arXiv subjects

Jing Cheng

Publications and source records attributed to Jing Cheng.

At least 19 recordsLinked to original sources

arXiv2026

DreamStereo: Towards Real-Time Stereo Inpainting for HD Videos

Stereo video inpainting, which aims to fill the occluded regions of warped videos with visually coherent content while maintaining temporal consistency, remains a challenging open problem. The regions to be filled are scattered along object boundaries and occupy only a small fraction of each frame, leading to two key challenges. First, existing approaches perform poorly on such tasks due to the scarcity of high-quality stereo inpainting datasets, which limits their ability to learn effective inpainting priors. Second, these methods apply equal processing to all regions of the frame, even though most pixels require no modification, resulting in substantial redundant computation. To address these issues, we introduce three interconnected components. We first propose Gradient-Aware Parallax Warping (GAPW), which leverages backward warping and the gradient of the coordinate mapping function to obtain continuous edges and smooth occlusion regions. Then, a Parallax-Based Dual Projection (PBDP) strategy is introduced, which incorporates GAPW to produce geometrically consistent stereo inpainting pairs and accurate occlusion masks without requiring stereo videos. Finally, we present Sparsity-Aware Stereo Inpainting (SASI), which reduces over 70% of redundant tokens, achieving a 10.7x speedup during diffusion inference and delivering results comparable to its full-computation counterpart, enabling real-time processing of HD (768 x 1280) videos at 25 FPS on a single A100 GPU.

cs.CV↗

arXiv2025

Flow-Guided Implicit Neural Representation for Motion-Aware Dynamic MRI Reconstruction

Dynamic magnetic resonance imaging (dMRI) captures temporally-resolved anatomy but is often challenged by limited sampling and motion-induced artifacts. Conventional motion-compensated reconstructions typically rely on pre-estimated optical flow, which is inaccurate under undersampling and degrades reconstruction quality. In this work, we propose a novel implicit neural representation (INR) framework that jointly models both the dynamic image sequence and its underlying motion field. Specifically, one INR is employed to parameterize the spatiotemporal image content, while another INR represents the optical flow. The two are coupled via the optical flow equation, which serves as a physics-inspired regularization, in addition to a data consistency loss that enforces agreement with k-space measurements. This joint optimization enables simultaneous recovery of temporally coherent images and motion fields without requiring prior flow estimation. Experiments on dynamic cardiac MRI datasets demonstrate that the proposed method outperforms state-of-the-art motion-compensated and deep learning approaches, achieving superior reconstruction quality, accurate motion estimation, and improved temporal fidelity. These results highlight the potential of implicit joint modeling with flow-regularized constraints for advancing dMRI reconstruction.

cs.CV↗

arXiv2025

Self-supervised Deep Unrolled Model with Implicit Neural Representation Regularization for Accelerating MRI Reconstruction

Magnetic resonance imaging (MRI) is a vital clinical diagnostic tool, yet its application is limited by prolonged scan times. Accelerating MRI reconstruction addresses this issue by reconstructing high-fidelity MR images from undersampled k-space measurements. In recent years, deep learning-based methods have demonstrated remarkable progress. However, most methods rely on supervised learning, which requires large amounts of fully-sampled training data that are difficult to obtain. This paper proposes a novel zero-shot self-supervised reconstruction method named UnrollINR, which enables scan-specific MRI reconstruction without external training data. UnrollINR adopts a physics-guided unrolled reconstruction architecture and introduces implicit neural representation (INR) as a regularization prior to effectively constrain the solution space. This method overcomes the local bias limitation of CNNs in traditional deep unrolled methods and avoids the instability associated with relying solely on INR's implicit regularization in highly ill-posed scenarios. Consequently, UnrollINR significantly improves MRI reconstruction performance under high acceleration rates. Experimental results show that even at a high acceleration rate of 10, UnrollINR achieves superior reconstruction performance compared to supervised and self-supervised learning methods, validating its effectiveness and superiority.

cs.CV↗

arXiv2025

TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs

This paper introduces TempSamp-R1, a new reinforcement fine-tuning framework designed to improve the effectiveness of adapting multimodal large language models (MLLMs) to video temporal grounding tasks. We reveal that existing reinforcement learning methods, such as Group Relative Policy Optimization (GRPO), rely on on-policy sampling for policy updates. However, in tasks with large temporal search spaces, this strategy becomes both inefficient and limited in performance, as it often fails to identify temporally accurate solutions. To address this limitation, TempSamp-R1 leverages ground-truth annotations as off-policy supervision to provide temporally precise guidance, effectively compensating for the sparsity and misalignment in on-policy solutions. To further stabilize training and reduce variance in reward-based updates, TempSamp-R1 provides a non-linear soft advantage computation method that dynamically reshapes the reward feedback via an asymmetric transformation. By employing a hybrid Chain-of-Thought (CoT) training paradigm, TempSamp-R1 optimizes a single unified model to support both CoT and non-CoT inference modes, enabling efficient handling of queries with varying reasoning complexity. Experimental results demonstrate that TempSamp-R1 outperforms GRPO-based baselines, establishing new state-of-the-art performance on benchmark datasets: Charades-STA (R1@0.7: 52.9%, +2.7%), ActivityNet Captions (R1@0.5: 56.0%, +5.3%), and QVHighlights (mAP: 30.0%, +3.0%). Moreover, TempSamp-R1 shows robust few-shot generalization capabilities under limited data. Code: https://github.com/HVision-NKU/TempSamp-R1

cs.CV↗

arXiv2025

DreamPainter: Image Background Inpainting for E-commerce Scenarios

Although diffusion-based image genenation has been widely explored and applied, background generation tasks in e-commerce scenarios still face significant challenges. The first challenge is to ensure that the generated products are consistent with the given product inputs while maintaining a reasonable spatial arrangement, harmonious shadows, and reflections between foreground products and backgrounds. Existing inpainting methods fail to address this due to the lack of domain-specific data. The second challenge involves the limitation of relying solely on text prompts for image control, as effective integrating visual information to achieve precise control in inpainting tasks remains underexplored. To address these challenges, we introduce DreamEcom-400K, a high-quality e-commerce dataset containing accurate product instance masks, background reference images, text prompts, and aesthetically pleasing product images. Based on this dataset, we propose DreamPainter, a novel framework that not only utilizes text prompts for control but also flexibly incorporates reference image information as an additional control signal. Extensive experiments demonstrate that our approach significantly outperforms state-of-the-art methods, maintaining high product consistency while effectively integrating both text prompt and reference image information.

cs.CV↗

arXiv2025

Iteratively Learning Muscle Memory for Legged Robots to Master Adaptive and High Precision Locomotion

This paper presents a scalable and adaptive control framework for legged robots that integrates Iterative Learning Control (ILC) with a biologically inspired torque library (TL), analogous to muscle memory. The proposed method addresses key challenges in robotic locomotion, including accurate trajectory tracking under unmodeled dynamics and external disturbances. By leveraging the repetitive nature of periodic gaits and extending ILC to nonperiodic tasks, the framework enhances accuracy and generalization across diverse locomotion scenarios. The control architecture is data-enabled, combining a physics-based model derived from hybrid-system trajectory optimization with real-time learning to compensate for model uncertainties and external disturbances. A central contribution is the development of a generalized TL that stores learned control profiles and enables rapid adaptation to changes in speed, terrain, and gravitational conditions-eliminating the need for repeated learning and significantly reducing online computation. The approach is validated on the bipedal robot Cassie and the quadrupedal robot A1 through extensive simulations and hardware experiments. Results demonstrate that the proposed framework reduces joint tracking errors by up to 85% within a few seconds and enables reliable execution of both periodic and nonperiodic gaits, including slope traversal and terrain adaptation. Compared to state-of-the-art whole-body controllers, the learned skills eliminate the need for online computation during execution and achieve control update rates exceeding 30x those of existing methods. These findings highlight the effectiveness of integrating ILC with torque memory as a highly data-efficient and practical solution for legged locomotion in unstructured and dynamic environments.

cs.RO↗

arXiv2025

Refining Motion for Peak Performance: Identifying Optimal Gait Parameters for Energy-Efficient Quadrupedal Bounding

Energy efficiency is a critical factor in the performance and autonomy of quadrupedal robots. While previous research has focused on mechanical design and actuation improvements, the impact of gait parameters on energetics has been less explored. In this paper, we hypothesize that gait parameters, specifically duty factor, phase shift, and stride duration, are key determinants of energy consumption in quadrupedal locomotion. To test this hypothesis, we modeled the Unitree A1 quadrupedal robot and developed a locomotion controller capable of independently adjusting these gait parameters. Simulations of bounding gaits were conducted in Gazebo across a range of gait parameters at three different speeds: low, medium, and high. Experimental tests were also performed to validate the simulation results. The findings demonstrate that optimizing gait parameters can lead to significant reductions in energy consumption, enhancing the overall efficiency of quadrupedal locomotion. This work contributes to the advancement of energy-efficient control strategies for legged robots, offering insights directly applicable to commercially available platforms.

cs.RO↗

arXiv2025

DUN-SRE: Deep Unrolling Network with Spatiotemporal Rotation Equivariance for Dynamic MRI Reconstruction

Dynamic Magnetic Resonance Imaging (MRI) exhibits transformation symmetries, including spatial rotation symmetry within individual frames and temporal symmetry along the time dimension. Explicit incorporation of these symmetry priors in the reconstruction model can significantly improve image quality, especially under aggressive undersampling scenarios. Recently, Equivariant convolutional neural network (ECNN) has shown great promise in exploiting spatial symmetry priors. However, existing ECNNs critically fail to model temporal symmetry, arguably the most universal and informative structural prior in dynamic MRI reconstruction. To tackle this issue, we propose a novel Deep Unrolling Network with Spatiotemporal Rotation Equivariance (DUN-SRE) for Dynamic MRI Reconstruction. The DUN-SRE establishes spatiotemporal equivariance through a (2+1)D equivariant convolutional architecture. In particular, it integrates both the data consistency and proximal mapping module into a unified deep unrolling framework. This architecture ensures rigorous propagation of spatiotemporal rotation symmetry constraints throughout the reconstruction process, enabling more physically accurate modeling of cardiac motion dynamics in cine MRI. In addition, a high-fidelity group filter parameterization mechanism is developed to maintain representation precision while enforcing symmetry constraints. Comprehensive experiments on Cardiac CINE MRI datasets demonstrate that DUN-SRE achieves state-of-the-art performance, particularly in preserving rotation-symmetric structures, offering strong generalization capability to a broad range of dynamic MRI reconstruction tasks.

eess.IV↗

arXiv2025

Unsupervised patch-based dynamic MRI reconstruction using learnable tensor function with implicit neural representation

Dynamic MRI suffers from limited spatiotemporal resolution due to long acquisition times. Undersampling k-space accelerates imaging but makes accurate reconstruction challenging. Supervised deep learning methods achieve impressive results but rely on large fully sampled datasets, which are difficult to obtain. Recently, implicit neural representations (INR) have emerged as a powerful unsupervised paradigm that reconstructs images from a single undersampled dataset without external training data. However, existing INR-based methods still face challenges when applied to highly undersampled dynamic MRI, mainly due to their inefficient representation capacity and high computational cost. To address these issues, we propose TenF-INR, a novel unsupervised framework that integrates low-rank tensor modeling with INR, where each factor matrix in the tensor decomposition is modeled as a learnable factor function. Specifically,we employ INR to model learnable tensor functions within a low-rank decomposition, reducing the parameter space and computational burden. A patch-based nonlocal tensor modeling strategy further exploits temporal correlations and inter-patch similarities, enhancing the recovery of fine spatiotemporal details. Experiments on dynamic cardiac and abdominal datasets demonstrate that TenF-INR achieves up to 21-fold acceleration, outperforming both supervised and unsupervised state-of-the-art methods in image quality, temporal fidelity, and quantitative accuracy.

eess.IV↗

arXiv2025

BrainSegDMlF: A Dynamic Fusion-enhanced SAM for Brain Lesion Segmentation

The segmentation of substantial brain lesions is a significant and challenging task in the field of medical image segmentation. Substantial brain lesions in brain imaging exhibit high heterogeneity, with indistinct boundaries between lesion regions and normal brain tissue. Small lesions in single slices are difficult to identify, making the accurate and reproducible segmentation of abnormal regions, as well as their feature description, highly complex. Existing methods have the following limitations: 1) They rely solely on single-modal information for learning, neglecting the multi-modal information commonly used in diagnosis. This hampers the ability to comprehensively acquire brain lesion information from multiple perspectives and prevents the effective integration and utilization of multi-modal data inputs, thereby limiting a holistic understanding of lesions. 2) They are constrained by the amount of data available, leading to low sensitivity to small lesions and difficulty in detecting subtle pathological changes. 3) Current SAM-based models rely on external prompts, which cannot achieve automatic segmentation and, to some extent, affect diagnostic efficiency.To address these issues, we have developed a large-scale fully automated segmentation model specifically designed for brain lesion segmentation, named BrainSegDMLF. This model has the following features: 1) Dynamic Modal Interactive Fusion (DMIF) module that processes and integrates multi-modal data during the encoding process, providing the SAM encoder with more comprehensive modal information. 2) Layer-by-Layer Upsampling Decoder, enabling the model to extract rich low-level and high-level features even with limited data, thereby detecting the presence of small lesions. 3) Automatic segmentation masks, allowing the model to generate lesion masks automatically without requiring manual prompts.

cs.CV↗

arXiv2025

16 Ways to Gallop: Energetics and Body Dynamics of High-Speed Quadrupedal Gaits

Galloping is a common high-speed gait in both animals and quadrupedal robots, yet its energetic characteristics remain insufficiently explored. This study systematically analyzes a large number of possible galloping gaits by categorizing them based on the number of flight phases per stride and the phase relationships between the front and rear legs, following Hildebrand's framework for asymmetrical gaits. Using the A1 quadrupedal robot from Unitree, we model galloping dynamics as a hybrid dynamical system and employ trajectory optimization (TO) to minimize the cost of transport (CoT) across a range of speeds. Our results reveal that rotary and transverse gallop footfall sequences exhibit no fundamental energetic difference, despite variations in body yaw and roll motion. However, the number of flight phases significantly impacts energy efficiency: galloping with no flight phases is optimal at lower speeds, whereas galloping with two flight phases minimizes energy consumption at higher speeds. We validate these findings using a quadratic programming (QP)-based controller, developed in our previous work, in Gazebo simulations. These insights advance the understanding of quadrupedal locomotion energetics and may inform future legged robot designs for adaptive, energy-efficient gait transitions.

cs.RO↗

arXiv2024

SRE-CNN: A Spatiotemporal Rotation-Equivariant CNN for Cardiac Cine MR Imaging

Dynamic MR images possess various transformation symmetries,including the rotation symmetry of local features within the image and along the temporal dimension. Utilizing these symmetries as prior knowledge can facilitate dynamic MR imaging with high spatiotemporal resolution. Equivariant CNN is an effective tool to leverage the symmetry priors. However, current equivariant CNN methods fail to fully exploit these symmetry priors in dynamic MR imaging. In this work, we propose a novel framework of Spatiotemporal Rotation-Equivariant CNN (SRE-CNN), spanning from the underlying high-precision filter design to the construction of the temporal-equivariant convolutional module and imaging model, to fully harness the rotation symmetries inherent in dynamic MR images. The temporal-equivariant convolutional module enables exploitation the rotation symmetries in both spatial and temporal dimensions, while the high-precision convolutional filter, based on parametrization strategy, enhances the utilization of rotation symmetry of local features to improve the reconstruction of detailed anatomical structures. Experiments conducted on highly undersampled dynamic cardiac cine data (up to 20X) have demonstrated the superior performance of our proposed approach, both quantitatively and qualitatively.

eess.IV↗

arXiv2024

NegotiaToR: Towards A Simple Yet Effective On-demand Reconfigurable Datacenter Network

Recent advances in fast optical switching technology show promise in meeting the high goodput and low latency requirements of datacenter networks (DCN). We present NegotiaToR, a simple network architecture for optical reconfigurable DCNs that utilizes on-demand scheduling to handle dynamic traffic. In NegotiaToR, racks exchange scheduling messages through an in-band control plane and distributedly calculate non-conflicting paths from binary traffic demand information. Optimized for incasts, it also provides opportunities to bypass scheduling delays. NegotiaToR is compatible with prevalent flat topologies, and is tailored towards a minimalist design for on-demand reconfigurable DCNs, enhancing practicality. Through large-scale simulations, we show that NegotiaToR achieves both small mice flow completion time (FCT) and high goodput on two representative flat topologies, especially under heavy loads. Particularly, the FCT of mice flows is one to two orders of magnitude better than the state-of-the-art traffic-oblivious reconfigurable DCN design.

cs.NI↗

arXiv2024

LINEAR: Learning Implicit Neural Representation With Explicit Physical Priors for Accelerated Quantitative T1rho Mapping

Quantitative T1rho mapping has shown promise in clinical and research studies. However, it suffers from long scan times. Deep learning-based techniques have been successfully applied in accelerated quantitative MR parameter mapping. However, most methods require fully-sampled training dataset, which is impractical in the clinic. In this study, a novel subject-specific unsupervised method based on the implicit neural representation is proposed to reconstruct T1rho-weighted images from highly undersampled k-space data, which only takes spatiotemporal coordinates as the input. Specifically, the proposed method learned a implicit neural representation of the MR images driven by two explicit priors from the physical model of T1rho mapping, including the signal relaxation prior and self-consistency of k-t space data prior. The proposed method was verified using both retrospective and prospective undersampled k-space data. Experiment results demonstrate that LINEAR achieves a high acceleration factor up to 14, and outperforms the state-of-the-art methods in terms of suppressing artifacts and achieving the lowest error.

eess.IV↗

arXiv2024

Harnessing Natural Oscillations for High-Speed, Efficient Asymmetrical Locomotion in Quadrupedal Robots

This study explores the dynamics of asymmetrical bounding gaits in quadrupedal robots, focusing on the integration of torso pitching and hip motion to enhance speed and stability. Traditional control strategies often enforce a fixed posture, minimizing natural body movements to simplify the control problem. However, this approach may overlook the inherent dynamical advantages found in natural locomotion. By considering the robot as two interconnected segments, we concentrate on stance leg motion while allowing passive torso oscillation, drawing inspiration from natural dynamics and underactuated robotics principles. Our control scheme employs Linear Inverted Pendulum (LIP) and Spring-Loaded Inverted Pendulum (SLIP) models to govern front and rear leg movements independently. This approach has been validated through extensive simulations and hardware experiments, demonstrating successful high-speed locomotion with top speeds nearing 4 m/s and reduced ground reaction forces, indicating a more efficient gait. Furthermore, unlike conventional methods, our strategy leverages natural torso oscillations to aid leg circulation and stride length, aligning robot dynamics more closely with biological counterparts. Our findings suggest that embracing the natural dynamics of quadrupedal movement, particularly in asymmetrical gaits like bounding, can lead to more stable, efficient, and high-speed robotic locomotion. This investigation lays the groundwork for future studies on versatile and dynamic quadrupedal gaits and their potential applications in scenarios demanding rapid and effective locomotion.

cs.RO↗

arXiv2024

Learning Stable and Passive Neural Differential Equations

In this paper, we introduce a novel class of neural differential equation, which are intrinsically Lyapunov stable, exponentially stable or passive. We take a recently proposed Polyak Lojasiewicz network (PLNet) as an Lyapunov function and then parameterize the vector field as the descent directions of the Lyapunov function. The resulting models have a same structure as the general Hamiltonian dynamics, where the Hamiltonian is lower- and upper-bounded by quadratic functions. Moreover, it is also positive definite w.r.t. either a known or learnable equilibrium. We illustrate the effectiveness of the proposed model on a damped double pendulum system.

eess.SY↗

arXiv2023

Proximal Gradient Descent Unfolding Dense-spatial Spectral-attention Transformer for Compressive Spectral Imaging

The Coded Aperture Snapshot Spectral Compressive Imaging (CASSI) system modulates three-dimensional hyperspectral images into two-dimensional compressed images in a single exposure. Subsequently, three-dimensional hyperspectral images (HSI) can be reconstructed from the two-dimensional compressed measurements using reconstruction algorithms. Among these methods, deep unfolding techniques have demonstrated excellent performance, with RDLUF-MixS^2 achieving the best reconstruction results. However, RDLUF-MixS^2 requires extensive training time, taking approximately 14 days to train RDLUF-MixS^2-9stg on a single RTX 3090 GPU, making it computationally expensive. Furthermore, RDLUF-MixS^2 performs poorly on real data, resulting in significant artifacts in the reconstructed images. In this study, we introduce the Dense-spatial Spectral-attention Transformer (DST) into the Proximal Gradient Descent Unfolding Framework (PGDUF), creating a novel approach called Proximal Gradient Descent Unfolding Dense-spatial Spectral-attention Transformer (PGDUDST). Compared to RDLUF-MixS^2, PGDUDST not only surpasses the network reconstruction performance limit of RDLUF-MixS^2 but also achieves faster convergence. PGDUDST requires only 58% of the training time of RDLUF-MixS^2-9stg to achieve comparable reconstruction results. Additionally, PGDUDST significantly alleviates the artifact issues caused by RDLUF-MixS^2 in real experimental data, demonstrating superior performance and producing clearer reconstructed images.

eess.SP↗

arXiv2023

Physics-Informed DeepMRI: Bridging the Gap from Heat Diffusion to k-Space Interpolation

In the field of parallel imaging (PI), alongside image-domain regularization methods, substantial research has been dedicated to exploring $k$-space interpolation. However, the interpretability of these methods remains an unresolved issue. Furthermore, these approaches currently face acceleration limitations that are comparable to those experienced by image-domain methods. In order to enhance interpretability and overcome the acceleration limitations, this paper introduces an interpretable framework that unifies both $k$-space interpolation techniques and image-domain methods, grounded in the physical principles of heat diffusion equations. Building upon this foundational framework, a novel $k$-space interpolation method is proposed. Specifically, we model the process of high-frequency information attenuation in $k$-space as a heat diffusion equation, while the effort to reconstruct high-frequency information from low-frequency regions can be conceptualized as a reverse heat equation. However, solving the reverse heat equation poses a challenging inverse problem. To tackle this challenge, we modify the heat equation to align with the principles of magnetic resonance PI physics and employ the score-based generative method to precisely execute the modified reverse heat diffusion. Finally, experimental validation conducted on publicly available datasets demonstrates the superiority of the proposed approach over traditional $k$-space interpolation methods, deep learning-based $k$-space interpolation methods, and conventional diffusion models in terms of reconstruction accuracy, particularly in high-frequency regions.

cs.CV↗