arXiv subjects

Ming Lu

Publications and source records attributed to Ming Lu.

At least 109 records · Page 6Linked to original sources

arXiv2025

CoGen: 3D Consistent Video Generation via Adaptive Conditioning for Autonomous Driving

Recent progress in driving video generation has shown significant potential for enhancing self-driving systems by providing scalable and controllable training data. Although pretrained state-of-the-art generation models, guided by 2D layout conditions (e.g., HD maps and bounding boxes), can produce photorealistic driving videos, achieving controllable multi-view videos with high 3D consistency remains a major challenge. To tackle this, we introduce a novel spatial adaptive generation framework, CoGen, which leverages advances in 3D generation to improve performance in two key aspects: (i) To ensure 3D consistency, we first generate high-quality, controllable 3D conditions that capture the geometry of driving scenes. By replacing coarse 2D conditions with these fine-grained 3D representations, our approach significantly enhances the spatial consistency of the generated videos. (ii) Additionally, we introduce a consistency adapter module to strengthen the robustness of the model to multi-condition control. The results demonstrate that this method excels in preserving geometric fidelity and visual realism, offering a reliable video generation solution for autonomous driving.

cs.CV↗

arXiv2025

MC-LLaVA: Multi-Concept Personalized Vision-Language Model

Current vision-language models (VLMs) show exceptional abilities across diverse tasks, such as visual question answering. To enhance user experience, recent studies investigate VLM personalization to understand user-provided concepts. However, they mainly focus on single-concept personalization, neglecting the existence and interplay of multiple concepts, which limits real-world applicability. This paper proposes the first multi-concept personalization paradigm, MC-LLaVA. Specifically, MC-LLaVA employs a multi-concept instruction tuning strategy, effectively integrating multiple concepts in a single training step. To reduce the costs related to joint training, we propose a personalized textual prompt that uses visual token information to initialize concept tokens. Additionally, we introduce a personalized visual prompt during inference, aggregating location confidence maps for enhanced recognition and grounding capabilities. To advance multi-concept personalization research, we further contribute a high-quality instruction tuning dataset. We carefully collect images with multiple characters and objects from movies and manually generate question-answer samples for multi-concept scenarios, featuring superior diversity. Comprehensive qualitative and quantitative experiments demonstrate that MC-LLaVA can achieve impressive multi-concept personalized responses, paving the way for VLMs to become better user-specific assistants. The code and dataset will be publicly available at https://github.com/arctanxarc/MC-LLaVA}.

cs.CV↗

arXiv2025

DiffusionTalker: Efficient and Compact Speech-Driven 3D Talking Head via Personalizer-Guided Distillation

Real-time speech-driven 3D facial animation has been attractive in academia and industry. Traditional methods mainly focus on learning a deterministic mapping from speech to animation. Recent approaches start to consider the nondeterministic fact of speech-driven 3D face animation and employ the diffusion model for the task. Existing diffusion-based methods can improve the diversity of facial animation. However, personalized speaking styles conveying accurate lip language is still lacking, besides, efficiency and compactness still need to be improved. In this work, we propose DiffusionTalker to address the above limitations via personalizer-guided distillation. In terms of personalization, we introduce a contrastive personalizer that learns identity and emotion embeddings to capture speaking styles from audio. We further propose a personalizer enhancer during distillation to enhance the influence of embeddings on facial animation. For efficiency, we use iterative distillation to reduce the steps required for animation generation and achieve more than 8x speedup in inference. To achieve compactness, we distill the large teacher model into a smaller student model, reducing our model's storage by 86.4\% while minimizing performance loss. After distillation, users can derive their identity and emotion embeddings from audio to quickly create personalized animations that reflect specific speaking styles. Extensive experiments are conducted to demonstrate that our method outperforms state-of-the-art methods. The code will be released at: https://github.com/ChenVoid/DiffusionTalker.

cs.CV↗

arXiv2025

MoVE-KD: Knowledge Distillation for VLMs with Mixture of Visual Encoders

Visual encoders are fundamental components in vision-language models (VLMs), each showcasing unique strengths derived from various pre-trained visual foundation models. To leverage the various capabilities of these encoders, recent studies incorporate multiple encoders within a single VLM, leading to a considerable increase in computational cost. In this paper, we present Mixture-of-Visual-Encoder Knowledge Distillation (MoVE-KD), a novel framework that distills the unique proficiencies of multiple vision encoders into a single, efficient encoder model. Specifically, to mitigate conflicts and retain the unique characteristics of each teacher encoder, we employ low-rank adaptation (LoRA) and mixture-of-experts (MoEs) to selectively activate specialized knowledge based on input features, enhancing both adaptability and efficiency. To regularize the KD process and enhance performance, we propose an attention-based distillation strategy that adaptively weighs the different encoders and emphasizes valuable visual tokens, reducing the burden of replicating comprehensive but distinct features from multiple teachers. Comprehensive experiments on popular VLMs, such as LLaVA and LLaVA-NeXT, validate the effectiveness of our method. Our code is available at: https://github.com/hey-cjj/MoVE-KD.

cs.CV↗

arXiv2025

On Quantizing Neural Representation for Variable-Rate Video Coding

This work introduces NeuroQuant, a novel post-training quantization (PTQ) approach tailored to non-generalized Implicit Neural Representations for variable-rate Video Coding (INR-VC). Unlike existing methods that require extensive weight retraining for each target bitrate, we hypothesize that variable-rate coding can be achieved by adjusting quantization parameters (QPs) of pre-trained weights. Our study reveals that traditional quantization methods, which assume inter-layer independence, are ineffective for non-generalized INR-VC models due to significant dependencies across layers. To address this, we redefine variable-rate INR-VC as a mixed-precision quantization problem and establish a theoretical framework for sensitivity criteria aimed at simplified, fine-grained rate control. Additionally, we propose network-wise calibration and channel-wise quantization strategies to minimize quantization-induced errors, arriving at a unified formula for representation-oriented PTQ calibration. Our experimental evaluations demonstrate that NeuroQuant significantly outperforms existing techniques in varying bitwidth quantization and compression efficiency, accelerating encoding by up to eight times and enabling quantization down to INT2 with minimal reconstruction loss. This work introduces variable-rate INR-VC for the first time and lays a theoretical foundation for future research in rate-distortion optimization, advancing the field of video coding technology. The materials will be available at https://github.com/Eric-qi/NeuroQuant.

eess.IV↗

arXiv2025

Analogue of Feigin's map on $\imath$quantum group of split type

The (universal) $\imath$quantum groups are as a vast generalization of (Drinfeld double) quantum groups. We establish an algebra homomorphism from universal $\imath$quantum group of split type to a certain quantum torus, which can be viewed as an $\imath$analogue of Feigin's map on the quantum group.

math.QA↗

arXiv2025

CMamba: Learned Image Compression with State Space Models

Learned Image Compression (LIC) has explored various architectures, such as Convolutional Neural Networks (CNNs) and transformers, in modeling image content distributions in order to achieve compression effectiveness. However, achieving high rate-distortion performance while maintaining low computational complexity (\ie, parameters, FLOPs, and latency) remains challenging. In this paper, we propose a hybrid Convolution and State Space Models (SSMs) based image compression framework, termed \textit{CMamba}, to achieve superior rate-distortion performance with low computational complexity. Specifically, CMamba introduces two key components: a Content-Adaptive SSM (CA-SSM) module and a Context-Aware Entropy (CAE) module. First, we observed that SSMs excel in modeling overall content but tend to lose high-frequency details. In contrast, CNNs are proficient at capturing local details. Motivated by this, we propose the CA-SSM module that can dynamically fuse global content extracted by SSM blocks and local details captured by CNN blocks in both encoding and decoding stages. As a result, important image content is well preserved during compression. Second, our proposed CAE module is designed to reduce spatial and channel redundancies in latent representations after encoding. Specifically, our CAE leverages SSMs to parameterize the spatial content in latent representations. Benefiting from SSMs, CAE significantly improves spatial compression efficiency while reducing spatial content redundancies. Moreover, along the channel dimension, CAE reduces inter-channel redundancies of latent representations via an autoregressive manner, which can fully exploit prior knowledge from previous channels without sacrificing efficiency. Experimental results demonstrate that CMamba achieves superior rate-distortion performance.

eess.IV↗

arXiv2025

SliceOcc: Indoor 3D Semantic Occupancy Prediction with Vertical Slice Representation

3D semantic occupancy prediction is a crucial task in visual perception, as it requires the simultaneous comprehension of both scene geometry and semantics. It plays a crucial role in understanding 3D scenes and has great potential for various applications, such as robotic vision perception and autonomous driving. Many existing works utilize planar-based representations such as Bird's Eye View (BEV) and Tri-Perspective View (TPV). These representations aim to simplify the complexity of 3D scenes while preserving essential object information, thereby facilitating efficient scene representation. However, in dense indoor environments with prevalent occlusions, directly applying these planar-based methods often leads to difficulties in capturing global semantic occupancy, ultimately degrading model performance. In this paper, we present a new vertical slice representation that divides the scene along the vertical axis and projects spatial point features onto the nearest pair of parallel planes. To utilize these slice features, we propose SliceOcc, an RGB camera-based model specifically tailored for indoor 3D semantic occupancy prediction. SliceOcc utilizes pairs of slice queries and cross-attention mechanisms to extract planar features from input images. These local planar features are then fused to form a global scene representation, which is employed for indoor occupancy prediction. Experimental results on the EmbodiedScan dataset demonstrate that SliceOcc achieves a mIoU of 15.45% across 81 indoor categories, setting a new state-of-the-art performance among RGB camera-based models for indoor 3D semantic occupancy prediction. Code is available at https://github.com/NorthSummer/SliceOcc.

cs.CV↗

arXiv2025

Accelerating Discovery of Solid-State Thin-Film Metal Dealloying for 3D Nanoarchitecture Materials Design through Laser Thermal Gradient Treatment

Thin-film solid-state metal dealloying (thin-film SSMD) is a promising method for fabricating nanostructures with controlled morphology and efficiency, offering advantages over conventional bulk materials processing methods for integration into practical applications. Although machine learning (ML) has facilitated the design of dealloying systems, the selection of key thermal treatment parameters for nanostructure formation remains largely unknown and dependent on experimental trial and error. To overcome this challenge, a workflow enabling high-throughput characterization of thermal treatment parameters while probing local nanostructures of thin-film samples is needed. In this work, a laser-based thermal treatment is demonstrated to create temperature gradients on single thin-film samples of Nb-Al/Sc and Nb-Al/Cu. This continuous thermal space enables observation of dealloying transitions and the resulting nanostructures of interest. Through synchrotron X-ray multimodal and high-throughput characterization, critical transitions and nanostructures can be rapidly captured and subsequently verified using electron microscopy. The key temperatures driving chemical reactions and morphological evolutions are clearly identified within this framework. While the oxidation process may contribute to nanostructure formation during thin-film treatment, the dealloying process at the dealloying front involves interactions solely between the dealloying elements, highlighting the availability and viability of the selected systems. This approach enables efficient exploration of the dealloying process and validation of ML predictions, thereby accelerating the discovery of thin-film SSMD systems with targeted nanostructures.

cond-mat.mtrl-sci↗

arXiv2025

Towards Loss-Resilient Image Coding for Unstable Satellite Networks

Geostationary Earth Orbit (GEO) satellite communication demonstrates significant advantages in emergency short burst data services. However, unstable satellite networks, particularly those with frequent packet loss, present a severe challenge to accurate image transmission. To address it, we propose a loss-resilient image coding approach that leverages end-to-end optimization in learned image compression (LIC). Our method builds on the channel-wise progressive coding framework, incorporating Spatial-Channel Rearrangement (SCR) on the encoder side and Mask Conditional Aggregation (MCA) on the decoder side to improve reconstruction quality with unpredictable errors. By integrating the Gilbert-Elliot model into the training process, we enhance the model's ability to generalize in real-world network conditions. Extensive evaluations show that our approach outperforms traditional and deep learning-based methods in terms of compression performance and stability under diverse packet loss, offering robust and efficient progressive transmission even in challenging environments. Code is available at https://github.com/NJUVISION/LossResilientLIC.

cs.CV↗

arXiv2024

GraphAvatar: Compact Head Avatars with GNN-Generated 3D Gaussians

Rendering photorealistic head avatars from arbitrary viewpoints is crucial for various applications like virtual reality. Although previous methods based on Neural Radiance Fields (NeRF) can achieve impressive results, they lack fidelity and efficiency. Recent methods using 3D Gaussian Splatting (3DGS) have improved rendering quality and real-time performance but still require significant storage overhead. In this paper, we introduce a method called GraphAvatar that utilizes Graph Neural Networks (GNN) to generate 3D Gaussians for the head avatar. Specifically, GraphAvatar trains a geometric GNN and an appearance GNN to generate the attributes of the 3D Gaussians from the tracked mesh. Therefore, our method can store the GNN models instead of the 3D Gaussians, significantly reducing the storage overhead to just 10MB. To reduce the impact of face-tracking errors, we also present a novel graph-guided optimization module to refine face-tracking parameters during training. Finally, we introduce a 3D-aware enhancer for post-processing to enhance the rendering quality. We conduct comprehensive experiments to demonstrate the advantages of GraphAvatar, surpassing existing methods in visual fidelity and storage consumption. The ablation study sheds light on the trade-offs between rendering quality and model size. The code will be released at: https://github.com/ucwxb/GraphAvatar

cs.CV↗

arXiv2024

ASGDiffusion: Parallel High-Resolution Generation with Asynchronous Structure Guidance

Training-free high-resolution (HR) image generation has garnered significant attention due to the high costs of training large diffusion models. Most existing methods begin by reconstructing the overall structure and then proceed to refine the local details. Despite their advancements, they still face issues with repetitive patterns in HR image generation. Besides, HR generation with diffusion models incurs significant computational costs. Thus, parallel generation is essential for interactive applications. To solve the above limitations, we introduce a novel method named ASGDiffusion for parallel HR generation with Asynchronous Structure Guidance (ASG) using pre-trained diffusion models. To solve the pattern repetition problem of HR image generation, ASGDiffusion leverages the low-resolution (LR) noise weighted by the attention mask as the structure guidance for the denoising step to ensure semantic consistency. The proposed structure guidance can significantly alleviate the pattern repetition problem. To enable parallel generation, we further propose a parallelism strategy, which calculates the patch noises and structure guidance asynchronously. By leveraging multi-GPU parallel acceleration, we significantly accelerate generation speed and reduce memory usage per GPU. Extensive experiments demonstrate that our method effectively and efficiently addresses common issues like pattern repetition and achieves state-of-the-art HR generation.

cs.CV↗

arXiv2024

$\imath$Hall algebras of weighted projective lines and quantum symmetric pairs III: quasi-split type

From a category $\mathcal{A}$ with an involution $\varrho$, we introduce $\varrho$-complexes, which are a generalization of (bounded) complexes, periodic complexes and modules of $\imath$quiver algebras. The homological properties of the category $\mathcal{C}_\varrho(\mathcal{A})$ of $\varrho$-complexes are given to make the machinery of semi-derived Ringel-Hall algebras applicable. The $\imath$Hall algebra of the weighted projective line $\mathbb{X}$ is the twisted semi-derived Ringel-Hall algebra of $\mathcal{C}_\varrho({\rm coh}(\mathbb{X}))$, where $\varrho$ is an involution of ${\rm coh}(\mathbb{X})$. This $\imath$Hall algebra is used to realize the quasi-split $\imath$quantum loop algebra, which is a generalization of the $\imath$quantum group arising from the quantum symmetric pair of quasi-split affine type ADE in its Drinfeld type presentation.

math.QA↗

arXiv2024

Skin-topological effect in two-dimensional nonreciprocal topological superconductor

We investigate the interplay between non-Hermitian skin effect (NHSE) and topological properties in two-dimensional topological superconductor. Two kinds of non-Hermiticity are considered. The first is the spin-independent non-reciprocal hopping, which respects particle-hole symmetry (PHS) and dictates the bulk as well as topological edge modes localize at opposite corners, manifested as the $Z_2$ NHSE protected by PHS. The direction of the localization can be conveniently characterized by the sign of the winding numbers. The other is the spin-dependent non-reciprocal hopping, where the NHSE is protected by time-reversal symmetry (TRS). The Kramers doublets are localized at opposite corners, namely the TRS protected $Z_2$ NHSE. When apply an external magnetic field, its internal symmetry changes from the symplectic class into the orthogonal class, eliminating the NHSE for the states in the spectrum continuum. For the zero energy states which are isolated, the NHSE still has its effects despite the orthogonality. For the spin-independent case, edge states can be effectively tuned by the direction of Zeeman field, where at certain directions the zero-energy edge state can be free of NHSE and uniformly distributed. Our work paves the way for the study of the interplay between topology and non-Hermiticity in superconducting systems.

cond-mat.supr-con↗

arXiv2024

Room-temperature non-volatile optical manipulation of polar order in a charge density wave

Utilizing ultrafast light-matter interaction to manipulate electronic states of quantum materials is an emerging area of research in condensed matter physics. It has significant implications for the development of future ultrafast electronic devices. However, the ability to induce long-lasting metastable electronic states in a fully reversible manner is a long-standing challenge.Here, by using ultrafast laser excitations, we demonstrate the capability to manipulate the electronic polar states in the charge-density-wavematerial EuTe4 in a non-volatile manner. The process is completely reversible and is achieved at room temperature with an all-optical approach. Each induced non-volatile state brings about modifications to the electrical resistance and second harmonic generation intensity. The results point to layer-specific phase inversion dynamics by which photoexcitation mediates the stacking polar order of the system. Our findings extend the scope of non-volatile all-optical control of electronic states to ambient conditions, and highlight a distinct role of layerdependent phase manipulation in quasi-two-dimensional systems with inherent sublayer stacking orders.

cond-mat.str-el↗

arXiv2024

High-Efficiency Neural Video Compression via Hierarchical Predictive Learning

The enhanced Deep Hierarchical Video Compression-DHVC 2.0-has been introduced. This single-model neural video codec operates across a broad range of bitrates, delivering not only superior compression performance to representative methods but also impressive complexity efficiency, enabling real-time processing with a significantly smaller memory footprint on standard GPUs. These remarkable advancements stem from the use of hierarchical predictive coding. Each video frame is uniformly transformed into multiscale representations through hierarchical variational autoencoders. For a specific scale's feature representation of a frame, its corresponding latent residual variables are generated by referencing lower-scale spatial features from the same frame and then conditionally entropy-encoded using a probabilistic model whose parameters are predicted using same-scale temporal reference from previous frames and lower-scale spatial reference of the current frame. This feature-space processing operates from the lowest to the highest scale of each frame, completely eliminating the need for the complexity-intensive motion estimation and compensation techniques that have been standard in video codecs for decades. The hierarchical approach facilitates parallel processing, accelerating both encoding and decoding, and supports transmission-friendly progressive decoding, making it particularly advantageous for networked video applications in the presence of packet loss. Source codes will be made available.

eess.IV↗

arXiv2024

All-in-One Image Coding for Joint Human-Machine Vision with Multi-Path Aggregation

Image coding for multi-task applications, catering to both human perception and machine vision, has been extensively investigated. Existing methods often rely on multiple task-specific encoder-decoder pairs, leading to high overhead of parameter and bitrate usage, or face challenges in multi-objective optimization under a unified representation, failing to achieve both performance and efficiency. To this end, we propose Multi-Path Aggregation (MPA) integrated into existing coding models for joint human-machine vision, unifying the feature representation with an all-in-one architecture. MPA employs a predictor to allocate latent features among task-specific paths based on feature importance varied across tasks, maximizing the utility of shared features while preserving task-specific features for subsequent refinement. Leveraging feature correlations, we develop a two-stage optimization strategy to alleviate multi-task performance degradation. Upon the reuse of shared features, as low as 1.89% parameters are further augmented and fine-tuned for a specific task, which completely avoids extensive optimization of the entire model. Experimental results show that MPA achieves performance comparable to state-of-the-art methods in both task-specific and multi-objective optimization across human viewing and machine analysis tasks. Moreover, our all-in-one design supports seamless transitions between human- and machine-oriented reconstruction, enabling task-controllable interpretation without altering the unified model. Code is available at https://github.com/NJUVISION/MPA.

cs.CV↗

arXiv2024

Accelerating block-level rate control for learned image compression

Despite the unprecedented compression efficiency achieved by deep learned image compression (LIC), existing methods usually approximate the desired bitrate by adjusting a single quality factor for a given input image, which may compromise the rate control results. Considering the Rate-Distortion (R - D) characteristics of different spatial content, this work introduces the block-level rate control based on a novel D - λ model specific for LIC. Furthermore, we try to exploit the inter-block correlations and propose a block-wise R - D prediction algorithm which greatly speeds up block-level rate control while still guaranteeing high accuracy. Experimental results show that the proposed rate control achieves up to 100 times, speed-up with more than 98% accuracy. Our approach provides an optimal bit allocation for each block and therefore improves the overall compression performance, which offers great potential for block-level LIC.

eess.IV↗