CVPR 2026 论文列表

Few-step generation has been a long-standing goal, with recent one-step generation methods exemplified by MeanFlow achieving remarkable results. Existing research on MeanFlow primarily focuses on class-to-image generation. However, an intuitive yet unexplored direction is to extend the condition from fixed class labels to flexible text inputs, enabling richer content creation. Compared to the limited class labels, text conditions pose greater challenges to the model's understanding capability, necessitating the effective integration of powerful text encoders into the MeanFlow framework. Surprisingly, although incorporating text conditions appears straightforward, we find that integrating powerful LLM-based text encoders using conventional training strategies results in unsatisfactory performance. To uncover the underlying cause, we conduct detailed analyses and reveal that, due to the extremely limited number of refinement steps in the MeanFlow generation, such as only one step, the text feature representations are required to possess sufficiently high discriminability. This also explains why discrete and easily distinguishable class features perform well within the MeanFlow framework. Guided by these insights, we leverage a powerful LLM-based text encoder validated to possess the required semantic properties and adapt the MeanFlow generation process to this framework, resulting in efficient text-conditioned synthesis for the first time. Furthermore, we validate our approach on the widely used diffusion model, demonstrating significant generation performance improvements. We hope this work provides a general and practical reference for future research on text-conditioned MeanFlow generation. The code is available at \supp https://github.com/AMAP-ML/EMF.

Supervised and unsupervised homography estimation methods depend on image pairs tailored to specific modalities to achieve high accuracy. However, their performance deteriorates substantially when applied to unseen modalities. To address this issue, we propose a training data synthesis method that generates unaligned image pairs with ground-truth offsets from a single input image. Our approach renders the image pairs with diverse textures and colors while preserving their structural information. These synthetic data empower the trained model to achieve greater robustness and improved generalization across various domains. Additionally, we design a network to fully leverage cross-scale information and decouple color information from feature representations, thus improving estimation accuracy. Extensive experiments show that our training data synthesis method improves generalization performance. The results also confirm the effectiveness of the proposed network.

Reconstructing textured 3D human models from a single image is fundamental for AR/VR and digital human applications. However, existing methods mostly focus on single individuals and thus fail in multi-human scenes, where naive composition of individual reconstructions often leads to artifacts such as unrealistic overlaps, missing geometry in occluded regions, and distorted interactions. These limitations highlight the need for approaches that incorporate group-level context and interaction priors. We introduce a holistic method that explicitly models both group- and instance-level information. To mitigate perspective-induced geometric distortions, we first transform the input into a canonical orthographic space. Our primary component, Human Group-Instance Multi-View Diffusion (HUG-MVD), then generates complete multi-view normals and images by jointly modeling individuals and group context to resolve occlusions and proximity. Subsequently, the Human Group-Instance Geometric Reconstruction (HUG-GR) module optimizes the geometry by leveraging explicit, physics-based interaction priors to enforce physical plausibility and accurately model inter-human contact. Finally, the multi-view images are fused into a high-fidelity texture. Together, these components form our complete framework, HUG3D. Extensive experiments show that HUG3D significantly outperforms both single-human and existing multi-human methods, producing physically plausible, high-fidelity 3D reconstructions of interacting people from a single image.

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.

High-quality 3D assets are critical for VR/AR, industrial design, and entertainment, driving growing interest in generative models that can create 3D content from user-provided prompts. Most existing 3D generators, however, rely on a single conditioning modality: image-conditioned models deliver high visual fidelity by exploiting pixel-aligned cues but suffer from viewpoint bias when the input view is limited or ambiguous, whereas text-conditioned models benefit from broad semantic guidance yet lack low-level visual detail. This restricts how users can express their intent and raises a natural question: can the two modalities be combined to yield more flexible and faithful 3D generation? Our diagnostic study shows that even a simple late fusion of text- and image-conditioned predictions improves over single-modality models, evidencing strong cross-modal complementarity. Building on this finding, we formalize the task of Text-Image Conditioned 3D Generation, which requires joint reasoning over a visual exemplar and a textual specification during generation. To address this task, we introduce TIGON, a minimalist dual-branch baseline that maintains separate image- and text-conditioned backbones with lightweight cross-modal fusion. Extensive experiments demonstrate that text-image conditioning yields consistent gains over single-modality methods, suggesting complementary vision-language guidance as a promising direction for future 3D generation research.

As a representative technique in neural architecture search, neural architecture generation aims to construct high-performance architectures for a given task directly. It is poised to replace the inefficient random exploration components of some search strategies, such as the acquisition strategies in Bayesian optimization. Despite significant research, current architecture generation techniques face problems such as low generation efficiency and insufficient constraints, leading to invalidly generated architectures. To this end, we propose Progressive Neural Architecture Generation (PNAG), which constructs architectures incrementally through coarse-to-fine evolution, enhancing generation efficiency, and incorporates step-wise refinements to ensure the validity of the generated architecture. To achieve this, PNGA involves two modules, multi-scale sub-architecture quantization (MSQ) and step-wise consistency constraint (SCC). Specifically, MSQ constructs sub-architectures using quantization decoding and progressively expands them, transitioning from simple to complex forms. This operation bypasses network inference to enhance efficiency.Complementing MSQ, SCC, implemented through a tailored regularization mechanism, introduces penalties for deviations during sub-architecture generation, guiding the process towards valid target architectures. As such, PNAG establishes a clear generation path, laying the groundwork for generating suitable architectures in downstream tasks. Extensive experiments demonstrate that PNAG not only generates superior architectures for various downstream tasks (+8.43%/+5.07%, on average) but also significantly improves generation efficiency, reducing the architecture generation time by 1300x. Furthermore, PNAG demonstrates strong extensibility by successfully generating Transformer-based architectures.

Meshes serve as a primary representation for 3D assets. Autoregressive mesh generators serialize faces into sequences and train on truncated segments with sliding-window inference to cope with memory limits. However, this mismatch breaks long-range geometric dependencies, producing holes and fragmented components. To address this critical limitation, we introduce MeshRipple, which expands a mesh outward from an active generation frontier, akin to a ripple on a surface. MeshRipple rests on three key innovations: a frontier-aware BFS tokenization that aligns the generation order with surface topology; an expansive prediction strategy that maintains coherent, connected surface growth; and a sparse-attention global memory that provides an effectively unbounded receptive field to resolve long-range topological dependencies. This integrated design enables MeshRipple to generate meshes with high surface fidelity and topological completeness, outperforming strong recent 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.

Multimodal generative models can process instructions in various modalities and demonstrate outstanding performance across a wide range of image generation tasks. However, their robustness in complex real-world scenarios remains limited due to insufficient generalized instruction alignment. We introduce OmniGen2, a unified multimodal generator designed to follow complex, fine-grained instructions. Our core contribution is a two-stage design that first builds a strong, world-knowledge-grounded foundation model and then aligns it using a progressive, multi-task instruction tuning strategy. The foundation model features a streamlined architecture with decoupled decoding for versatile multimodal generation and a novel positional encoding scheme to improve learning efficiency. We ground this model in real-world knowledge using large-scale data construction pipelines. Building on this foundation, we propose a progressive, reinforcement-based alignment process. This phase carefully schedules training tasks and reward signals to foster cross-task knowledge transfer, significantly improving the model's instruction-following capabilities. Our models demonstrate competitive performance on standard benchmarks and our dedicated in-context generation benchmark, OmniContext. We have released our models, code, benchmark, and training datasets at https://github.com/VectorSpaceLab/OmniGen2.

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.

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.

Event cameras hold excellent dynamic properties, showing great potential for monocular depth estimation (MDE). However, existing methods mainly improve performance by optimizing contextual features, but still struggle with the ill-posed and nonlinear nature of direct full-depth regression. In this paper, we propose HypoDepth, the first event-image monocular depth iterative refinement framework. By introducing a discrete Depth Hypothesis Volume (DHV), we transform the depth regression problem into a constrained depth search task. Specifically, we construct a 3D cost volume between the DHV features and contextual features and perform a multi-scale correlation search to guide stable residual optimization. This lightweight cost volume enables efficient global-to-local refinement across multi-resolution. Our method outperforms existing approaches on DSEC and MVSEC with state-of-the-art results and strong zero-shot generalization. Meanwhile, our tiny model achieves an excellent balance between accuracy and efficiency, enabling real-time performance on resource-limited devices.

Multilingual text-to-image (T2I) models have advanced rapidly in terms of visual realism and semantic alignment, and are now widely utilised. Yet outputs vary across cultural contexts: because language carries cultural connotations, images synthesized from multilingual prompts should preserve cross-lingual cultural consistency. We conduct a comprehensive analysis showing that current T2I models often produce culturally neutral or English-biased results under multilingual prompts.Analyses of two representative models indicate that the issue stems not from missing cultural knowledge but from insufficient activation of culture-related representations. We propose a probing method that localizes culture-sensitive signals to a small set of neurons in a few fixed layers. Guided by this finding, we introduce two complementary alignment strategies: (1) inference-time cultural activation that amplifies the identified neurons without backbone fine-tuned; and (2) layer-targeted cultural enhancement that updates only culturally relevant layers. Experiments on our CultureBench demonstrate consistent improvements over strong baselines in cultural consistency while preserving fidelity and diversity.

Recent unified multimodal models (UMMs) have achieved remarkable progress in visual comprehension and generation. However, existing datasets and benchmarks focus predominantly on single-turn interactions, overlooking the multi-turn, context-dependent nature of real-world image creation and editing. To bridge this gap, we introduce W E A V E, the first comprehensive suite for in-context interleaved cross-modality comprehension and generation, comprising two complementary components. W E A V E-100k is a large-scale dataset of 100,000 interleaved samples spanning over 370,000 dialogue turns and 500,000 images, encompassing comprehension, editing, and generation tasks that demand reasoning over prior context. W E A V E-Bench is a human-annotated benchmark of 100 items with 480 images, equipped with a hybrid VLM judge evaluation framework that jointly leverages reference images and original-image-instruction pairs to assess multi-turn generation, visual memory, and world-knowledge reasoning across diverse domains. Experiments show that training on W E A V E-100k substantially improves vision comprehension, image editing, and comprehension-generation collaboration, while further enabling the emergence of visual-memory capabilities in UMMs. Extensive evaluations on W E A V E-Bench reveal persistent limitations of current approaches in multi-turn, context-aware image generation and editing. We hope W E A V E provides both a perspective and a foundation for advancing in-context interleaved comprehension and generation in the multimodal community.

Text-Image Person Re-Identification (TI-ReID) is widely deployed in intelligent surveillance. Built on deep neural networks and vision-language models, TI-ReID models inherit vulnerabilities to adversarial attacks, posing security risks. Yet its security remains less explored than retrieval accuracy, and its robustness to adversarial attacks is largely unexplored. To fill this gap, we propose Reconstruction-residual based Targeted and Untargeted Attack (R^2TUA), which generates perturbations from an image and adversarial prompt that mislead TI-ReID into matching the perturbed image with the adversarial identity. To precisely inject identity attributes into perturbations and achieve fine-grained targeted attack, R^2TUA proposes Transformer-based Gradual Multimodal Fusion (TGMF) that fuses image and adversarial prompt progressively across layers with tunable cross-modal weight. In addition, we propose a fully differentiable Soft Clamp Function (SCF), ensuring perturbations remain inconspicuous while avoiding local gradient vanishing effects that would trap training into suboptimal local minima. To further align perturbed images with the adversarial text descriptions while leading them to mismatch their original descriptions, R^2TUA employs (PPLs) and matching losses during training. Extensive evaluations across multiple datasets and models demonstrate the superior untargeted attack and targeted attack performance of R^2TUA. It also exhibits strong adaptability and transferability against black-box models, outperforming all related attacks across multiple tasks.

Existing concept customization methods have achieved remarkable outcomes in high-fidelity and multi-concept customization. However, they often neglect the influence on the original model's behavior and capabilities when learning new personalized concepts. To address this issue, we propose PureCC. PureCC introduces a novel decoupled learning objective for concept customization, which combines the implicit guidance of the target concept with the original conditional prediction. This separated form enables PureCC to substantially focus on the original model during training. Moreover, based on this objective, PureCC designs a dual-branch training pipeline that includes a frozen extractor providing purified target concept representations as implicit guidance and a trainable flow model producing the original conditional prediction, jointly achieving pure learning for personalized concepts. Furthermore, PureCC introduces a novel adaptive guidance scale l* to dynamically adjust the guidance strength of the target concept, balancing customization fidelity and model preservation. Extensive experiments show that PureCC achieves state-of-the-art performance in preserving the original behavior and capabilities while enabling high-fidelity concept customization.

Transformers rely on explicit positional encoding to model structure in data. WhileRotary Position Embedding (RoPE) excels in 1D domains, its application to image generation reveals significant limitations such as fine-grained spatial relationmodeling, color cues, and object counting. This paper identifies key limitationsof standard multi-dimensional RoPE--rigid frequency allocation, axis-wise independence, and uniform head treatment--in capturing the complex structural biasesrequired for fine-grained image generation. We propose HARoPE, a head-wiseadaptive extension that inserts a learnable linear transformation parameterized viasingular value decomposition (SVD) before the rotary mapping. This lightweightmodification enables dynamic frequency reallocation, semantic alignment of rotaryplanes, and head-specific positional receptive fields while rigorously preservingRoPE's relative-position property. Extensive experiments on class-conditional ImageNet and text-to-image generation (Flux and MMDiT) demonstrate that HARoPEconsistently improves performance over strong RoPE baselines and other extensions. The method serves as an effective drop-in replacement, offering a principledand adaptable solution for enhancing positional awareness in transformer-basedimage generative models.

We present FlowFixer, a refinement framework for subject-driven generation (SDG) that restores fine details lost during generation caused by changes in scale and perspective of a subject. FlowFixer proposes direct image-to-image translation from visual references, avoiding ambiguities in language prompts. To enable image-to-image training, we introduce a one-step denoising scheme to generate self-supervised training data, which automatically removes high-frequency details while preserving global structure, effectively simulating real-world SDG errors. We further propose a keypoint matching-based metric to properly assess fidelity in details beyond semantic similarities usually measured by CLIP or DINO. Experimental results demonstrate that FlowFixer outperforms state-of-the-art SDG methods in both qualitative and quantitative evaluations, setting a new benchmark for high-fidelity subject-driven generation.