Monocular 3D pose estimation is fundamentally ill-posed due to depth ambiguity and occlusions, thereby motivating probabilistic methods that generate multiple plausible 3D pose hypotheses. In particular, diffusion-based models have recently demonstrated strong performance, but their iterative denoising process typically requires many timesteps for each prediction, making inference computationally expensive. In contrast, we leverage Flow Matching (FM) to learn a velocity field defined by an Ordinary Differential Equation (ODE), enabling efficient generation of 3D pose samples with only a few integration steps. We propose a novel generative pose estimation framework, FMPose3D, that formulates 3D pose estimation as a conditional distribution transport problem. It continuously transports samples from a standard Gaussian prior to the distribution of plausible 3D poses conditioned only on 2D inputs. Although ODE trajectories are deterministic, FMPose3D naturally generates various pose hypotheses by sampling different noise seeds. To obtain a single accurate prediction from those hypotheses, we further introduce a Reprojection-based Posterior Expectation Aggregation (RPEA) module, which approximates the Bayesian posterior expectation over 3D hypotheses. FMPose3D surpasses existing methods on the widely used human pose estimation benchmarks Human3.6M and MPI-INF-3DHP, and further achieves state-of-the-art performance on the 3D animal pose datasets Animal3D and CtrlAni3D, demonstrating strong performance across both 3D pose domains. The code is available at https://github.com/AdaptiveMotorControlLab/FMPose3D.
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
Training machine learning models on massive datasets is expensive and time-consuming. Dataset distillation addresses this by creating a small synthetic dataset that achieves the same performance as the full dataset. Recent methods use diffusion models to generate distilled data, either by promoting diversity or matching training gradients. However, existing approaches produce redundant training signals, where samples convey overlapping information. Empirically, disjoint subsets of distilled datasets capture 80-90% overlapping signals. This redundancy stems from optimizing visual diversity or average training dynamics without accounting for similarity across samples, leading to datasets where multiple samples share similar information rather than complementary knowledge. We propose learnability-driven dataset distillation, which constructs synthetic datasets incrementally through successive stages. Starting from a small set, we train a model and generate new samples guided by learnability scores that identify what the current model can learn from, creating an adaptive curriculum. We introduce Learnability-Guided Diffusion (LGD), which balances training utility for the current model with validity under a reference model to generate curriculum-aligned samples. Our approach reduces redundancy by 39.1%, promotes specialization across training stages, and achieves state-of-the-art results on ImageNet-1K (60.1%), ImageNette (87.2%), and ImageWoof (72.9%).
Text-to-video generation has significantly enriched content creation and holds the potential to evolve into powerful world simulators. However, modeling the vast spatiotemporal space remains computationally demanding, particularly when employing Transformers, which incur quadratic complexity in sequence processing and thus limit practical applications. Recent advancements in linear-time sequence modeling, particularly the Mamba architecture, offer a more efficient alternative. Nevertheless, its plain design limits its direct applicability to multimodal and spatiotemporal video generation tasks. To address these challenges, we introduce M4V, a multimodal Mamba framework for efficient text-to-video generation. Specifically, a MultiModal diffusion Mamba (MM-DiM) block is designed within the framework to enable seamless integration of multimodal information and spatiotemporal modeling. In detail, we introduce a novel multimodal token re-composition design, which employs a bidirectional scheme for multimodal information integration through simple token arrangement, along with visual registers to enhance spatial-temporal consistency. As a result, the MM-DiM blocks in M4V reduce FLOPs by 45% compared with the attention-based alternative when generating videos at 768x1280 resolution. Additionally, several training strategies are explored in this work to provide a better understanding of training text-to-video models using only publicly available datasets. Extensive experiments on text-to-video benchmarks demonstrate M4V's ability to produce high-quality videos while significantly lowering computational costs. Code will be made publicly available.
Diffusion Magnetic Resonance Imaging (dMRI) plays a critical role in studying microstructural changes in the brain. It is, therefore, widely used in clinical practice; yet progress in learning general-purpose representations from dMRI has been limited. A key challenge is that existing deep learning approaches are not well-suited to capture the unique properties of diffusion signals. Brain dMRI is normally composed of several brain volumes, each with different attenuation characteristics dependent on the direction and strength of the diffusion-sensitized gradients. Thus, there is a need to jointly model spatial, diffusion-weighting, and directional dependencies in dMRI. Furthermore, varying acquisition protocols (e.g., differing numbers of directions) further limit traditional models. To address these gaps, we introduce a diffusion space rotatory positional embedding (D-RoPE) plugged into our dMRI transformer to capture both the spatial structure and directional characteristics of diffusion data, enabling robust and transferable representations across diverse acquisition settings and an arbitrary number of diffusion directions. After self-supervised masked autoencoding pretraining, tests on several downstream tasks show that the learned representations and the pretrained model can provide competitive or superior performance compared to several baselines in these downstream tasks (even compared to a fully trained baseline); the finetuned features from our pretrained encoder resulted in a 6% higher accuracy in classifying mild cognitive impairment and a 0.05 increase in the correlation coefficient when predicting cognitive scores. Code is available at: github.com/gustavochau/D-RoPE
Latent inpainting in diffusion models still relies almost universally on linearly interpolating VAE latents under a downsampled mask. We propose a key principle for compositing image latents: Pixel-Equivalent Latent Compositing (PELC). An equivalent latent compositor should be the same as compositing in pixel space. This principle enables full-resolution mask control and true soft-edge alpha compositing, even though VAEs compress images 8x spatially. Modern VAEs capture global context beyond patch-aligned local structure, so linear latent blending cannot be pixel-equivalent: it produces large artifacts at mask seams and global degradation and color shifts. We introduce DecFormer, a 7.7M-parameter transformer that predicts per-channel blend weights and an off-manifold residual correction to realize mask-consistent latent fusion. DecFormer is trained so that decoding after fusion matches pixel-space alpha compositing, is plug-compatible with existing diffusion pipelines, requires no backbone finetuning and adds only 0.07% of FLUX.1-Dev's parameters and 3.5% FLOP overhead. On the FLUX.1 family, DecFormer restores global color consistency, soft-mask support, sharp boundaries, and high-fidelity masking, reducing error metrics around edges by up to 53% over standard mask interpolation. Used as an inpainting prior, a lightweight LoRA on FLUX.1-Dev with DecFormer achieves fidelity comparable to FLUX.1-Fill, a fully finetuned inpainting model. While we focus on inpainting, PELC is a general recipe for pixel-equivalent latent editing, as we demonstrate on a complex color-correction task.
Recent advances in text-to-audio (TTA) generation excel at synthesizing short audio clips but struggle with long-form narrative audio, which requires temporal coherence and compositional reasoning. To fill this gap, we propose AudioStory, a unified framework that integrates large language models (LLMs) with TTA systems to generate structured, long-form audio narratives. AudioStory possesses strong instruction-following reasoning generation capabilities. It employs LLMs to decompose complex narrative queries into temporally ordered sub-tasks with contextual cues, enabling coherent scene transitions and emotional tone consistency. AudioStory has two appealing features: (1) Decoupled bridging mechanism: AudioStory disentangles LLM-diffuser collaboration into two specialized components, i.e., a bridging query for intra-event semantic alignment and a residual query for inter-event coherence preservation. (2) End-to-end training: By unifying instruction comprehension and audio generation within a single end-to-end framework, AudioStory eliminates the need for modular training pipelines while enhancing synergy between components. Furthermore, we establish a benchmark AudioStory-10K, encompassing diverse domains such as animated soundscapes and natural sound narratives. Extensive experiments show the superiority of AudioStory on both single-audio generation and narrative audio generation, surpassing prior TTA baselines in both instruction-following ability and audio fidelity. Our code and dataset will be publicly available.
EMGauss: Continuous Slice-to-3D Reconstruction via Dynamic Gaussian Modeling in Volume Electron Microscopy
PDF ↗Volume electron microscopy (vEM) enables nanoscale 3D imaging of biological structures but remains constrained by acquisition trade-offs, leading to anisotropic volumes with limited axial resolution. Existing deep learning methods seek to restore isotropy by leveraging lateral priors; yet their assumptions break down for morphologically anisotropic structures. We present **EMGauss**, a general framework for 3D reconstruction from planar scanned 2D slices with applications in vEM, which circumvents the inherent limitations of isotropy-based approaches. Our key innovation is to reframe slice-to-3D reconstruction as a 3D dynamic scene rendering problem based on Gaussian splatting, where the progression of axial slices is modeled as the temporal evolution of 2D Gaussian point clouds. To enhance fidelity in data-sparse regimes, we incorporate a **Teacher-Student bootstrapping mechanism** that uses high-confidence predictions on unobserved slices as pseudo-supervisory signals. Compared with diffusion- and GAN-based reconstruction methods, EMGauss substantially improves interpolation quality, enables continuous slice synthesis, and eliminates the need for large-scale pretraining. Beyond vEM, it potentially provides a generalizable slice-to-3D solution across diverse imaging domains.
Pan-sharpening, a fundamental image preprocessing technique in remote sensing, aims to generate spatially and spectrally enriched multispectral imagery by integrating complementary information from texture-rich panchromatic (PAN) images and paired low-resolution multispectral (LRMS) counterparts. Although recent generative diffusion models have achieved impressive fusion quality, these performance gains often come with substantial computational costs, rendering them impractical for resource-constrained scenarios common in remote sensing applications. This work introduces a function-space diffusion model built upon a neural operator architecture that achieves compelling performance with promising efficiency. Specifically, our framework replaces the standard attention-based denoising backbone with a Galerkin-type neural operator, significantly reducing computational complexity while maintaining excellent representational capacity. Furthermore, by explicitly integrating pixel-wise spatial-spectral consistency residuals into each reverse diffusion step, our method establishes a fine-grained, closed-loop guidance mechanism that dynamically calibrates spatial details and spectral fidelity throughout the generation process. Extensive experiments on multiple benchmark datasets demonstrate the effectiveness of our approach over state-of-the-art methods.
Image classification is a well-studied task in computer vision, and yet it remains challenging under high-uncertainty conditions, such as when input images are corrupted or training data are limited. Conventional classification approaches typically train models to directly predict class labels from input images, but this might lead to suboptimal performance in such scenarios. To address this issue, we propose Discrete Diffusion Classification Modeling (DiDiCM), a novel framework that leverages a diffusion-based procedure to model the posterior distribution of class labels conditioned on the input image. DiDiCM supports diffusion-based predictions either on class probabilities or on discrete class labels, providing flexibility in computation and memory trade-offs. We conduct a comprehensive empirical study demonstrating the superior performance of DiDiCM over standard classifiers, showing that a few diffusion iterations achieve higher classification accuracy on the ImageNet dataset compared to baselines, with accuracy gains increasing as the task becomes more challenging. We release our code at https://github.com/omerb01/didicm.
We often aim to generate images that are both photorealistic and 3D-consistent, adhering to precise geometry, material, and viewpoint controls. Typically, this is achieved by fine-tuning an image generator, pre-trained on billions of real images, using renders of synthetic 3D assets, where annotations for control signals are available. While this approach can learn the desired controls, it often compromises the realism of the images due to domain gap between photographs and renders. We observe that this issue largely arises from the model learning an unintended association between the presence of control signals and the synthetic appearance of the images. To address this, we introduce Realiz3D, a lightweight framework for training diffusion models, that decouples controls and visual domain. The key idea is to explicitly learn visual domain, real or synthetic, separately from other control signals by introducing a co-variate that, fed into small residual adapters, shifts the domain. Then, the generator can be trained to gain controllability, without fitting to specific visual domain. In this way, the model can be guided to produce realistic images even when controls are applied. We enhance control transferability to the real domain by leveraging insights about roles of different layers and denoising steps in diffusion-based generators, informing new training and inference strategies that further mitigate the gap. We demonstrate the advantages of Realiz3D in tasks as text-to-multiview generation and texturing from 3D inputs, producing outputs that are 3D-consistent and photorealistic.
Recent advances in semantic correspondence rely on dual-encoder architectures, combining DINOv2 with diffusion backbones. While accurate, these billion-parameter models generalize poorly beyond training keypoints, revealing a gap between benchmark performance and real-world usability, where queried points rarely match those seen during training. Building upon DINOv2, we introduce MARCO, a unified model for generalizable correspondence driven by a novel training framework that enhances both fine-grained localization and semantic generalization. By coupling a coarse-to-fine objective that refines spatial precision with a self-distillation framework, which expands sparse supervision beyond annotated regions, our approach transforms a handful of keypoints into dense, semantically coherent correspondences. MARCO sets a new state of the art on SPair-71k, AP-10K, and PF-PASCAL, with gains that amplify at fine-grained localization thresholds (+8.9 PCK@0.01), strongest generalization to unseen keypoints (+5.1, SPair-U) and categories (+4.7, MP-100), while remaining 3x smaller and 10x faster than diffusion-based approaches.
The efficiency of hyperparameter optimization (HPO) is critical for deep learning, yet state-of-the-art methods share a fundamental flaw: they are difficulty-agnostic, treating all hyperparameter configurations homogeneously. This approach leads to inefficient resource allocation, wasting budget in simple regions while under-exploring complex, rugged landscapes, and thereby critically undermining both search efficiency and final performance. To address this universal challenge, we introduce DABO, a framework that pioneers difficulty-aware tuning within the efficient context of Freeze-Thaw Bayesian Optimization. We first model optimization difficulty hierarchically. Then, departing from hand-crafted priors, we train a conditional diffusion model on 120,000 real learning curves, generating synthetic data with 2.3xhigher fidelity. This data trains our difficulty-aware surrogate model and acquisition function to dynamically adapt the search strategy. Across 75 tasks, DABO reduces regret by 11-18% compared to the leading difficulty-agnostic method, ifBO. Our work establishes a new paradigm for HPO, shifting the focus from configuration-centric to difficulty-aware resource allocation to enable more robust and efficient optimization.
EasyOmnimatte: Taming Pretrained Inpainting Diffusion Models for End-to-End Video Layered Decompositio
PDF ↗Existing video omnimatte methods typically rely on slow, multi-stage, or inference-time optimization pipelines that fail to fully exploit powerful generative priors, producing suboptimal decompositions. Our key insight is that, if a video inpainting model can be finetuned to remove the foreground-associated effects, then it must be inherently capable of perceiving these effects, and hence can also be finetuned for the complementary task: foreground layer decomposition with associated effects. However, although naively finetuning the inpainting model with LoRA applied to all blocks can produce high-quality alpha mattes, it fails to capture associated effects. Our systematic analysis reveals this arises because effect-related cues are primarily encoded in specific DiT blocks and become suppressed when LoRA is applied across all blocks. To address this, we introduce EasyOmnimatte, the first unified, end-to-end video omnimatte method. Concretely, we finetune a pretrained video inpainting diffusion model to learn dual complementary experts while keeping its original weights intact: an Effect Expert, where LoRA is applied only to effect-sensitive DiT blocks to capture the coarse structure of the foreground and associated effects, and a fully LoRA-finetuned Quality Expert learns to refine the alpha matte. During sampling, Effect Expert is used for denoising at early, high-noise steps, while Quality Expert takes over at later, low-noise steps. This design eliminates the need for two full diffusion passes, significantly reducing computational cost without compromising output quality. Ablation studies validate the effectiveness of this Dual-Expert strategy. Experiments demonstrate that EasyOmnimatte sets a new state-of-the-art for video omnimatte and enables various downstream tasks, significantly outperforming baselines in both quality and efficiency.
Recent video diffusion models generate photorealistic, temporally coherent videos, yet they fall short as reliable world models for autonomous driving, where structured motion and physically consistent interactions are essential. Adapting these generalist video models to driving domains has shown promise but typically requires massive domain-specific data and costly fine-tuning. We propose an efficient adaptation framework that converts generalist video diffusion models into controllable driving world models with minimal supervision. The key idea is to decouple motion learning from appearance synthesis. First, the model is adapted to predict structured motion in a simplified form: videos of skeletonized agents and scene elements, focusing learning on physical and social plausibility. Then, the same backbone is reused to synthesize realistic RGB videos conditioned on these motion sequences, effectively "dressing" the motion with texture and lighting. This two-stage process mirrors a reasoning-rendering paradigm: first infer dynamics, then render appearance. Our experiments show this decoupled approach is exceptionally efficient: adapting SVD, we match prior SOTA models with less than 6% of their compute. Scaling to LTX, our MAD-LTX model outperforms all open-source competitors, and supports a comprehensive suite of text, ego, and object controls. Project page: \href https://vita-epfl.github.io/MAD-World-Model/ https://vita-epfl.github.io/MAD-World-Model/
OpenDPR: Open-Vocabulary Change Detection via Vision-Centric Diffusion-Guided Prototype Retrieval for Remote Sensing Imagery
PDF ↗Open-vocabulary change detection (OVCD) seeks to recognize arbitrary changes of interest by enabling generalization beyond a fixed set of predefined classes. We reformulate OVCD as a two-stage pipeline: first generate class-agnostic change proposals using visual foundation models (VFMs) such as SAM and DINOv2, and then perform category identification with vision-language models (VLMs) such as CLIP. We reveal that category identification errors are the primary bottleneck of OVCD, mainly due to the limited ability of VLMs based on image-text matching to represent fine-grained land-cover categories. To address this, we propose OpenDPR, a training-free vision-centric diffusion-guided prototype retrieval framework. OpenDPR leverages diffusion models to construct diverse prototypes for target categories offline, and to perform similarity retrieval with change proposals in the visual space during inference. The secondary bottleneck lies in change localization, due to the inherent lack of change priors in VFMs. To bridge this gap, we design a spatial-to-change weakly supervised change detection module named S2C to adapt their strong spatial modeling capabilities for change localization. Integrating the pretrained S2C into OpenDPR leads to an optional weakly supervised variant named OpenDPR-W, which further improves OVCD with minimal supervision. Experimental results on four benchmark datasets demonstrate that the proposed methods achieve state-of-the-art performance under both supervision modes. Code is available at https://github.com/guoqi2002/OpenDPR.
Visual tokenizers play a crucial role in diffusion models. The dimensionality of latent space governs both reconstruction fidelity and the semantic expressiveness of the latent feature. However, a fundamental trade-off is inherent between dimensionality and generation quality, constraining existing methods to low-dimensional latent spaces. Although recent works have leveraged vision foundation models (VFMs) to enrich the semantics of visual tokenizers and accelerate convergence, high-dimensional tokenizers still underperform their low-dimensional counterparts. In this work, we propose RecTok, which overcomes the limitations of high-dimensional visual tokenizers through two key innovations: flow semantic distillation and reconstruction-alignment distillation. Our key insight is to make the forward flow in flow matching semantically rich, which serves as the training space of diffusion transformers, rather than focusing on the latent space as in previous works. Specifically, our method distill the semantic information in VFMs into the forward flow trajectories in flow matching. And we further enhance the semantics by introducing a masked feature reconstruction loss. Our RecTok achieves superior image reconstruction, generation quality, and discriminative performance. It achieves state-of-the-art results on the gFID-50K under both with and without classifier-free guidance settings, while maintaining a semantically rich latent space structure. Furthermore, as the latent dimensionality increases, we observe consistent improvements. Code and model will be publicly available.
MaskDiME: Adaptive Masked Diffusion for Precise and Efficient Visual Counterfactual Explanations
PDF ↗Visual counterfactual explanations aim to reveal the minimal semantic modifications that can alter a model's prediction, providing causal and interpretable insights into deep neural networks. However, existing diffusion-based counterfactual generation methods are often computationally expensive, slow to sample, and imprecise in localizing the modified regions. To address these limitations, we propose MaskDiME, a simple, fast, yet effective diffusion framework that unifies semantic consistency and spatial precision through localized sampling. Our approach adaptively focuses on decision-relevant regions to achieve localized and semantically consistent counterfactual generation while preserving high image fidelity. Our training-free framework, MaskDiME, performs inference over 30x faster than the baseline and achieves comparable or state-of-the-art performance across five benchmark datasets spanning diverse visual domains, establishing a practical and generalizable solution for efficient counterfactual explanation. Our code is available at https://github.com/clguo/MaskDiME.
Diffusion Transformers (DiTs) have greatly advanced text-to-image generation, but models still struggle to generate the correct spatial relations between objects as specified in the text prompt. In this study, we adopt a mechanistic interpretability approach to investigate how a DiT can generate correct spatial relations between objects. We train, from scratch, DiTs of different sizes with different text encoders to learn to generate images containing two objects whose attributes and spatial relations are specified in the text prompt. We find that, although all the models can learn this task to near-perfect accuracy, the underlying mechanisms differ drastically depending on the choice of text encoder. When using random text embeddings, we find that the spatial-relation information is passed to image tokens through a two-stage circuit, involving two cross-attention heads that separately read the spatial relation and single-object attributes in the text prompt. When using a pretrained text encoder (T5), we find that the DiT uses a different circuit that leverages information fusion in the text tokens, reading spatial-relation and single-object information together from a single text token. We further show that, although the in-domain performance is similar for the two settings, their robustness to out-of-domain perturbations differs, potentially suggesting the difficulty of generating correct relations in real-world scenarios.
Aligning Diffusion models has achieved remarkable breakthroughs in generating high-quality, human preference-aligned images. Existing techniques, such as supervised fine-tuning (SFT) and DPO-style preference optimization, have become principled tools for fine-tuning diffusion models. However, SFT relies on high-quality images that are costly to obtain, while DPO-style methods depend on large-scale preference datasets, which are often inconsistent in quality. Beyond data dependency, these methods are further constrained by computational inefficiency. To address these two challenges, we propose Composite Reward Assisted Fine-Tuning (CRAFT), a lightweight yet powerful fine-tuning paradigm that requires significantly reduced training data while maintaining computational efficiency. It first leverages a Composite Reward Filtering (CRF) technique to construct a high-quality and consistent training dataset and then perform an enhanced variant of SFT. We also theoretically prove that CRAFT actually optimizes the lower bound of group-based reinforcement learning, establishing a principled connection between SFT with selected data and reinforcement learning. Our extensive empirical results demonstrate that CRAFT with only 100 samples can easily outperform recent SOTA preference optimization methods with thousands of preference-paired samples. Moreover, CRAFT can even achieve 11-220xfaster convergences than the baseline preference optimization methods, highlighting its extremely high efficiency.
Although recent work has explored generative modeling of 3D or 4D driving scenes, most approaches operate on dense voxel-based representations, which are computationally expensive and struggle to maintain temporal or structural consistency. These methods often produce blurred or merged entities (i.e., cars, trucks, pedestrians) and lack fine-grained control over individual scene elements. We propose LatentWorld, a framework for generative modeling in a compact, entity-centric latent space, where each grounded 3D latent represents a semantically meaningful local region of the scene. This formulation enables precise, consistent control of both foreground and background elements while preserving geometric detail. We further extend this representation to 4D by learning a motion diffusion model for both ego and dynamic actors, conditioned on the generated 3D scene, and by propagating the grounded latents through time. Our framework produces physically consistent and temporally coherent 4D scenes, supporting controllable and realistic generation.