Emerging video diffusion models achieve high visual fidelity but fundamentally couple scene dynamics with camera motion, limiting their ability to provide precise spatial and temporal control. We introduce a 4D-controllable video diffusion framework that explicitly decouples scene dynamics from camera pose, enabling fine-grained manipulation of both scene dynamics and camera viewpoint. Our framework takes continuous world-time sequences and camera trajectories as conditioning inputs, injecting them into the video diffusion model through a 4D positional embedding in the attention layer and adaptive normalizations for feature modulation. To train this model, we curate a unique dataset in which temporal and camera variations are independently parameterized. Experiments show that our model achieves robust real-world 4D control across diverse timing patterns and camera trajectories, while preserving high generation quality and outperforming prior work in controllability.
论文检索
输入标题、作者或关键词，从 9,256 篇学术成果中精准定位
Reconstructing a dynamic target moving over a large area is challenging. Standard approaches for dynamic object reconstruction require dense coverage in both the viewing space and the temporal dimension, typically relying on multi-view videos captured at each time step.However, such setups are only possible in constrained environments. In real-world scenarios, observations are often sparse over time and captured sparsely from diverse viewpoints (e.g., from security cameras), making dynamic reconstruction highly ill-posed. We present SV-GS, a framework that simultaneously estimates a deformation model and the object's motion over time under sparse observations. To initialize SV-GS, we leverage a rough skeleton graph and an initial static reconstruction as inputs to guide motion estimation. (Later, we show that this input requirement can be relaxed.) Our method optimizes a skeleton-driven deformation field composed of a coarse skeleton joint pose estimator and a module for fine-grained deformations. By making only the joint pose estimator time-dependent, our model enables smooth motion interpolation while preserving learned geometric details. Experiments on synthetic datasets show that our method outperforms existing approaches under sparse observations by up to 34% in PSNR, and achieves comparable performance to dense monocular video methods on real-world datasets despite using significantly fewer frames. Moreover, we demonstrate that the input initial static reconstruction can be replaced by a diffusion-based generative prior, making our method more practical for real-world scenarios.
CubeComposer: Spatio-Temporal Autoregressive 4K 360deg Video Generation from Perspective Video
PDF ↗Generating high-quality 360deg panoramic videos from perspective input is one of the crucial applications for virtual reality (VR), whereby high-resolution videos are especially important for immersive experience. Existing methods are constrained by computational limitations of vanilla diffusion models, only supporting <= 1K resolution native generation and relying on suboptimal post-hoc super-resolution. We introduce CubeComposer, a novel spatio-temporal autoregressive diffusion model that natively generates 4K-resolution 360deg videos. By decomposing videos into cubemap representations with six faces, CubeComposer autoregressively synthesizes content in a well-planned spatio-temporal order, reducing peak memory demands while enabling high-resolution output. Specifically, to address challenges in multi-dimensional autoregression, we propose: (1) a spatio-temporal autoregressive strategy that orchestrates 360deg video generation across cube faces and time windows for coherent synthesis; (2) a cube face context management mechanism, equipped with a sparse context attention design to improve efficiency; and (3) continuity-aware techniques, including cube-aware positional encoding, padding, and blending to eliminate boundary seams. Extensive experiments on benchmark datasets demonstrate that CubeComposer outperforms state-of-the-art methods in native resolution and visual quality, supporting practical VR application scenarios.
When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models
PDF ↗Text-to-video diffusion models have enabled open-ended video synthesis, but often struggle with generating the correct number of objects specified in a prompt. We introduce NUMINA, a training-free identify-then-guide framework for improved numerical alignment. NUMINA identifies prompt-layout inconsistencies by selecting discriminative self- and cross-attention heads to derive a countable latent layout. It then refines this layout conservatively and modulates cross-attention to guide regeneration. On the introduced CountBench, NUMINA improves counting accuracy by up to 7.4% on Wan2.1-1.3B, and by 4.9% and 5.5% on 5B and 14B models, respectively. Furthermore, CLIP alignment is improved while maintaining temporal consistency. These results demonstrate that structural guidance complements seed search and prompt enhancement, offering a practical path toward count-accurate text-to-video diffusion. The code is available at https://github.com/H-EmbodVis/NUMINA.
Diffusion models have become the dominant tool for high-fidelity image and video generation, yet are critically bottlenecked by their inference speed due to the numerous iterative passes of Diffusion Transformers. To reduce the exhaustive compute, recent works resort to the feature caching and reusing scheme that skips network evaluations at selected diffusion steps by using cached features in previous steps. However, their preliminary design solely relies on local approximation, causing errors to grow rapidly with large skips and leading to degraded sample quality at high speedups. In this work, we propose spectral diffusion feature forecaster (Spectrum), a training-free approach that enables global, long-range feature reuse with tightly controlled error. In particular, we view the latent features of the denoiser as functions over time and approximate them with Chebyshev polynomials. Specifically, we fit the coefficient for each basis via ridge regression, which is then leveraged to forecast features at multiple future diffusion steps. We theoretically reveal that our approach admits more favorable long-horizon behavior and yields an error bound that does not compound with the step size. Extensive experiments on various state-of-the-art image and video diffusion models consistently verify the superiority of our approach. Notably, we achieve up to 4.79x speedup on FLUX.1 and 4.67x speedup on Wan2.1-14B, while maintaining much higher sample quality compared with the baselines.
We present FloodDiffusion, a new framework for text-driven, streaming human motion generation. Given time-varying text prompts, FloodDiffusion generates text-aligned, seamless motion sequences with real-time latency.Unlike existing methods that rely on chunk-by-chunk or auto-regressive model with diffusion head, we adopt a diffusion forcing framework to model this time-series generation task under time-varying control events.We find that a straightforward implementation of vanilla diffusion forcing (as proposed for video models) fails to model real motion distributions. We demonstrate that to guarantee modeling the output distribution, the vanilla diffusion forcing must be tailored to: (i) train with a bi-directional attention instead of casual attention; (ii) implement a lower triangular time scheduler instead of a random one; (iii) utilize a continues time-varying way to introduce text conditioning.With these improvements, we demonstrate in the first time that the diffusion forcing-based framework achieves state-of-the-art performance on the streaming motion generation task, reaching an FID of 0.057 on the HumanML3D benchmark. Models, code, and weights are available.
Classifier-Free Guidance (CFG) is a widely used inference-time technique to boost the image quality of diffusion models. Yet, its reliance on text conditions prevents its use in unconditional generation. We propose a simple method to enable CFG-like guidance for both conditional and unconditional generation. The key idea is to generate a perturbed prediction via simple token swap operations, and use the direction between it and the clean prediction to steer sampling towards higher-fidelity distributions. In practice, we swap pairs of most semantically dissimilar token latents in either spatial or channel dimensions. Unlike existing methods that apply perturbation in a global or less constrained manner, our approach selectively exchanges and recomposes token latents, allowing finer control over perturbation and its influence on generated samples. Experiments on MS-COCO 2014, MS-COCO 2017, and ImageNet datasets demonstrate that the proposed Self-Swap Guidance (SSG), when applied to popular diffusion models, outperforms previous condition-free methods in image fidelity and prompt alignment under different set-ups. Its fine-grained perturbation granularity also improves robustness, reducing side-effects across a wider range of perturbation strengths. Overall, SSG extends CFG to a broader scope of applications including both conditional and unconditional generation, and can be readily inserted into any diffusion model as a plug-in to gain immediate improvements.
M3DLayout: A Multi-Source Dataset of 3D Indoor Layouts and Structured Descriptions for 3D Generation
PDF ↗In text-driven 3D scene generation, object layout serves as a crucial intermediate representation that bridges high-level language instructions with detailed geometric output. It not only provides a structural blueprint for ensuring physical plausibility but also supports semantic controllability and interactive editing. However, the learning capabilities of current 3D indoor layout generation models are constrained by the limited scale, diversity, and annotation quality of existing datasets. To address this, we introduce M3DLayout, a large-scale, multi-source dataset for 3D indoor layout generation. M3DLayout comprises 21,367 layouts and over 433k object instances, integrating three distinct sources: real-world scans, professional CAD designs, and procedurally generated scenes. Each layout is paired with detailed structured text describing global scene summaries, relational placements of large furniture, and fine-grained arrangements of smaller items. This diverse and richly annotated resource enables models to learn complex spatial and semantic patterns across a wide variety of indoor environments. To assess the potential of M3DLayout, we establish a benchmark using both a text-conditioned diffusion model and a text-conditioned autoregressive model. Experimental results demonstrate that our dataset provides a solid foundation for training layout generation models. Its multi-source composition enhances diversity, notably through the Inf3DLayout subset which provides rich small-object information, enabling the generation of more complex and detailed scenes. We hope that M3DLayout can serve as a valuable resource for advancing research in text-driven 3D scene synthesis. All dataset and code will be made public upon acceptance.
A fundamental dilemma in generative modeling persists: iterative diffusion models achieve outstanding fidelity, but at a significant computational cost, while efficient few-step alternatives are constrained by a hard quality ceiling. This conflict between generation steps and output quality arises from restrictive training objectives that focus exclusively on either infinitesimal dynamics (PF-ODEs) or direct endpoint prediction. We address this challenge by introducing an exact, continuous-time dynamics equation that analytically defines state transitions across any finite time interval (\Delta t). This leads to a novel generative paradigm, Transition Models (TiM), which adapt to arbitrary-step transitions, seamlessly traversing the generative trajectory from single leaps to fine-grained refinement with more steps.Despite having only 865M parameters, TiM achieves state-of-the-art performance, surpassing leading models such as SD3.5 (8B parameters) and FLUX.1 (12B parameters) across all evaluated step counts. Importantly, unlike previous few-step generators, TiM demonstrates monotonic quality improvement as the sampling budget increases. Additionally, when employing our native-resolution strategy, TiM delivers exceptional fidelity at resolutions up to (4096x4096).
SDUIE: Semi-Supervised Diffusion for Underwater Image Enhancement with Quant-Text Dual Control
PDF ↗Underwater images often exhibit dominant blue-green hues due to wavelength-dependent light attenuation. While existing enhancement methods have achieved promising performance, they typically overlook the subjective nature of visual preferences. To address this gap, we propose SDUIE, a level-aware Semi-supervised Diffusion framework for Underwater Image Enhancement that enables dual control through both quantitative and textual inputs. SDUIE-Quant allows continuous, numerical adjustment of enhancement levels via low-rank adaptation weight merging within a dual-branch diffusion model. This model comprises a supervised branch trained on synthetic underwater-terrestrial pairs and a self-supervised branch designed to preserve the natural hues of real-world underwater scenes. Building on this, SDUIE-Text introduces intuitive, language-guided control by aligning semantic prompts with visual enhancement effects, leveraging the learned fusion weights. This dual-modality design offers both precise control and flexible, user-preferred enhancement. Experimental results demonstrate that SDUIE achieves state-of-the-art results while better preserving the aesthetic qualities often missed by conventional methods. The source code is in https://github.com/Xiaofeng-life/SDUIE.
Large video diffusion and flow models have achieved remarkable success in high-quality video generation, but their use in real-time interactive applications remains limited due to their inefficient multi-step sampling process. In this work, we present Transition Matching Distillation (TMD), a novel framework for distilling video diffusion models into efficient few-step generators. The central idea of TMD is to match the multi-step denoising trajectory of a diffusion model with a few-step probability transition process, where each transition is modeled as a lightweight conditional flow. To enable efficient distillation, we decompose the original diffusion backbone into two components: (1) a main backbone, comprising the majority of early layers, that extracts semantic representations at each outer transition step; and (2) a flow head, consisting of the last few layers, that leverages these representations to perform multiple inner flow updates. Given a pretrained video flow model, we first introduce a flow head to the model, and adapt it into a conditional flow map. We then apply distribution matching distillation to the student model with flow head rollout in each transition step. Extensive experiments on distilling Wan2.1 1.3B and 14B text-to-video models demonstrate that TMD provides a flexible and strong trade-off between generation speed and visual quality. In particular, TMD outperforms existing distilled models under comparable inference costs in terms of visual fidelity and prompt adherence.
Today's denoising diffusion models do not "denoise" in the classical sense, i.e., they do not directly predict clean images. Rather, the neural networks predict noise or a noised quantity. In this paper, we suggest that predicting clean data and predicting noised quantities are fundamentally different. According to the manifold assumption, natural data should lie on a low-dimensional manifold, whereas noised quantities do not. With this assumption, we advocate for models that directly predict clean data, which allows apparently under-capacity networks to operate effectively in very high-dimensional spaces. We show that simple, large-patch Transformers on pixels can be strong generative models: using no tokenizer, no pre-training, and no extra loss. Our approach is conceptually nothing more than "Just image Transformers", or JiT, as we call it. We report competitive results using JiT with large patch sizes of 16 and 32 on ImageNet at resolutions of 256 and 512, where predicting high-dimensional noised quantities can fail catastrophically. With our networks mapping back to the basics of the manifold, our research goes back to basics and pursues a self-contained paradigm for Transformer-based diffusion on raw natural data.
Beyond the commonly recognized optical aberrations, the imaging performance of simplified optical systems--including single-lens and metalens designs--is often further degraded by veiling glare caused by stray-light scattering from non-ideal optical surfaces and coatings, particularly in complex real-world environments.This compound degradation undermines traditional lens aberration correction yet remains underexplored. A major challenge is that conventional scattering models (e.g., for dehazing) fail to fit veiling glare due to its spatial-varying and depth-independent nature.Consequently, paired high-quality data are difficult to prepare via simulation, hindering application of data-driven veiling glare removal models.To this end, we propose VeilGen, a generative model that learns to simulate veiling glare by estimating its underlying optical transmission and glare maps in an unsupervised manner from target images, regularized by Stable Diffusion (SD)-based priors.VeilGen enables paired dataset generation with realistic compound degradation of optical aberrations and veiling glare, while also providing the estimated latent optical transmission and glare maps to guide the veiling glare removal process.We further introduce DeVeiler, a restoration network trained with a reversibility constraint, which utilizes the predicted latent maps to guide an inverse process of the learned scattering model.Extensive experiments on challenging compact optical systems demonstrate that our approach delivers superior restoration quality and physical fidelity compared with existing methods.These suggest that VeilGen reliably synthesizes realistic veiling glare, and its learned latent maps effectively guide the restoration process in DeVeiler. All code and datasets will be publicly released.
Infinity-RoPE: Action-Controllable Infinite Video Generation Emerges From Autoregressive Self-Rollout
PDF ↗Current autoregressive video diffusion models are constrained by three core bottlenecks: (i) the finite temporal horizon imposed by the base model's 3D Rotary Positional Embedding (3D-RoPE), (ii) slow prompt responsiveness in maintaining fine-grained action control during long-form rollouts, and (iii) the inability to realize discontinuous cinematic transitions within a single generation stream. We introduce Infinity-RoPE, a unified inference-time framework that addresses all three limitations through three interconnected components: Block-Relativistic RoPE, KV Flush, and RoPE Cut. Block-Relativistic RoPE reformulates temporal encoding as a moving local reference frame, where each newly generated latent block is rotated relative to the base model's maximum frame horizon while earlier blocks are rotated backward to preserve relative temporal geometry. This relativistic formulation eliminates fixed temporal positions, enabling continuous video generation far beyond the base positional limits. To obtain fine-grained action control without re-encoding, KV Flush renews the KV cache by retaining only two anchor tokens, the global sink and the last generated latent frame, thereby ensuring immediate prompt responsiveness. Finally, RoPE Cut introduces controlled discontinuities in temporal RoPE coordinates, enabling multi-cut scene transitions within a single continuous rollout. Together, these components establish Infinity-RoPE as a training-free foundation for infinite-horizon, controllable, and cinematic video diffusion. Comprehensive experiments show that Infinity-RoPE consistently surpasses previous autoregressive models in overall VBench scores while requiring only a fraction of their KV cache budget.
Discrete Diffusion Models (DDMs) have shown great potential in image generation, especially when equipped with reinforcement learning (RL) techniques.However, a fundamental yet overlooked limitation is revealed in our experiments: severe imbalance of credit assignment across timesteps during training. As a result, early generation timesteps, which carry higher exploration potential and determine the global structure, provide a smaller contribution to policy optimization.To conquer this, we propose a simple-yet-effective approach, to Re-balance timestep credit of Reinforcement Learning (RebRL) for better exploration-exploitation trade-off and more efficient training of DDMs.RebRL is plug-and-play\textemdash simply replacing uniform temporal policy with strategic rebalancing along masking stages. RebRL is analytically plausible\textemdashderivation and analysis show that it enjoys a uniform token-level policy gradient, which benefits policy optimization.Experiments on text-to-image generation benchmarks show that RebRL achieves state-of-the-art performance on GenEval and improves human preference score by up to 3.40 while effectively reducing training steps by ~40\%.
Video-to-Speech (VTS) generation aims to synthesize speech from a silent video without auditory signals, and holds substantial promise for applications such as film dubbing and voice restoration for individuals with aphonia. However, existing VTS methods disregard the hierarchical nature of speech, which spans coarse speaker-aware semantics to fine-grained prosodic details. This oversight hinders direct alignment between visual and speech features at specific hierarchical levels during property matching. In this paper, leveraging the hierarchical structure of Residual Vector Quantization (RVQ)-based codec, we propose HiCoDiT, a novel Hierarchical Codec Diffusion Transformer that exploits the inherent hierarchy of discrete speech tokens to achieve strong audio-visual alignment. Specifically, since lower-level tokens encode coarse speaker-aware semantics and higher-level tokens capture fine-grained prosody, HiCoDiT employs low-level and high-level blocks to generate tokens at different levels. The low-level blocks condition on lip-synchronized motion and facial identity to capture speaker-aware content, while the high-level blocks use facial expression to modulate prosodic dynamics. Finally, to enable more effective coarse-to-fine conditioning, we propose a dual-scale adaptive instance layer normalization that jointly captures global vocal style through channel-wise normalisation and local prosody dynamics through temporal-wise normalization. Extensive experiments demonstrate that HiCoDiT outperforms baselines in fidelity and expressiveness, highlighting the potential of discrete modelling for VTS. The code and speech demo are both available at https://github.com/Jiaxin-Ye/HiCoDiT.
Diff-SemiER: Transparency-Aware Adaptive Fusion Diffusion Model with Generative Prior for Semi-Transparent Eyeglasses Removal
PDF ↗Existing eyeglasses removal methods primarily focus on opaque or fully transparent lenses. However, when dealing with semi-transparent sunglasses, these methods often corrupt the visible facial details beneath the lenses, thereby degrading the performance of downstream vision tasks. To address this issue, we propose Diff-SemiER, a novel diffusion-based framework for semi-transparent eyeglasses removal that leverages generative priors and transparency-aware adaptive fusion. The proposed framework fully utilizes the visible eye-region information beneath the lenses while retaining sufficient generative flexibility, thereby striking a balance between generation and restoration within semi-transparent regions. Specifically, Diff-SemiER comprises two diffusion branches: the Generative Prior Diffusion Model (GPDM) generates high-quality eyeglass-free facial images via image inpainting, which provides global semantic guidance for highly occluded scenarios. The Transparency-Aware Adaptive Fusion Diffusion Model (TAFDM) employs a Soft Mask-Aware Adaptive Fusion (SMAF) mechanism to adaptively merge generative and restorative features across multiple scales, enabling dynamic trade-offs between generative capability and fine-detail preservation under varying occlusion levels. Furthermore, we design a transmittance-based data synthesis method to construct a large-scale, high-quality dataset of faces with semi-transparent eyeglasses for model training and evaluation. Extensive experimental results demonstrate that Diff-SemiER significantly outperforms state-of-the-art methods in both synthetic and real-world scenarios.
MUST: Modality-Specific Representation-Aware Transformer for Diffusion-Enhanced Survival Prediction with Missing Modality
PDF ↗Accurate survival prediction from multimodal medical data is essential for precision oncology, yet clinical deployment faces a persistent challenge: modalities are frequently incomplete due to cost constraints, technical limitations, or retrospective data availability. While recent methods attempt to address missing modalities through feature alignment or joint distribution learning, they fundamentally lack explicit modeling of the unique contributions of each modality as opposed to the information derivable from other modalities. We propose a novel framework that explicitly decomposes each modality's representation into modality-specific and cross-modal contextualized components through algebraic constraints in a learned low-rank shared subspace. This decomposition enables us to identify precisely what information is missing when a modality is absent. For the truly modality-specific information that cannot be inferred from available modalities, we employ conditional latent diffusion models to generate high-quality representations conditioned on recovered shared information and learned structural priors. Extensive experiments on five TCGA cancer datasets demonstrate that the proposed method achieves state-of-the-art performance with complete data while maintaining robust predictions in both missing pathology and missing genomics conditions.
Diffusion and flow matching models generate high-fidelity data by simulating paths defined by Ordinary or Stochastic Differential Equations (ODEs/SDEs), starting from a tractable prior distribution. The probability flow ODE formulation enables the use of advanced numerical solvers to accelerate sampling. Orthogonal yet vital to solver design is the discretization strategy. While early approaches employed handcrafted heuristics and recent methods adopt optimization-based techniques, most existing strategies enforce a globally shared timestep schedule across all samples. This uniform treatment fails to account for instance-specific complexity in the generative process, potentially limiting performance.Motivated by controlled experiments on synthetic data, which reveals the suboptimality of global schedules under instance-specific dynamics, we propose an instance-aware discretization framework. Our method learns to adapt timestep allocations based on input-dependent priors, extending gradient-based discretization search to the conditional generative setting. Empirical results across diverse settings, including synthetic data, pixel-space diffusion, latent-space images and video flow matching models, demonstrate that our method consistently improves generation quality with marginal tuning cost compared to training and negligible inference overhead.
Human motion recovery for real-world interaction demands both precise action details and metric-scale trajectories. Recovering absolute human pose from monocular input presents a viable solution, but faces two main challenges: (1) models' reliance on 3D training data from constrained environments limits their out-of-distribution generalization; and (2) the inherent difficulty of estimating metric-scale poses from monocular observations. This paper introduces Mocap-2-to-3, a novel framework that differs from prior HMR methods by recovering absolute poses from monocular input and leveraging abundant 2D data to enhance 3D motion recovery. To effectively utilize the action priors and diversity in large-scale 2D datasets, we reformulate 3D motion as a multi-view synthesis process and divide the training into two stages: a single-view diffusion model is first pre-trained on extensive 2D data, followed by multi-view fine-tuning on 3D data, thus achieving a combination of strong priors and geometric constraints. Furthermore, to recover absolute poses, we introduce a novel human motion representation that decouples the learning of local pose and global movements, while encoding ground geometric priors to accelerate convergence, thereby yielding more precise positioning in the physical world. Experiments on in-the-wild benchmarks show that our method outperforms state-of-the-art approaches in both camera-space motion realism and world-grounded human positioning, while exhibiting strong generalization capability.