arXiv subjects

Hao Luo

Publications and source records attributed to Hao Luo.

At least 73 records · Page 4Linked to original sources

arXiv2025

Accurate and lightweight dehazing via multi-receptive-field non-local network and novel contrastive regularization

Recently, deep learning-based methods have dominated image dehazing domain. A multi-receptive-field non-local network (MRFNLN) consisting of the multi-stream feature attention block (MSFAB) and the cross non-local block (CNLB) is presented in this paper to further enhance the performance. We start with extracting richer features for dehazing. Specifically, a multi-stream feature extraction (MSFE) sub-block, which contains three parallel convolutions with different receptive fields (i.e., $1\times 1$, $3\times 3$, $5\times 5$), is designed for extracting multi-scale features. Following MSFE, an attention sub-block is employed to make the model adaptively focus on important channels/regions. These two sub-blocks constitute our MSFAB. Then, we design a cross non-local block (CNLB), which can capture long-range dependencies beyond the query. Instead of the same input source of query branch, the key and value branches are enhanced by fusing more preceding features. CNLB is computation-friendly by leveraging a spatial pyramid down-sampling (SPDS) strategy to reduce the computation and memory consumption without sacrificing the performance. Last but not least, a novel detail-focused contrastive regularization (DFCR) is presented by emphasizing the low-level details and ignoring the high-level semantic information in a representation space specially designed for dehazing. Comprehensive experimental results demonstrate that the proposed MRFNLN model outperforms recent state-of-the-art dehazing methods with less than 1.5 Million parameters.

cs.CV↗

arXiv2025

JCo-MVTON: Jointly Controllable Multi-Modal Diffusion Transformer for Mask-Free Virtual Try-on

Virtual try-on systems have long been hindered by heavy reliance on human body masks, limited fine-grained control over garment attributes, and poor generalization to real-world, in-the-wild scenarios. In this paper, we propose JCo-MVTON (Jointly Controllable Multi-Modal Diffusion Transformer for Mask-Free Virtual Try-On), a novel framework that overcomes these limitations by integrating diffusion-based image generation with multi-modal conditional fusion. Built upon a Multi-Modal Diffusion Transformer (MM-DiT) backbone, our approach directly incorporates diverse control signals -- such as the reference person image and the target garment image -- into the denoising process through dedicated conditional pathways that fuse features within the self-attention layers. This fusion is further enhanced with refined positional encodings and attention masks, enabling precise spatial alignment and improved garment-person integration. To address data scarcity and quality, we introduce a bidirectional generation strategy for dataset construction: one pipeline uses a mask-based model to generate realistic reference images, while a symmetric ``Try-Off'' model, trained in a self-supervised manner, recovers the corresponding garment images. The synthesized dataset undergoes rigorous manual curation, allowing iterative improvement in visual fidelity and diversity. Experiments demonstrate that JCo-MVTON achieves state-of-the-art performance on public benchmarks including DressCode, significantly outperforming existing methods in both quantitative metrics and human evaluations. Moreover, it shows strong generalization in real-world applications, surpassing commercial systems.

cs.CV↗

arXiv2025

Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference

We present Seed Diffusion Preview, a large-scale language model based on discrete-state diffusion, offering remarkably fast inference speed. Thanks to non-sequential, parallel generation, discrete diffusion models provide a notable speedup to mitigate the inherent latency of token-by-token decoding, as demonstrated recently (e.g., Mercury Coder, Gemini Diffusion). Seed Diffusion Preview achieves an inference speed of 2,146 token/s over H20 GPUs while maintaining competitive performance across a sweep of standard code evaluation benchmarks, significantly faster than contemporary Mercury and Gemini Diffusion, establishing new state of the art on the speed-quality Pareto frontier for code models.

cs.CL↗

arXiv2025

Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos

We introduce Being-H0, a dexterous Vision-Language-Action model (VLA) trained on large-scale human videos. Existing VLAs struggle with complex manipulation tasks requiring high dexterity and generalize poorly to novel scenarios and tasks, primarily due to their reliance on synthetic data with significant sim-to-real gaps or teleoperated demonstrations lacking scale and diversity. To address this data bottleneck, we propose leveraging human hands as a foundation manipulator, capitalizing on the rich dexterity and scalability present in web data. Our approach centers on physical instruction tuning, a novel training paradigm that combines large-scale VLA pretraining from human videos, physical space alignment for 3D reasoning, and post-training adaptation for robotic tasks. Additionally, we introduce a part-level motion tokenization method which achieves millimeter-level reconstruction accuracy to model precise hand trajectories for action learning. To support our proposed paradigm, we further develop a comprehensive data curation pipeline that integrates heterogeneous sources -- including motion capture, VR, and RGB-only videos -- into a large-scale dataset with millions of motion-based instructional instances. We empirically show the excellence of Being-H0 in hand motion generation and instruction following, and it also scales well with model and data sizes. Importantly, we observe the expected gains of Being-H0 in real-world robotic manipulation as physical instruction tuning is applied. More details are available at https://beingbeyond.github.io/Being-H0.

cs.CV↗

arXiv2025

Free-Form Motion Control: Controlling the 6D Poses of Camera and Objects in Video Generation

Controlling the movements of dynamic objects and the camera within generated videos is a meaningful yet challenging task. Due to the lack of datasets with comprehensive 6D pose annotations, existing text-to-video methods can not simultaneously control the motions of both camera and objects in 3D-aware manner, resulting in limited controllability over generated contents. To address this issue and facilitate the research in this field, we introduce a Synthetic Dataset for Free-Form Motion Control (SynFMC). The proposed SynFMC dataset includes diverse object and environment categories and covers various motion patterns according to specific rules, simulating common and complex real-world scenarios. The complete 6D pose information facilitates models learning to disentangle the motion effects from objects and the camera in a video.~To provide precise 3D-aware motion control, we further propose a method trained on SynFMC, Free-Form Motion Control (FMC). FMC can control the 6D poses of objects and camera independently or simultaneously, producing high-fidelity videos. Moreover, it is compatible with various personalized text-to-image (T2I) models for different content styles. Extensive experiments demonstrate that the proposed FMC outperforms previous methods across multiple scenarios.

cs.CV↗

arXiv2025

Efficient Adaptation of Pre-trained Vision Transformer underpinned by Approximately Orthogonal Fine-Tuning Strategy

A prevalent approach in Parameter-Efficient Fine-Tuning (PEFT) of pre-trained Vision Transformers (ViT) involves freezing the majority of the backbone parameters and solely learning low-rank adaptation weight matrices to accommodate downstream tasks. These low-rank matrices are commonly derived through the multiplication structure of down-projection and up-projection matrices, exemplified by methods such as LoRA and Adapter. In this work, we observe an approximate orthogonality among any two row or column vectors within any weight matrix of the backbone parameters; however, this property is absent in the vectors of the down/up-projection matrices. Approximate orthogonality implies a reduction in the upper bound of the model's generalization error, signifying that the model possesses enhanced generalization capability. If the fine-tuned down/up-projection matrices were to exhibit this same property as the pre-trained backbone matrices, could the generalization capability of fine-tuned ViTs be further augmented? To address this question, we propose an Approximately Orthogonal Fine-Tuning (AOFT) strategy for representing the low-rank weight matrices. This strategy employs a single learnable vector to generate a set of approximately orthogonal vectors, which form the down/up-projection matrices, thereby aligning the properties of these matrices with those of the backbone. Extensive experimental results demonstrate that our method achieves competitive performance across a range of downstream image classification tasks, confirming the efficacy of the enhanced generalization capability embedded in the down/up-projection matrices.

cs.CV↗

arXiv2025

AnyI2V: Animating Any Conditional Image with Motion Control

Recent advancements in video generation, particularly in diffusion models, have driven notable progress in text-to-video (T2V) and image-to-video (I2V) synthesis. However, challenges remain in effectively integrating dynamic motion signals and flexible spatial constraints. Existing T2V methods typically rely on text prompts, which inherently lack precise control over the spatial layout of generated content. In contrast, I2V methods are limited by their dependence on real images, which restricts the editability of the synthesized content. Although some methods incorporate ControlNet to introduce image-based conditioning, they often lack explicit motion control and require computationally expensive training. To address these limitations, we propose AnyI2V, a training-free framework that animates any conditional images with user-defined motion trajectories. AnyI2V supports a broader range of modalities as the conditional image, including data types such as meshes and point clouds that are not supported by ControlNet, enabling more flexible and versatile video generation. Additionally, it supports mixed conditional inputs and enables style transfer and editing via LoRA and text prompts. Extensive experiments demonstrate that the proposed AnyI2V achieves superior performance and provides a new perspective in spatial- and motion-controlled video generation. Code is available at https://henghuiding.com/AnyI2V/.

cs.CV↗

arXiv2025

Grid: Omni Visual Generation

Visual generation has witnessed remarkable progress in single-image tasks, yet extending these capabilities to temporal sequences remains challenging. Current approaches either build specialized video models from scratch with enormous computational costs or add separate motion modules to image generators, both requiring learning temporal dynamics anew. We observe that modern image generation models possess underutilized potential in handling structured layouts with implicit temporal understanding. Building on this insight, we introduce GRID, which reformulates temporal sequences as grid layouts, enabling holistic processing of visual sequences while leveraging existing model capabilities. Through a parallel flow-matching training strategy with coarse-to-fine scheduling, our approach achieves up to 67 faster inference speeds while using <1/1000 of the computational resources compared to specialized models. Extensive experiments demonstrate that GRID not only excels in temporal tasks from Text-to-Video to 3D Editing but also preserves strong performance in image generation, establishing itself as an efficient and versatile omni-solution for visual generation.

cs.CV↗

arXiv2025

Unified Multimodal Understanding via Byte-Pair Visual Encoding

Multimodal large language models (MLLMs) have made significant progress in vision-language understanding, yet effectively aligning different modalities remains a fundamental challenge. We present a framework that unifies multimodal understanding by applying byte-pair encoding to visual tokens. Unlike conventional approaches that rely on modality-specific encoders, our method directly incorporates structural information into visual tokens, mirroring successful tokenization strategies in text-only language models. We introduce a priority-guided encoding scheme that considers both frequency and spatial consistency, coupled with a multi-stage training procedure based on curriculum-driven data composition. These enhancements enable the transformer model to better capture cross-modal relationships and reason with visual information. Comprehensive experiments demonstrate improved performance across diverse vision-language tasks. By bridging the gap between visual and textual representations, our approach contributes to the advancement of more capable and efficient multimodal foundation models.

cs.CV↗

arXiv2025

WorldVLA: Towards Autoregressive Action World Model

We present WorldVLA, an autoregressive action world model that unifies action and image understanding and generation. Our WorldVLA intergrates Vision-Language-Action (VLA) model and world model in one single framework. The world model predicts future images by leveraging both action and image understanding, with the purpose of learning the underlying physics of the environment to improve action generation. Meanwhile, the action model generates the subsequent actions based on image observations, aiding in visual understanding and in turn helps visual generation of the world model. We demonstrate that WorldVLA outperforms standalone action and world models, highlighting the mutual enhancement between the world model and the action model. In addition, we find that the performance of the action model deteriorates when generating sequences of actions in an autoregressive manner. This phenomenon can be attributed to the model's limited generalization capability for action prediction, leading to the propagation of errors from earlier actions to subsequent ones. To address this issue, we propose an attention mask strategy that selectively masks prior actions during the generation of the current action, which shows significant performance improvement in the action chunk generation task.

cs.RO↗

arXiv2025

LayerFlow: A Unified Model for Layer-aware Video Generation

We present LayerFlow, a unified solution for layer-aware video generation. Given per-layer prompts, LayerFlow generates videos for the transparent foreground, clean background, and blended scene. It also supports versatile variants like decomposing a blended video or generating the background for the given foreground and vice versa. Starting from a text-to-video diffusion transformer, we organize the videos for different layers as sub-clips, and leverage layer embeddings to distinguish each clip and the corresponding layer-wise prompts. In this way, we seamlessly support the aforementioned variants in one unified framework. For the lack of high-quality layer-wise training videos, we design a multi-stage training strategy to accommodate static images with high-quality layer annotations. Specifically, we first train the model with low-quality video data. Then, we tune a motion LoRA to make the model compatible with static frames. Afterward, we train the content LoRA on the mixture of image data with high-quality layered images along with copy-pasted video data. During inference, we remove the motion LoRA thus generating smooth videos with desired layers.

cs.CV↗

arXiv2025

VideoAnydoor: High-fidelity Video Object Insertion with Precise Motion Control

Despite significant advancements in video generation, inserting a given object into videos remains a challenging task. The difficulty lies in preserving the appearance details of the reference object and accurately modeling coherent motions at the same time. In this paper, we propose VideoAnydoor, a zero-shot video object insertion framework with high-fidelity detail preservation and precise motion control. Starting from a text-to-video model, we utilize an ID extractor to inject the global identity and leverage a box sequence to control the overall motion. To preserve the detailed appearance and meanwhile support fine-grained motion control, we design a pixel warper. It takes the reference image with arbitrary key-points and the corresponding key-point trajectories as inputs. It warps the pixel details according to the trajectories and fuses the warped features with the diffusion U-Net, thus improving detail preservation and supporting users in manipulating the motion trajectories. In addition, we propose a training strategy involving both videos and static images with a weighted loss to enhance insertion quality. VideoAnydoor demonstrates significant superiority over existing methods and naturally supports various downstream applications (e.g., talking head generation, video virtual try-on, multi-region editing) without task-specific fine-tuning.

cs.CV↗

arXiv2025

Guiding LLM-based Smart Contract Generation with Finite State Machine

Smart contract is a kind of self-executing code based on blockchain technology with a wide range of application scenarios, but the traditional generation method relies on manual coding and expert auditing, which has a high threshold and low efficiency. Although Large Language Models (LLMs) show great potential in programming tasks, they still face challenges in smart contract generation w.r.t. effectiveness and security. To solve these problems, we propose FSM-SCG, a smart contract generation framework based on finite state machine (FSM) and LLMs, which significantly improves the quality of the generated code by abstracting user requirements to generate FSM, guiding LLMs to generate smart contracts, and iteratively optimizing the code with the feedback of compilation and security checks. The experimental results show that FSM-SCG significantly improves the quality of smart contract generation. Compared to the best baseline, FSM-SCG improves the compilation success rate of generated smart contract code by at most 48%, and reduces the average vulnerability risk score by approximately 68%.

cs.AI↗

arXiv2025

Reconstruction of Antarctic sea ice thickness from sparse satellite laser altimetry data using a partial convolutional neural network

The persistent lack of spatially complete Antarctic sea ice thickness (SIT) data at sub-monthly resolution has fundamentally constrained the quantitative understanding of large-scale sea ice mass balance processes. In this study, a pan-Antarctic SIT dataset at 5-day and 12.5 km resolution was developed based on sparse Ice, Cloud and Land Elevation Satellite (ICESat: 2003-2009) and ICESat-2 (2018-2024) along-track laser altimetry SIT retrievals using a deep learning approach. The reconstructed SIT was quantitatively validated against independent upward-looking sonar (ULS) observations and showed higher accuracy than the other four satellite-derived and reanalyzed Antarctic SIT datasets. The temporal evolution of the reconstructed SIT was further validated by ULS and ICESat-2 observations. Consistent seasonal cycles and intra-seasonal tendencies across these datasets confirm the reconstruction's reliability. Beyond advancing the mechanistic understanding of Antarctic sea ice variability and climate linkages, this reconstruction dataset's near-real-time updating capability offers operational value for monitoring and forecasting the Antarctic sea ice state.

physics.geo-ph↗

arXiv2025

Uncovering the Maximum Chirality in Dielectric Nanostructures

Maximum structural chirality refers to the highest selectivity for circularly polarized light (CPL) in nanostructures, often manifested as maximum circular dichroism (CD), optical rotation (OR), and spin-orbit coupling (SOC). However, the underlying physical mechanisms that lead to maximum chirality remain unclear. In this work, we demonstrate that maximum chirality in dielectric nanostructures arises from the constructive and destructive interference of multipole moments with different CPL. By employing generalized multipole decomposition, we introduce a generalized chiral multipole mechanism that allows for direct numerical calculation of CD and establishes the conditions required to achieve maximum chirality. This approach provides a comprehensive framework for analyzing chirality and serves as a foundation for future investigations of chiral nanostructures.

physics.optics↗

arXiv2025

RCNet: Deep Recurrent Collaborative Network for Multi-View Low-Light Image Enhancement

Scene observation from multiple perspectives would bring a more comprehensive visual experience. However, in the context of acquiring multiple views in the dark, the highly correlated views are seriously alienated, making it challenging to improve scene understanding with auxiliary views. Recent single image-based enhancement methods may not be able to provide consistently desirable restoration performance for all views due to the ignorance of potential feature correspondence among different views. To alleviate this issue, we make the first attempt to investigate multi-view low-light image enhancement. First, we construct a new dataset called Multi-View Low-light Triplets (MVLT), including 1,860 pairs of triple images with large illumination ranges and wide noise distribution. Each triplet is equipped with three different viewpoints towards the same scene. Second, we propose a deep multi-view enhancement framework based on the Recurrent Collaborative Network (RCNet). Specifically, in order to benefit from similar texture correspondence across different views, we design the recurrent feature enhancement, alignment and fusion (ReEAF) module, in which intra-view feature enhancement (Intra-view EN) followed by inter-view feature alignment and fusion (Inter-view AF) is performed to model the intra-view and inter-view feature propagation sequentially via multi-view collaboration. In addition, two different modules from enhancement to alignment (E2A) and from alignment to enhancement (A2E) are developed to enable the interactions between Intra-view EN and Inter-view AF, which explicitly utilize attentive feature weighting and sampling for enhancement and alignment, respectively. Experimental results demonstrate that our RCNet significantly outperforms other state-of-the-art methods. All of our dataset, code, and model will be available at https://github.com/hluo29/RCNet.

cs.CV↗

arXiv2025

VideoOrion: Tokenizing Object Dynamics in Videos

We present VideoOrion, a Video Large Language Model (Video-LLM) that explicitly captures the key semantic information in videos - the spatial-temporal dynamics of objects throughout the videos. VideoOrion employs expert vision models to extract object dynamics through a detect-segment-track pipeline, encoding them into a set of object tokens by aggregating spatial-temporal object features. Our method addresses the persistent challenge in Video-LLMs of efficiently compressing high-dimensional video data into semantic tokens that are comprehensible to LLMs. Compared to prior methods which resort to downsampling the original video or aggregating visual tokens using resamplers, leading to information loss and entangled semantics, VideoOrion not only offers a more natural and efficient way to derive compact, disentangled semantic representations but also enables explicit object modeling of video content with minimal computational cost. Moreover, the introduced object tokens naturally allow VideoOrion to accomplish video-based referring tasks. Experimental results show that VideoOrion can learn to make good use of the object tokens, and achieves competitive results on both general video question answering and video-based referring benchmarks.

cs.CV↗

arXiv2025

Intelligent logistics management robot path planning algorithm integrating transformer and GCN network

This research delves into advanced route optimization for robots in smart logistics, leveraging a fusion of Transformer architectures, Graph Neural Networks (GNNs), and Generative Adversarial Networks (GANs). The approach utilizes a graph-based representation encompassing geographical data, cargo allocation, and robot dynamics, addressing both spatial and resource limitations to refine route efficiency. Through extensive testing with authentic logistics datasets, the proposed method achieves notable improvements, including a 15% reduction in travel distance, a 20% boost in time efficiency, and a 10% decrease in energy consumption. These findings highlight the algorithm's effectiveness, promoting enhanced performance in intelligent logistics operations.

cs.RO↗