Guoxi Huang

Guoxi Huang, Hongtao Fu, Adrian G. Bors

Deeper Vision Transformers (ViTs) are more challenging to train. We expose a degradation problem in deeper layers of ViT when using masked image modeling (MIM) for pre-training. To ease the training of deeper ViTs, we introduce a self-supervised learning framework called Masked Image Residual Learning (MIRL), which significantly alleviates the degradation problem, making scaling ViT along depth a promising direction for performance upgrade. We reformulate the pre-training objective for deeper layers of ViT as learning to recover the residual of the masked image. We provide extensive empirical evidence showing that deeper ViTs can be effectively optimized using MIRL and easily gain accuracy from increased depth. With the same level of computational complexity as ViT-Base and ViT-Large, we instantiate 4.5$\times$ and 2$\times$ deeper ViTs, dubbed ViT-S-54 and ViT-B-48. The deeper ViT-S-54, costing 3$\times$ less than ViT-Large, achieves performance on par with ViT-Large. ViT-B-48 achieves 86.2% top-1 accuracy on ImageNet. On one hand, deeper ViTs pre-trained with MIRL exhibit excellent generalization capabilities on downstream tasks, such as object detection and semantic segmentation. On the other hand, MIRL demonstrates high pre-training efficiency. With less pre-training time, MIRL yields competitive performance compared to other approaches.

Ruirui Lin, Nantheera Anantrasirichai, Guoxi Huang et al.

Low-light videos often exhibit spatiotemporal incoherent noise, compromising visibility and performance in computer vision applications. One significant challenge in enhancing such content using deep learning is the scarcity of training data. This paper introduces a novel low-light video dataset, consisting of 40 scenes with various motion scenarios under two distinct low-lighting conditions, incorporating genuine noise and temporal artifacts. We provide fully registered ground truth data captured in normal light using a programmable motorized dolly and refine it via an image-based approach for pixel-wise frame alignment across different light levels. We provide benchmarks based on four different technologies: convolutional neural networks, transformers, diffusion models, and state space models (mamba). Our experimental results demonstrate the significance of fully registered video pairs for low-light video enhancement (LLVE) and the comprehensive evaluation shows that the models trained with our dataset outperform those trained with the existing datasets. Our dataset and links to benchmarks are publicly available at https://doi.org/10.21227/mzny-8c77.

Bin Hu, Zipeng Qi, Guoxi Huang et al. · tsinghua

Single-view reference-to-video methods often struggle to preserve identity consistency under large facial-angle variations. This limitation naturally motivates the incorporation of multi-view facial references. However, simply introducing additional reference images exacerbates the \textit{copy-paste} problem, particularly the \textbf{\textit{view-dependent copy-paste}} artifact, which reduces facial motion naturalness. Although cross-paired data can alleviate this issue, collecting such data is costly. To balance the consistency and naturalness, we propose $\mathrm{Mv}^2\mathrm{ID}$, a multi-view conditioned framework under in-paired supervision. We introduce a region-masking training strategy to prevent shortcut learning and extract essential identity features by encouraging the model to aggregate complementary identity cues across views. In addition, we design a reference decoupled-RoPE mechanism that assigns distinct positional encoding to video and conditioning tokens for better modeling of their heterogeneous properties. Furthermore, we construct a large-scale dataset with diverse facial-angle variations and propose dedicated evaluation metrics for identity consistency and motion naturalness. Extensive experiments demonstrate that our method significantly improves identity consistency while maintaining motion naturalness, outperforming existing approaches trained with cross-paired data.

Guoxi Huang, Adrian G. Bors

Static appearance of video may impede the ability of a deep neural network to learn motion-relevant features in video action recognition. In this paper, we introduce a new concept, Dynamic Appearance (DA), summarizing the appearance information relating to movement in a video while filtering out the static information considered unrelated to motion. We consider distilling the dynamic appearance from raw video data as a means of efficient video understanding. To this end, we propose the Pixel-Wise Temporal Projection (PWTP), which projects the static appearance of a video into a subspace within its original vector space, while the dynamic appearance is encoded in the projection residual describing a special motion pattern. Moreover, we integrate the PWTP module with a CNN or Transformer into an end-to-end training framework, which is optimized by utilizing multi-objective optimization algorithms. We provide extensive experimental results on four action recognition benchmarks: Kinetics400, Something-Something V1, UCF101 and HMDB51.

Ruirui Lin, Guoxi Huang, David Bull et al.

Low-light images exhibit severe noise, contrast loss, and semantic ambiguity, making enhancement a joint problem of denoising and detail recovery. We propose PixIE, a feed-forward pixel-space LLIE framework semantically-prompted by a vision foundation model. PixIE first performs a cross-scale denoising to suppress noise and preserve structure, then refines details with DINO-Prompted Pixel Blocks (DPPB) that inject intermediate DINOv3 features via patch-conditioned, spatially continuous per-pixel modulation. We introduce a Spatial-Channel Compaction (SCC), which folds features into a compact spatial grid and compresses in the channel dimension, so pixel-attention is computed efficiently with bounded cost across scales. We further propose Multi-Receptive-Field Pixel Embedding (MRPE) to provide neighborhood-aware pixel representations before semantic prompting, improving robustness to signal-dependent noise beyond point-wise embeddings. Experiments on LLIE benchmarks show that PixIE improves the average PSNR by 1.9-15.0% over recent state-of-the-art methods and reduces LPIPS by 8.5-44.4%. Qualitative comparisons further demonstrate that PixIE recovers sharper details and more stable textures, resulting in improved reconstruction fidelity and perceptual quality.

Guoxi Huang, Ruirui Lin, Yini Li et al.

Videos captured in low-light and underwater conditions often suffer from distortions such as noise, low contrast, color imbalance, and blur. These issues not only limit visibility but also degrade automatic tasks like detection. Post-processing is typically required but can be time-consuming. AI-based tools for video enhancement also demand significantly more computational resources compared to image-based methods. This paper introduces a novel framework, Visual Mamba, designed to reduce memory usage and computational time by leveraging the Visual State Space (VSS) model. The framework consists of two modules: (i) a feature alignment module, where spatio-temporal displacement between input frames is registered in the feature space, and (ii) an enhancement module, where noise removal and brightness adjustment are performed using a UNet-like architecture, with all convolutional layers replaced by VSS blocks. Experimental results show that the Visual Mamba technique outperforms Transformer and convolution-based models in both low-light and underwater video enhancement tasks. Code is available on line at https://github.com/russellllaputa/BVI-Mamba.

Zipeng Qi, Guoxi Huang, Chenyang Liu et al.

This paper introduces innovative solutions to enhance spatial controllability in diffusion models reliant on text queries. We first introduce vision guidance as a foundational spatial cue within the perturbed distribution. This significantly refines the search space in a zero-shot paradigm to focus on the image sampling process adhering to the spatial layout conditions. To precisely control the spatial layouts of multiple visual concepts with the employment of vision guidance, we propose a universal framework, Layered Rendering Diffusion (LRDiff), which constructs an image-rendering process with multiple layers, each of which applies the vision guidance to instructively estimate the denoising direction for a single object. Such a layered rendering strategy effectively prevents issues like unintended conceptual blending or mismatches while allowing for more coherent and contextually accurate image synthesis. The proposed method offers a more efficient and accurate means of synthesising images that align with specific layout and contextual requirements. Through experiments, we demonstrate that our method outperforms existing techniques, both quantitatively and qualitatively, in two specific layout-to-image tasks: bounding box-to-image and instance maskto-image. Furthermore, we extend the proposed framework to enable spatially controllable editing

Zhuodong Jiang, Haoran Wang, Guoxi Huang et al.

Reconstructing high-fidelity underwater scenes remains a challenging task due to light absorption, scattering, and limited visibility inherent in aquatic environments. This paper presents an enhanced Gaussian Splatting-based framework that improves both the visual quality and geometric accuracy of deep underwater rendering. We propose decoupled learning for RGB channels, guided by the physics of underwater attenuation, to enable more accurate colour restoration. To address sparse-view limitations and improve view consistency, we introduce a frame interpolation strategy with a novel adaptive weighting scheme. Additionally, we introduce a new loss function aimed at reducing noise while preserving edges, which is essential for deep-sea content. We also release a newly collected dataset, Submerged3D, captured specifically in deep-sea environments. Experimental results demonstrate that our framework consistently outperforms state-of-the-art methods with PSNR gains up to 1.90dB, delivering superior perceptual quality and robustness, and offering promising directions for marine robotics and underwater visual analytics. The code of RUSplatting is available at https://github.com/theflash987/RUSplatting and the dataset Submerged3D can be downloaded at https://zenodo.org/records/15482420.

Xiaoning Liu, Zongwei Wu, Florin-Alexandru Vasluianu et al.

This paper presents a comprehensive review of the NTIRE 2025 Low-Light Image Enhancement (LLIE) Challenge, highlighting the proposed solutions and final outcomes. The objective of the challenge is to identify effective networks capable of producing brighter, clearer, and visually compelling images under diverse and challenging conditions. A remarkable total of 762 participants registered for the competition, with 28 teams ultimately submitting valid entries. This paper thoroughly evaluates the state-of-the-art advancements in LLIE, showcasing the significant progress.

Xin Li, Yeying Jin, Xin Jin et al.

This paper reviews the NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images. This challenge received a wide range of impressive solutions, which are developed and evaluated using our collected real-world Raindrop Clarity dataset. Unlike existing deraining datasets, our Raindrop Clarity dataset is more diverse and challenging in degradation types and contents, which includes day raindrop-focused, day background-focused, night raindrop-focused, and night background-focused degradations. This dataset is divided into three subsets for competition: 14,139 images for training, 240 images for validation, and 731 images for testing. The primary objective of this challenge is to establish a new and powerful benchmark for the task of removing raindrops under varying lighting and focus conditions. There are a total of 361 participants in the competition, and 32 teams submitting valid solutions and fact sheets for the final testing phase. These submissions achieved state-of-the-art (SOTA) performance on the Raindrop Clarity dataset. The project can be found at https://lixinustc.github.io/CVPR-NTIRE2025-RainDrop-Competition.github.io/.

Guoxi Huang, Nantheera Anantrasirichai, Fei Ye et al.

In image enhancement tasks, such as low-light and underwater image enhancement, a degraded image can correspond to multiple plausible target images due to dynamic photography conditions, such as variations in illumination. This naturally results in a one-to-many mapping challenge. To address this, we propose a Bayesian Enhancement Model (BEM) that incorporates Bayesian Neural Networks (BNNs) to capture data uncertainty and produce diverse outputs. To achieve real-time inference, we introduce a two-stage approach: Stage I employs a BNN to model the one-to-many mappings in the low-dimensional space, while Stage II refines fine-grained image details using a Deterministic Neural Network (DNN). To accelerate BNN training and convergence, we introduce a dynamic Momentum Prior. Extensive experiments on multiple low-light and underwater image enhancement benchmarks demonstrate the superiority of our method over deterministic models.

Guoxi Huang, Haoran Wang, Brett Seymour et al.

Underwater visual enhancement (UVE) and underwater 3D reconstruction pose significant challenges in computer vision and AI-based tasks due to complex imaging conditions in aquatic environments. Despite the development of numerous enhancement algorithms, a comprehensive and systematic review covering both UVE and underwater 3D reconstruction remains absent. To advance research in these areas, we present an in-depth review from multiple perspectives. First, we introduce the fundamental physical models, highlighting the peculiarities that challenge conventional techniques. We survey advanced methods for visual enhancement and 3D reconstruction specifically designed for underwater scenarios. The paper assesses various approaches from non-learning methods to advanced data-driven techniques, including Neural Radiance Fields and 3D Gaussian Splatting, discussing their effectiveness in handling underwater distortions. Finally, we conduct both quantitative and qualitative evaluations of state-of-the-art UVE and underwater 3D reconstruction algorithms across multiple benchmark datasets. Finally, we highlight key research directions for future advancements in underwater vision.

Runqing Wu, Fei Ye, Qihe Liu et al.

Continual Learning seeks to develop a model capable of incrementally assimilating new information while retaining prior knowledge. However, current research predominantly addresses a straightforward learning context, wherein all data samples originate from a singular data domain. This paper shifts focus to a more complex and realistic learning environment, characterized by data samples sourced from multiple distinct domains. We tackle this intricate learning challenge by introducing a novel methodology, termed the Multi-Source Dynamic Expansion Model (MSDEM), which leverages various pre-trained models as backbones and progressively establishes new experts based on them to adapt to emerging tasks. Additionally, we propose an innovative dynamic expandable attention mechanism designed to selectively harness knowledge from multiple backbones, thereby accelerating the new task learning. Moreover, we introduce a dynamic graph weight router that strategically reuses all previously acquired parameters and representations for new task learning, maximizing the positive knowledge transfer effect, which further improves generalization performance. We conduct a comprehensive series of experiments, and the empirical findings indicate that our proposed approach achieves state-of-the-art performance.

Ruirui Lin, Guoxi Huang, Nantheera Anantrasirichai

Low-light video enhancement (LLVE) is challenging due to noise, low contrast, and color degradations. Learning-based approaches offer fast inference but still struggle with heavy noise in real low-light scenes, primarily due to limitations in effectively leveraging temporal information. In this paper, we address this issue with DWTA-Net, a novel two-stage framework that jointly exploits short- and long-term temporal cues. Stage I employs Visual State-Space blocks for multi-frame alignment, recovering brightness, color, and structure with local consistency. Stage II introduces a recurrent refinement module with dynamic weight-based temporal aggregation guided by optical flow, adaptively balancing static and dynamic regions. A texture-adaptive loss further preserves fine details while promoting smoothness in flat areas. Experiments on real-world low-light videos show that DWTA-Net effectively suppresses noise and artifacts, delivering superior visual quality compared with state-of-the-art methods.

Guoxi Huang, Haoran Wang, Zipeng Qi et al.

Underwater image degradation poses significant challenges for 3D reconstruction, where simplified physical models often fail in complex scenes. We propose \textbf{R-Splatting}, a unified framework that bridges underwater image restoration (UIR) with 3D Gaussian Splatting (3DGS) to improve both rendering quality and geometric fidelity. Our method integrates multiple enhanced views produced by diverse UIR models into a single reconstruction pipeline. During inference, a lightweight illumination generator samples latent codes to support diverse yet coherent renderings, while a contrastive loss ensures disentangled and stable illumination representations. Furthermore, we propose \textit{Uncertainty-Aware Opacity Optimization (UAOO)}, which models opacity as a stochastic function to regularize training. This suppresses abrupt gradient responses triggered by illumination variation and mitigates overfitting to noisy or view-specific artifacts. Experiments on Seathru-NeRF and our new BlueCoral3D dataset demonstrate that R-Splatting outperforms strong baselines in both rendering quality and geometric accuracy.

Zhuodong Jiang, Haoran Wang, Guoxi Huang et al.

Accurate 3D reconstruction in underwater environments remains a complex challenge due to issues such as light distortion, turbidity, and limited visibility. AI-based techniques have been applied to address these issues, however, existing methods have yet to fully exploit the potential of AI, particularly in integrating language models with visual processing. In this paper, we propose a novel framework that leverages multimodal cross-knowledge to create semantic-guided 3D Gaussian Splatting for robust and high-fidelity deep-sea scene reconstruction. By embedding an extra semantic feature into each Gaussian primitive and supervised by the CLIP extracted semantic feature, our method enforces semantic and structural awareness throughout the training. The dedicated semantic consistency loss ensures alignment with high-level scene understanding. Besides, we propose a novel stage-wise training strategy, combining coarse-to-fine learning with late-stage parameter refinement, to further enhance both stability and reconstruction quality. Extensive results show that our approach consistently outperforms state-of-the-art methods on SeaThru-NeRF and Submerged3D datasets across three metrics, with an improvement of up to 3.09 dB on average in terms of PSNR, making it a strong candidate for applications in underwater exploration and marine perception.

Alexandra Malyugina, Guoxi Huang, Eduardo Ruiz et al.

Underwater videos often suffer from degraded quality due to light absorption, scattering, and various noise sources. Among these, marine snow, which is suspended organic particles appearing as bright spots or noise, significantly impacts machine vision tasks, particularly those involving feature matching. Existing methods for removing marine snow are ineffective due to the lack of paired training data. To address this challenge, this paper proposes a novel enhancement framework that introduces a new approach for generating paired datasets from raw underwater videos. The resulting dataset consists of paired images of generated snowy and snow, free underwater videos, enabling supervised training for video enhancement. We describe the dataset creation process, highlight its key characteristics, and demonstrate its effectiveness in enhancing underwater image restoration in the absence of ground truth.

Guoxi Huang, Adrian G. Bors

In video data, busy motion details from moving regions are conveyed within a specific frequency bandwidth in the frequency domain. Meanwhile, the rest of the frequencies of video data are encoded with quiet information with substantial redundancy, which causes low processing efficiency in existing video models that take as input raw RGB frames. In this paper, we consider allocating intenser computation for the processing of the important busy information and less computation for that of the quiet information. We design a trainable Motion Band-Pass Module (MBPM) for separating busy information from quiet information in raw video data. By embedding the MBPM into a two-pathway CNN architecture, we define a Busy-Quiet Net (BQN). The efficiency of BQN is determined by avoiding redundancy in the feature space processed by the two pathways: one operating on Quiet features of low-resolution, while the other processes Busy features. The proposed BQN outperforms many recent video processing models on Something-Something V1, Kinetics400, UCF101 and HMDB51 datasets.

Guoxi Huang, Adrian G. Bors

Convolutional Neural Networks (CNNs) model long-range dependencies by deeply stacking convolution operations with small window sizes, which makes the optimizations difficult. This paper presents region-based non-local (RNL) operations as a family of self-attention mechanisms, which can directly capture long-range dependencies without using a deep stack of local operations. Given an intermediate feature map, our method recalibrates the feature at a position by aggregating the information from the neighboring regions of all positions. By combining a channel attention module with the proposed RNL, we design an attention chain, which can be integrated into the off-the-shelf CNNs for end-to-end training. We evaluate our method on two video classification benchmarks. The experimental results of our method outperform other attention mechanisms, and we achieve state-of-the-art performance on the Something-Something V1 dataset.

Guoxi Huang, Adrian G. Bors

In this paper, we propose a new video representation learning method, named Temporal Squeeze (TS) pooling, which can extract the essential movement information from a long sequence of video frames and map it into a set of few images, named Squeezed Images. By embedding the Temporal Squeeze pooling as a layer into off-the-shelf Convolution Neural Networks (CNN), we design a new video classification model, named Temporal Squeeze Network (TeSNet). The resulting Squeezed Images contain the essential movement information from the video frames, corresponding to the optimization of the video classification task. We evaluate our architecture on two video classification benchmarks, and the results achieved are compared to the state-of-the-art.