that it does not require any manual segmentation annotations for either the foundation models or the distillation process. Extensive experiments show that our method even outperforms fully supervised models trained with segmentation annotations in certain scenes, suggesting that 3D open-vocabulary segmentation can be effectively learned from 2D images and text-image pairs. Code is available at \url{https://github.com/Kunhao-Liu/3D-OVS}.

Fangneng Zhan, Yingchen Yu, Rongliang Wu et al.

As information exists in various modalities in real world, effective interaction and fusion among multimodal information plays a key role for the creation and perception of multimodal data in computer vision and deep learning research. With superb power in modeling the interaction among multimodal information, multimodal image synthesis and editing has become a hot research topic in recent years. Instead of providing explicit guidance for network training, multimodal guidance offers intuitive and flexible means for image synthesis and editing. On the other hand, this field is also facing several challenges in alignment of multimodal features, synthesis of high-resolution images, faithful evaluation metrics, etc. In this survey, we comprehensively contextualize the advance of the recent multimodal image synthesis and editing and formulate taxonomies according to data modalities and model types. We start with an introduction to different guidance modalities in image synthesis and editing, and then describe multimodal image synthesis and editing approaches extensively according to their model types. After that, we describe benchmark datasets and evaluation metrics as well as corresponding experimental results. Finally, we provide insights about the current research challenges and possible directions for future research. A project associated with this survey is available at https://github.com/fnzhan/Generative-AI.

Aoran Xiao, Jiaxing Huang, Dayan Guan et al.

Knowledge transfer from synthetic to real data has been widely studied to mitigate data annotation constraints in various computer vision tasks such as semantic segmentation. However, the study focused on 2D images and its counterpart in 3D point clouds segmentation lags far behind due to the lack of large-scale synthetic datasets and effective transfer methods. We address this issue by collecting SynLiDAR, a large-scale synthetic LiDAR dataset that contains point-wise annotated point clouds with accurate geometric shapes and comprehensive semantic classes. SynLiDAR was collected from multiple virtual environments with rich scenes and layouts which consists of over 19 billion points of 32 semantic classes. In addition, we design PCT, a novel point cloud translator that effectively mitigates the gap between synthetic and real point clouds. Specifically, we decompose the synthetic-to-real gap into an appearance component and a sparsity component and handle them separately which improves the point cloud translation greatly. We conducted extensive experiments over three transfer learning setups including data augmentation, semi-supervised domain adaptation and unsupervised domain adaptation. Extensive experiments show that SynLiDAR provides a high-quality data source for studying 3D transfer and the proposed PCT achieves superior point cloud translation consistently across the three setups. SynLiDAR project page: \url{https://github.com/xiaoaoran/SynLiDAR}

Fangneng Zhan, Yingchen Yu, Changgong Zhang et al.

Inferring the scene illumination from a single image is an essential yet challenging task in computer vision and computer graphics. Existing works estimate lighting by regressing representative illumination parameters or generating illumination maps directly. However, these methods often suffer from poor accuracy and generalization. This paper presents Geometric Mover's Light (GMLight), a lighting estimation framework that employs a regression network and a generative projector for effective illumination estimation. We parameterize illumination scenes in terms of the geometric light distribution, light intensity, ambient term, and auxiliary depth, which can be estimated by a regression network. Inspired by the earth mover's distance, we design a novel geometric mover's loss to guide the accurate regression of light distribution parameters. With the estimated light parameters, the generative projector synthesizes panoramic illumination maps with realistic appearance and high-frequency details. Extensive experiments show that GMLight achieves accurate illumination estimation and superior fidelity in relighting for 3D object insertion. The codes are available at \href{https://github.com/fnzhan/Illumination-Estimation}{https://github.com/fnzhan/Illumination-Estimation}.

Jiahui Zhang, Fangneng Zhan, Muyu Xu et al.

3D Gaussian splatting has achieved very impressive performance in real-time novel view synthesis. However, it often suffers from over-reconstruction during Gaussian densification where high-variance image regions are covered by a few large Gaussians only, leading to blur and artifacts in the rendered images. We design a progressive frequency regularization (FreGS) technique to tackle the over-reconstruction issue within the frequency space. Specifically, FreGS performs coarse-to-fine Gaussian densification by exploiting low-to-high frequency components that can be easily extracted with low-pass and high-pass filters in the Fourier space. By minimizing the discrepancy between the frequency spectrum of the rendered image and the corresponding ground truth, it achieves high-quality Gaussian densification and alleviates the over-reconstruction of Gaussian splatting effectively. Experiments over multiple widely adopted benchmarks (e.g., Mip-NeRF360, Tanks-and-Temples and Deep Blending) show that FreGS achieves superior novel view synthesis and outperforms the state-of-the-art consistently.

Kunhao Liu, Fangneng Zhan, Muyu Xu et al.

We introduce StyleGaussian, a novel 3D style transfer technique that allows instant transfer of any image's style to a 3D scene at 10 frames per second (fps). Leveraging 3D Gaussian Splatting (3DGS), StyleGaussian achieves style transfer without compromising its real-time rendering ability and multi-view consistency. It achieves instant style transfer with three steps: embedding, transfer, and decoding. Initially, 2D VGG scene features are embedded into reconstructed 3D Gaussians. Next, the embedded features are transformed according to a reference style image. Finally, the transformed features are decoded into the stylized RGB. StyleGaussian has two novel designs. The first is an efficient feature rendering strategy that first renders low-dimensional features and then maps them into high-dimensional features while embedding VGG features. It cuts the memory consumption significantly and enables 3DGS to render the high-dimensional memory-intensive features. The second is a K-nearest-neighbor-based 3D CNN. Working as the decoder for the stylized features, it eliminates the 2D CNN operations that compromise strict multi-view consistency. Extensive experiments show that StyleGaussian achieves instant 3D stylization with superior stylization quality while preserving real-time rendering and strict multi-view consistency. Project page: https://kunhao-liu.github.io/StyleGaussian/

Keming Wu, Zuhao Yang, Kaichen Zhang et al.

Recent visual generation models have made major progress in photorealism, typography, instruction following, and interactive editing, yet they still struggle with spatial reasoning, persistent state, long-horizon consistency, and causal understanding. We argue that the field should move beyond appearance synthesis toward intelligent visual generation: plausible visuals grounded in structure, dynamics, domain knowledge, and causal relations. To frame this shift, we introduce a five-level taxonomy: Atomic Generation, Conditional Generation, In-Context Generation, Agentic Generation, and World-Modeling Generation, progressing from passive renderers to interactive, agentic, world-aware generators. We analyze key technical drivers, including flow matching, unified understanding-and-generation models, improved visual representations, post-training, reward modeling, data curation, synthetic data distillation, and sampling acceleration. We further show that current evaluations often overestimate progress by emphasizing perceptual quality while missing structural, temporal, and causal failures. By combining benchmark review, in-the-wild stress tests, and expert-constrained case studies, this roadmap offers a capability-centered lens for understanding, evaluating, and advancing the next generation of intelligent visual generation systems.

Heming Zhu, Fangneng Zhan, Christian Theobalt et al.

Creating controllable, photorealistic, and geometrically detailed digital doubles of real humans solely from video data is a key challenge in Computer Graphics and Vision, especially when real-time performance is required. Recent methods attach a neural radiance field (NeRF) to an articulated structure, e.g., a body model or a skeleton, to map points into a pose canonical space while conditioning the NeRF on the skeletal pose. These approaches typically parameterize the neural field with a multi-layer perceptron (MLP) leading to a slow runtime. To address this drawback, we propose TriHuman a novel human-tailored, deformable, and efficient tri-plane representation, which achieves real-time performance, state-of-the-art pose-controllable geometry synthesis as well as photorealistic rendering quality. At the core, we non-rigidly warp global ray samples into our undeformed tri-plane texture space, which effectively addresses the problem of global points being mapped to the same tri-plane locations. We then show how such a tri-plane feature representation can be conditioned on the skeletal motion to account for dynamic appearance and geometry changes. Our results demonstrate a clear step towards higher quality in terms of geometry and appearance modeling of humans as well as runtime performance.

Jiahui Zhang, Yuelei Li, Anpei Chen et al. · eth-zurich

3D reconstruction and view synthesis are foundational problems in computer vision, graphics, and immersive technologies such as augmented reality (AR), virtual reality (VR), and digital twins. Traditional methods rely on computationally intensive iterative optimization in a complex chain, limiting their applicability in real-world scenarios. Recent advances in feed-forward approaches, driven by deep learning, have revolutionized this field by enabling fast and generalizable 3D reconstruction and view synthesis. This survey offers a comprehensive review of feed-forward techniques for 3D reconstruction and view synthesis, with a taxonomy according to the underlying representation architectures including point cloud, 3D Gaussian Splatting (3DGS), Neural Radiance Fields (NeRF), etc. We examine key tasks such as pose-free reconstruction, dynamic 3D reconstruction, and 3D-aware image and video synthesis, highlighting their applications in digital humans, SLAM, robotics, and beyond. In addition, we review commonly used datasets with detailed statistics, along with evaluation protocols for various downstream tasks. We conclude by discussing open research challenges and promising directions for future work, emphasizing the potential of feed-forward approaches to advance the state of the art in 3D vision.

Xinlong Ji, Fangneng Zhan, Shijian Lu et al.

Accurately estimating scene lighting is critical for applications such as mixed reality. Existing works estimate illumination by generating illumination maps or regressing illumination parameters. However, the method of generating illumination maps has poor generalization performance and parametric models such as Spherical Harmonic (SH) and Spherical Gaussian (SG) fall short in capturing high-frequency or low-frequency components. This paper presents MixLight, a joint model that utilizes the complementary characteristics of SH and SG to achieve a more complete illumination representation, which uses SH and SG to capture low-frequency ambient and high-frequency light sources respectively. In addition, a special spherical light source sparsemax (SLSparsemax) module that refers to the position and brightness relationship between spherical light sources is designed to improve their sparsity, which is significant but omitted by prior works. Extensive experiments demonstrate that MixLight surpasses state-of-the-art (SOTA) methods on multiple metrics. In addition, experiments on Web Dataset also show that MixLight as a parametric method has better generalization performance than non-parametric methods.

Kaichen Zhou, Yuhan Wang, Grace Chen et al.

Recent 3D feed-forward models, such as the Visual Geometry Grounded Transformer (VGGT), have shown strong capability in inferring 3D attributes of static scenes. However, since they are typically trained on static datasets, these models often struggle in real-world scenarios involving complex dynamic elements, such as moving humans or deformable objects like umbrellas. To address this limitation, we introduce PAGE-4D, a feedforward model that extends VGGT to dynamic scenes, enabling camera pose estimation, depth prediction, and point cloud reconstruction -- all without post-processing. A central challenge in multi-task 4D reconstruction is the inherent conflict between tasks: accurate camera pose estimation requires suppressing dynamic regions, while geometry reconstruction requires modeling them. To resolve this tension, we propose a dynamics-aware aggregator that disentangles static and dynamic information by predicting a dynamics-aware mask -- suppressing motion cues for pose estimation while amplifying them for geometry reconstruction. Extensive experiments show that PAGE-4D consistently outperforms the original VGGT in dynamic scenarios, achieving superior results in camera pose estimation, monocular and video depth estimation, and dense point map reconstruction.

Pramod Rao, Abhimitra Meka, Xilong Zhou et al.

Rendering novel, relit views of a human head, given a monocular portrait image as input, is an inherently underconstrained problem. The traditional graphics solution is to explicitly decompose the input image into geometry, material and lighting via differentiable rendering; but this is constrained by the multiple assumptions and approximations of the underlying models and parameterizations of these scene components. We propose 3DPR, an image-based relighting model that leverages generative priors learnt from multi-view One-Light-at-A-Time (OLAT) images captured in a light stage. We introduce a new diverse and large-scale multi-view 4K OLAT dataset of 139 subjects to learn a high-quality prior over the distribution of high-frequency face reflectance. We leverage the latent space of a pre-trained generative head model that provides a rich prior over face geometry learnt from in-the-wild image datasets. The input portrait is first embedded in the latent manifold of such a model through an encoder-based inversion process. Then a novel triplane-based reflectance network trained on our lightstage data is used to synthesize high-fidelity OLAT images to enable image-based relighting. Our reflectance network operates in the latent space of the generative head model, crucially enabling a relatively small number of lightstage images to train the reflectance model. Combining the generated OLATs according to a given HDRI environment maps yields physically accurate environmental relighting results. Through quantitative and qualitative evaluations, we demonstrate that 3DPR outperforms previous methods, particularly in preserving identity and in capturing lighting effects such as specularities, self-shadows, and subsurface scattering. Project Page: https://vcai.mpi-inf.mpg.de/projects/3dpr/

Yuelei Li, Hyunjin Kim, Fangneng Zhan et al.

Objects produce different sounds when hit, and humans can intuitively infer how an object might sound based on its appearance and material properties. Inspired by this intuition, we propose Visual Acoustic Fields, a framework that bridges hitting sounds and visual signals within a 3D space using 3D Gaussian Splatting (3DGS). Our approach features two key modules: sound generation and sound localization. The sound generation module leverages a conditional diffusion model, which takes multiscale features rendered from a feature-augmented 3DGS to generate realistic hitting sounds. Meanwhile, the sound localization module enables querying the 3D scene, represented by the feature-augmented 3DGS, to localize hitting positions based on the sound sources. To support this framework, we introduce a novel pipeline for collecting scene-level visual-sound sample pairs, achieving alignment between captured images, impact locations, and corresponding sounds. To the best of our knowledge, this is the first dataset to connect visual and acoustic signals in a 3D context. Extensive experiments on our dataset demonstrate the effectiveness of Visual Acoustic Fields in generating plausible impact sounds and accurately localizing impact sources. Our project page is at https://yuelei0428.github.io/projects/Visual-Acoustic-Fields/.

Jiahui Zhang, Fangneng Zhan, Ling Shao et al.

Anchor-based 3D Gaussian splatting (3D-GS) exploits anchor features in 3D Gaussian prediction, which has achieved impressive 3D rendering quality with reduced Gaussian redundancy. On the other hand, it often encounters the dilemma among anchor features, model size, and rendering quality - large anchor features lead to large 3D models and high-quality rendering whereas reducing anchor features degrades Gaussian attribute prediction which leads to clear artifacts in the rendered textures and geometries. We design SOGS, an anchor-based 3D-GS technique that introduces second-order anchors to achieve superior rendering quality and reduced anchor features and model size simultaneously. Specifically, SOGS incorporates covariance-based second-order statistics and correlation across feature dimensions to augment features within each anchor, compensating for the reduced feature size and improving rendering quality effectively. In addition, it introduces a selective gradient loss to enhance the optimization of scene textures and scene geometries, leading to high-quality rendering with small anchor features. Extensive experiments over multiple widely adopted benchmarks show that SOGS achieves superior rendering quality in novel view synthesis with clearly reduced model size.

Fangneng Zhan, Lingjie Liu, Adam Kortylewski et al.

The recent advance of neural fields, such as neural radiance fields, has significantly pushed the boundary of scene representation learning. Aiming to boost the computation efficiency and rendering quality of 3D scenes, a popular line of research maps the 3D coordinate system to another measuring system, e.g., 2D manifolds and hash tables, for modeling neural fields. The conversion of coordinate systems can be typically dubbed as \emph{gauge transformation}, which is usually a pre-defined mapping function, e.g., orthogonal projection or spatial hash function. This begs a question: can we directly learn a desired gauge transformation along with the neural field in an end-to-end manner? In this work, we extend this problem to a general paradigm with a taxonomy of discrete \& continuous cases, and develop a learning framework to jointly optimize gauge transformations and neural fields. To counter the problem that the learning of gauge transformations can collapse easily, we derive a general regularization mechanism from the principle of information conservation during the gauge transformation. To circumvent the high computation cost in gauge learning with regularization, we directly derive an information-invariant gauge transformation which allows to preserve scene information inherently and yield superior performance. Project: https://fnzhan.com/Neural-Gauge-Fields

Kaiwen Cui, Jiaxing Huang, Zhipeng Luo et al.

Training effective Generative Adversarial Networks (GANs) requires large amounts of training data, without which the trained models are usually sub-optimal with discriminator over-fitting. Several prior studies address this issue by expanding the distribution of the limited training data via massive and hand-crafted data augmentation. We handle data-limited image generation from a very different perspective. Specifically, we design GenCo, a Generative Co-training network that mitigates the discriminator over-fitting issue by introducing multiple complementary discriminators that provide diverse supervision from multiple distinctive views in training. We instantiate the idea of GenCo in two ways. The first way is Weight-Discrepancy Co-training (WeCo) which co-trains multiple distinctive discriminators by diversifying their parameters. The second way is Data-Discrepancy Co-training (DaCo) which achieves co-training by feeding discriminators with different views of the input images (e.g., different frequency components of the input images). Extensive experiments over multiple benchmarks show that GenCo achieves superior generation with limited training data. In addition, GenCo also complements the augmentation approach with consistent and clear performance gains when combined.

Yingchen Yu, Fangneng Zhan, Shijian Lu et al.

Image inpainting aims to complete the missing or corrupted regions of images with realistic contents. The prevalent approaches adopt a hybrid objective of reconstruction and perceptual quality by using generative adversarial networks. However, the reconstruction loss and adversarial loss focus on synthesizing contents of different frequencies and simply applying them together often leads to inter-frequency conflicts and compromised inpainting. This paper presents WaveFill, a wavelet-based inpainting network that decomposes images into multiple frequency bands and fills the missing regions in each frequency band separately and explicitly. WaveFill decomposes images by using discrete wavelet transform (DWT) that preserves spatial information naturally. It applies L1 reconstruction loss to the decomposed low-frequency bands and adversarial loss to high-frequency bands, hence effectively mitigate inter-frequency conflicts while completing images in spatial domain. To address the inpainting inconsistency in different frequency bands and fuse features with distinct statistics, we design a novel normalization scheme that aligns and fuses the multi-frequency features effectively. Extensive experiments over multiple datasets show that WaveFill achieves superior image inpainting qualitatively and quantitatively.

Wenbo Hu, Changgong Zhang, Fangneng Zhan et al.

Graph convolutional networks have significantly improved 3D human pose estimation by representing the human skeleton as an undirected graph. However, this representation fails to reflect the articulated characteristic of human skeletons as the hierarchical orders among the joints are not explicitly presented. In this paper, we propose to represent the human skeleton as a directed graph with the joints as nodes and bones as edges that are directed from parent joints to child joints. By so doing, the directions of edges can explicitly reflect the hierarchical relationships among the nodes. Based on this representation, we further propose a spatial-temporal conditional directed graph convolution to leverage varying non-local dependence for different poses by conditioning the graph topology on input poses. Altogether, we form a U-shaped network, named U-shaped Conditional Directed Graph Convolutional Network, for 3D human pose estimation from monocular videos. To evaluate the effectiveness of our method, we conducted extensive experiments on two challenging large-scale benchmarks: Human3.6M and MPI-INF-3DHP. Both quantitative and qualitative results show that our method achieves top performance. Also, ablation studies show that directed graphs can better exploit the hierarchy of articulated human skeletons than undirected graphs, and the conditional connections can yield adaptive graph topologies for different poses.

Kaiwen Cui, Gongjie Zhang, Fangneng Zhan et al.

Generative Adversarial Networks (GANs) have become the de-facto standard in image synthesis. However, without considering the foreground-background decomposition, existing GANs tend to capture excessive content correlation between foreground and background, thus constraining the diversity in image generation. This paper presents a novel Foreground-Background Composition GAN (FBC-GAN) that performs image generation by generating foreground objects and background scenes concurrently and independently, followed by composing them with style and geometrical consistency. With this explicit design, FBC-GAN can generate images with foregrounds and backgrounds that are mutually independent in contents, thus lifting the undesirably learned content correlation constraint and achieving superior diversity. It also provides excellent flexibility by allowing the same foreground object with different background scenes, the same background scene with varying foreground objects, or the same foreground object and background scene with different object positions, sizes and poses. It can compose foreground objects and background scenes sampled from different datasets as well. Extensive experiments over multiple datasets show that FBC-GAN achieves competitive visual realism and superior diversity as compared with state-of-the-art methods.

Fangneng Zhan, Yingchen Yu, Rongliang Wu et al.

Generative adversarial networks (GANs) have achieved great success in image translation and manipulation. However, high-fidelity image generation with faithful style control remains a grand challenge in computer vision. This paper presents a versatile image translation and manipulation framework that achieves accurate semantic and style guidance in image generation by explicitly building a correspondence. To handle the quadratic complexity incurred by building the dense correspondences, we introduce a bi-level feature alignment strategy that adopts a top-$k$ operation to rank block-wise features followed by dense attention between block features which reduces memory cost substantially. As the top-$k$ operation involves index swapping which precludes the gradient propagation, we approximate the non-differentiable top-$k$ operation with a regularized earth mover's problem so that its gradient can be effectively back-propagated. In addition, we design a novel semantic position encoding mechanism that builds up coordinate for each individual semantic region to preserve texture structures while building correspondences. Further, we design a novel confidence feature injection module which mitigates mismatch problem by fusing features adaptively according to the reliability of built correspondences. Extensive experiments show that our method achieves superior performance qualitatively and quantitatively as compared with the state-of-the-art.

Jiahui Zhang, Shijian Lu, Fangneng Zhan et al.

Image super-resolution (SR) research has witnessed impressive progress thanks to the advance of convolutional neural networks (CNNs) in recent years. However, most existing SR methods are non-blind and assume that degradation has a single fixed and known distribution (e.g., bicubic) which struggle while handling degradation in real-world data that usually follows a multi-modal, spatially variant, and unknown distribution. The recent blind SR studies address this issue via degradation estimation, but they do not generalize well to multi-source degradation and cannot handle spatially variant degradation. We design CRL-SR, a contrastive representation learning network that focuses on blind SR of images with multi-modal and spatially variant distributions. CRL-SR addresses the blind SR challenges from two perspectives. The first is contrastive decoupling encoding which introduces contrastive learning to extract resolution-invariant embedding and discard resolution-variant embedding under the guidance of a bidirectional contrastive loss. The second is contrastive feature refinement which generates lost or corrupted high-frequency details under the guidance of a conditional contrastive loss. Extensive experiments on synthetic datasets and real images show that the proposed CRL-SR can handle multi-modal and spatially variant degradation effectively under blind settings and it also outperforms state-of-the-art SR methods qualitatively and quantitatively.