HHHua Huang

Hua Huang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Hua Huang has a total of 249 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Q-GMRES: Quantized Data Transmission Optimization for Distributed GMRES Algorithm

    by Jianhua Gao, Yuxiang Zhang, Danying Ge, Bingxin Liu, Weixing Ji, Hua Huang

    The generalized minimal residual (GMRES) algorithm is one of the key iterative algorithms for solving large-scale sparse linear systems, which finds extensive application in scientific and engineering computations. Although distributed GMRES can handle large-scale problems, data transmission between multiple nodes emerges as a primary bottleneck. Given the inefficient utilization of finite bits in the IEEE 754 format and the potential impact of low-precision floating-point representations on the convergence of iterative algorithms, this paper proposes a quantization-based method (Q-GMRES) to compress the data transmitted between nodes. Our approach not only reduces the amount of data transmission, but also uses the limited bit-width representation to achieve high accuracy. In this paper, we explore uniform and non-uniform quantization techniques and propose inner-outer mixed-precision and vector segmentation methods to improve residual accuracy. Experimental results demonstrate that the proposed communication compression method, which combines INT16 quantization with vector segmentation, achieves speedups of up to 2.19x and 2.49x on four and eight processes, respectively, while maintaining convergence accuracy comparable to GMRES-FP64.

  • GANG: Geometrically-Aligned Neural Gaussians for Efficient and Realistic Relighting

    by Deqi Li, Shi-Sheng Huang, Hongbo Fu, Hua Huang

    Efficient and realistic relighting of complex scenes with unknown illumination remains a crucial but challenging task. Recent advancements in 3D Gaussian Splatting (3DGS) have shown impressive object-level relighting. However, they still struggle with complex real-world scenes, mainly due to the challenges of accurately decoupling intricate geometry, materials, and lighting using concise 3D Gaussian primitives. In this paper, we propose a new Geometrically-Aligned Neural Gaussian Splatting (GANG) method, which performs efficient physically based rendering (PBR) directly on anchor-based relightable neural Gaussians. Our key idea is to regularize the decoded neural Gaussians geometrically aligned with the latent signed distance field (SDF) surface spawned from anchors using a differentiable implicit indicator function (IIF) solver. It brings effective geometric association to accurate decoupling of materials and lighting for efficient and realistic relighting of complex scenes. Furthermore, we propose a locally consistent geometry regularization to guide more concise neural Gaussian learning with a hybrid lighting model, which combines position-learnable spherical Gaussians (SGs) and an environment map, allowing accurate modeling of both local and global illumination. Experimental results on public datasets demonstrate that GANG consistently outperforms previous PBR methods in material decomposition and relighting quality, while representing complex scenes with concise anchors. To the best of our knowledge, GANG is a new state-of-the-art 3DGS method for realistic relighting, enabling efficient rendering and flexible editing materials and illumination, especially for complex scenes.

  • Self-Supervised Depth Completion Guided by 3D Perception and Geometry Consistency

    by Yu Cai, Tianyu Shen, Shi-Sheng Huang, Hua Huang

    Depth completion which aims at predicting dense depth maps from sparse depth measurements, plays a crucial role in many computer graphics and computer vision applications. Previous supervised learning based approaches have demonstrated overwhelming success in this task, while unsupervised high-precision depth completion without relying on the ground-truth data still remains challenging. One main drawback of most previous unsupervised solutions comes from the ignorance of 3D structural information, which often leads to inaccurate spatial propagation and mixed-depth problems. To alleviate the above challenges, this paper explores the utilization of 3D perceptual features and multi-view geometry consistency to devise a high-precision self-supervised depth completion method. Our key contribution is a 3D perceptual spatial propagation constructed with a point cloud representation and an attention weighting mechanism, to capture more reasonable and favorable neighbors during the depth propagation process. Based on the 3D perceptual spatial propagation, we also introduce multi-view geometric constraints between adjacent views to guide the optimization of the whole depth completion model, which achieves geometry consistent depth completion in a self-supervised manner. Extensive experiments on benchmark datasets of NYU-Depth-v2, VOID and KITTI Depth Completion demonstrate that the proposed model achieves the state-of-the-art depth completion performance compared with other unsupervised methods, and even competitive performance compared with previous supervised methods.

  • Tackling Ill-Posedness of Reversible Image Conversion With Well-Posed Invertible Network

    by Yuanfei Huang, Hua Huang

    Reversible image conversion (RIC) suffers from ill-posedness issues due to its forward conversion process being considered an underdetermined system. Despite employing invertible neural networks (INN), existing RIC methods intrinsically remain ill-posed as inevitably introducing uncertainty by incorporating randomly sampled variables. To tackle the ill-posedness dilemma, we focus on developing a reliable approximate left inverse for the underdetermined system by constructing an overdetermined system with a non-zero Gram determinant, thus ensuring a well-posed solution. Based on this principle, we propose a well-posed invertible $1\times 1$ convolution (WIC), which eliminates the reliance on random variable sampling and enables the development of well-posed invertible networks. Furthermore, we design two innovative networks, WIN-Naïve and WIN, with the latter incorporating advanced skip-connections to enhance long-term memory. Our methods are evaluated across diverse RIC tasks, including reversible image hiding, image rescaling, and image decolorization, consistently achieving state-of-the-art performance. Extensive experiments validate the effectiveness of our approach, demonstrating its ability to overcome the bottlenecks of existing RIC solutions and setting a new benchmark in the field.

  • DSNeRF: Dynamic View Synthesis for Ultra-Fast Scenes From Continuous Spike Streams

    by Lin Zhu, Kangmin Jia, Yifan Zhao, Yunshan Qi, Lizhi Wang, Hua Huang

    Spike cameras generate binary spikes in response to light intensity changes, enabling high-speed visual perception with unprecedented temporal resolution. However, the unique characteristics of spike stream present significant challenges for reconstructing dense 3D scene representations, particularly in dynamic environments and under non-ideal lighting conditions. In this paper, we introduce DSNeRF, the first method to derive a NeRF-based volumetric scene representation from spike camera data. Our approach leverages NeRF’s multi-view consistency to establish robust self-supervision, effectively eliminating erroneous measurements and uncovering coherent structures within exceedingly noisy input amidst diverse real-world illumination scenarios. We propose a novel mapping from pixel rays to the spike domain, integrating the spike generation process directly into NeRF training. Specifically, DSNeRF introduces an integrate-and-fire neuron layer that models non-idealities to capture intrinsic camera noise, including both random and fixed-pattern spike noise, thereby enhancing scene fidelity. Additionally, we propose a motion-guided spiking neuron layer and a long-term rendering photometric loss to better align dynamic spike streams, ensuring accurate scene geometry. Our method optimizes neural radiance fields to render photorealistic novel views from continuous spike streams, demonstrating advantages over other vision sensors in certain scenes. Empirical evaluations on both real and simulated sequences validate the effectiveness of our approach.

  • Learning Physics-Informed Noise Models from Dark Frames for Low-Light Raw Image Denoising

    by Hansen Feng, Lizhi Wang, Yiqi Huang, Yuzhi Wang, Lin Zhu, Hua Huang

    Recently, the mainstream practice for training low-light raw image denoising methods has shifted towards employing synthetic data. Noise modeling, which focuses on characterizing the noise distribution of real-world sensors, profoundly influences the effectiveness and practicality of synthetic data. Currently, physics-based noise modeling struggles to characterize the entire real noise distribution, while learning-based noise modeling impractically depends on paired real data. In this paper, we propose a novel strategy: learning the noise model from dark frames instead of paired real data, to break down the data dependency. Based on this strategy, we introduce an efficient physics-informed noise neural proxy (PNNP) to approximate the real-world sensor noise model. Specifically, we integrate physical priors into neural proxies and introduce three efficient techniques: physics-guided noise decoupling (PND), physics-aware proxy model (PPM), and differentiable distribution loss (DDL). PND decouples the dark frame into different components and handles different levels of noise flexibly, which reduces the complexity of noise modeling. PPM incorporates physical priors to constrain the synthetic noise, which promotes the accuracy of noise modeling. DDL provides explicit and reliable supervision for noise distribution, which promotes the precision of noise modeling. PNNP exhibits powerful potential in characterizing the real noise distribution. Extensive experiments on public datasets demonstrate superior performance in practical low-light raw image denoising. The source code will be publicly available at the https://fenghansen.github.io/publication/PNNP.