Jinglei Shi

Xi Wang, Robin Courant, Jinglei Shi et al.

This paper presents JAWS, an optimization-driven approach that achieves the robust transfer of visual cinematic features from a reference in-the-wild video clip to a newly generated clip. To this end, we rely on an implicit-neural-representation (INR) in a way to compute a clip that shares the same cinematic features as the reference clip. We propose a general formulation of a camera optimization problem in an INR that computes extrinsic and intrinsic camera parameters as well as timing. By leveraging the differentiability of neural representations, we can back-propagate our designed cinematic losses measured on proxy estimators through a NeRF network to the proposed cinematic parameters directly. We also introduce specific enhancements such as guidance maps to improve the overall quality and efficiency. Results display the capacity of our system to replicate well known camera sequences from movies, adapting the framing, camera parameters and timing of the generated video clip to maximize the similarity with the reference clip.

Jinglei Shi, Yihong Xu, Christine Guillemot

Light field is a type of image data that captures the 3D scene information by recording light rays emitted from a scene at various orientations. It offers a more immersive perception than classic 2D images but at the cost of huge data volume. In this paper, we draw inspiration from the visual characteristics of Sub-Aperture Images (SAIs) of light field and design a compact neural network representation for the light field compression task. The network backbone takes randomly initialized noise as input and is supervised on the SAIs of the target light field. It is composed of two types of complementary kernels: descriptive kernels (descriptors) that store scene description information learned during training, and modulatory kernels (modulators) that control the rendering of different SAIs from the queried perspectives. To further enhance compactness of the network meanwhile retain high quality of the decoded light field, we accordingly introduce modulator allocation and kernel tensor decomposition mechanisms, followed by non-uniform quantization and lossless entropy coding techniques, to finally form an efficient compression pipeline. Extensive experiments demonstrate that our method outperforms other state-of-the-art (SOTA) methods by a significant margin in the light field compression task. Moreover, after aligning descriptors, the modulators learned from one light field can be transferred to new light fields for rendering dense views, indicating a potential solution for view synthesis task.

Jinglei Shi, Christine Guillemot

We propose in this paper a Quantized Distilled Low-Rank Neural Radiance Field (QDLR-NeRF) representation for the task of light field compression. While existing compression methods encode the set of light field sub-aperture images, our proposed method learns an implicit scene representation in the form of a Neural Radiance Field (NeRF), which also enables view synthesis. To reduce its size, the model is first learned under a Low-Rank (LR) constraint using a Tensor Train (TT) decomposition within an Alternating Direction Method of Multipliers (ADMM) optimization framework. To further reduce the model's size, the components of the tensor train decomposition need to be quantized. However, simultaneously considering the optimization of the NeRF model with both the low-rank constraint and rate-constrained weight quantization is challenging. To address this difficulty, we introduce a network distillation operation that separates the low-rank approximation and the weight quantization during network training. The information from the initial LR-constrained NeRF (LR-NeRF) is distilled into a model of much smaller dimension (DLR-NeRF) based on the TT decomposition of the LR-NeRF. We then learn an optimized global codebook to quantize all TT components, producing the final QDLR-NeRF. Experimental results show that our proposed method yields better compression efficiency compared to state-of-the-art methods, and it additionally has the advantage of allowing the synthesis of any light field view with high quality.

Tengjiao Yin, Jinglei Shi, Heng Guo et al.

Video diffusion models lack explicit geometric supervision during training, leading to inconsistency artifacts such as object deformation, spatial drift, and depth violations in generated videos. To address this limitation, we propose a geometry-based reward model that leverages pretrained geometric foundation models to evaluate multi-view consistency through cross-frame reprojection error. Unlike previous geometric metrics that measure inconsistency in pixel space, where pixel intensity may introduce additional noise, our approach conducts error computation in a pointwise fashion, yielding a more physically grounded and robust error metric. Furthermore, we introduce a geometry-aware sampling strategy that filters out low-texture and non-semantic regions, focusing evaluation on geometrically meaningful areas with reliable correspondences to improve robustness. We apply this reward model to align video diffusion models through two complementary pathways: post-training of a bidirectional model via SFT or Reinforcement Learning and inference-time optimization of a Causal Video Model (e.g., Streaming video generator) via test-time scaling with our reward as a path verifier. Experimental results validate the effectiveness of our design, demonstrating that our geometry-based reward provides superior robustness compared to other variants. By enabling efficient inference-time scaling, our method offers a practical solution for enhancing open-source video models without requiring extensive computational resources for retraining.

Jinglei Shi, Yihong Xu, Christine Guillemot

Light fields are a type of image data that capture both spatial and angular scene information by recording light rays emitted by a scene from different orientations. In this context, spatial information is defined as features that remain static regardless of perspectives, while angular information refers to features that vary between viewpoints. We propose a novel neural network that, by design, can separate angular and spatial information of a light field. The network represents spatial information using spatial kernels shared among all Sub-Aperture Images (SAIs), and angular information using sets of angular kernels for each SAI. To further improve the representation capability of the network without increasing parameter number, we also introduce angular kernel allocation and kernel tensor decomposition mechanisms. Extensive experiments demonstrate the benefits of information separation: when applied to the compression task, our network outperforms other state-of-the-art methods by a large margin. And angular information can be easily transferred to other scenes for rendering dense views, showing the successful separation and the potential use case for the view synthesis task. We plan to release the code upon acceptance of the paper to encourage further research on this topic.

Shihao Zhou, Jinshan Pan, Jinglei Shi et al.

How to explore useful features from images as prompts to guide the deep image restoration models is an effective way to solve image restoration. In contrast to mining spatial relations within images as prompt, which leads to characteristics of different frequencies being neglected and further remaining subtle or undetectable artifacts in the restored image, we develop a Frequency Prompting image restoration method, dubbed FPro, which can effectively provide prompt components from a frequency perspective to guild the restoration model address these differences. Specifically, we first decompose input features into separate frequency parts via dynamically learned filters, where we introduce a gating mechanism for suppressing the less informative elements within the kernels. To propagate useful frequency information as prompt, we then propose a dual prompt block, consisting of a low-frequency prompt modulator (LPM) and a high-frequency prompt modulator (HPM), to handle signals from different bands respectively. Each modulator contains a generation process to incorporate prompting components into the extracted frequency maps, and a modulation part that modifies the prompt feature with the guidance of the decoder features. Experimental results on commonly used benchmarks have demonstrated the favorable performance of our pipeline against SOTA methods on 5 image restoration tasks, including deraining, deraindrop, demoiréing, deblurring, and dehazing. The source code and pre-trained models will be available at https://github.com/joshyZhou/FPro.

Zaiyan Yang, Xinpeng Liu, Heng Guo et al.

We propose a neural regularization method that refines the noisy 3D semantic field produced by lifting multi-view inconsistent 2D features, in order to obtain an accurate and robust 3D semantic Gaussian Splatting. The 2D features extracted from vision foundation models suffer from multi-view inconsistency due to a lack of cross-view constraints. Lifting these inconsistent features directly into 3D Gaussians results in a noisy semantic field, which degrades the performance of downstream tasks. Previous methods either focus on obtaining consistent multi-view features in the preprocessing stage or aim to mitigate noise through improved optimization strategies, often at the cost of increased preprocessing time or expensive computational overhead. In contrast, we introduce a variance-aware conditional MLP that operates directly on the 3D Gaussians, leveraging their geometric and appearance attributes to correct semantic errors in 3D space. Experiments on different datasets show that our method enhances the accuracy of lifted semantics, providing an efficient and effective approach to robust 3D semantic Gaussian Splatting.

Shihao Zhou, Dayu Li, Jinshan Pan et al.

Transformer-based approaches have gained significant attention in image restoration, where the core component, i.e, Multi-Head Attention (MHA), plays a crucial role in capturing diverse features and recovering high-quality results. In MHA, heads perform attention calculation independently from uniform split subspaces, and a redundancy issue is triggered to hinder the model from achieving satisfactory outputs. In this paper, we propose to improve MHA by exploring diverse learners and introducing various interactions between heads, which results in a Hierarchical multI-head atteNtion driven Transformer model, termed HINT, for image restoration. HINT contains two modules, i.e., the Hierarchical Multi-Head Attention (HMHA) and the Query-Key Cache Updating (QKCU) module, to address the redundancy problem that is rooted in vanilla MHA. Specifically, HMHA extracts diverse contextual features by employing heads to learn from subspaces of varying sizes and containing different information. Moreover, QKCU, comprising intra- and inter-layer schemes, further reduces the redundancy problem by facilitating enhanced interactions between attention heads within and across layers. Extensive experiments are conducted on 12 benchmarks across 5 image restoration tasks, including low-light enhancement, dehazing, desnowing, denoising, and deraining, to demonstrate the superiority of HINT. The source code is available in the supplementary materials.

Xin Zhang, Teodor Boyadzhiev, Jinglei Shi et al.

In this paper, we leverage image complexity as a prior for refining segmentation features to achieve accurate real-time semantic segmentation. The design philosophy is based on the observation that different pixel regions within an image exhibit varying levels of complexity, with higher complexities posing a greater challenge for accurate segmentation. We thus introduce image complexity as prior guidance and propose the Image Complexity prior-guided Feature Refinement Network (ICFRNet). This network aggregates both complexity and segmentation features to produce an attention map for refining segmentation features within an Image Complexity Guided Attention (ICGA) module. We optimize the network in terms of both segmentation and image complexity prediction tasks with a combined loss function. Experimental results on the Cityscapes and CamViD datasets have shown that our ICFRNet achieves higher accuracy with a competitive efficiency for real-time segmentation.

Yingjie Xia, Xi Wang, Jinglei Shi et al.

Images evoke emotions that profoundly influence perception, often prioritized over content. Current Image Emotional Synthesis (IES) approaches artificially separate generation and editing tasks, creating inefficiencies and limiting applications where these tasks naturally intertwine, such as therapeutic interventions or storytelling. In this work, we introduce MUSE, the first unified framework capable of both emotional generation and editing. By adopting a strategy conceptually aligned with Test-Time Scaling (TTS) that widely used in both LLM and diffusion model communities, it avoids the requirement for additional updating diffusion model and specialized emotional synthesis datasets. More specifically, MUSE addresses three key questions in emotional synthesis: (1) HOW to stably guide synthesis by leveraging an off-the-shelf emotion classifier with gradient-based optimization of emotional tokens; (2) WHEN to introduce emotional guidance by identifying the optimal timing using semantic similarity as a supervisory signal; and (3) WHICH emotion to guide synthesis through a multi-emotion loss that reduces interference from inherent and similar emotions. Experimental results show that MUSE performs favorably against all methods for both generation and editing, improving emotional accuracy and semantic diversity while maintaining an optimal balance between desired content, adherence to text prompts, and realistic emotional expression. It establishes a new paradigm for emotion synthesis.

Lishen Qu, Shihao Zhou, Jinshan Pan et al.

Intense light sources often produce flares in captured images at night, which deteriorates the visual quality and negatively affects downstream applications. In order to train an effective flare removal network, a reliable dataset is essential. The mainstream flare removal datasets are semi-synthetic to reduce human labour, but these datasets do not cover typical scenarios involving multiple scattering flares. To tackle this issue, we synthesize a prior-guided dataset named Flare7K*, which contains multi-flare images where the brightness of flares adheres to the laws of illumination. Besides, flares tend to occupy localized regions of the image but existing networks perform flare removal on the entire image and sometimes modify clean areas incorrectly. Therefore, we propose a plug-and-play Adaptive Focus Module (AFM) that can adaptively mask the clean background areas and assist models in focusing on the regions severely affected by flares. Extensive experiments demonstrate that our data synthesis method can better simulate real-world scenes and several models equipped with AFM achieve state-of-the-art performance on the real-world test dataset.

Yingjie Xia, Tao Liu, Jinglei Shi et al.

Video Large Language Models (VLLMs) face the challenge of high computational load during the pre-filling stage due to the processing of an enormous number of visual tokens. Although attention-based pruning methods are widely used to accelerate inference, trials at early decoder layers often result in significant performance degradation, especially under high compression rates. We argue that while attention-based pruning inherently holds the potential to identify the most relevant visual tokens, its effectiveness in shallow decoder layers is limited by factors such as positional encoding bias and insufficient information interaction. In this paper, we propose an improved attention-based pruning framework, termed ShaRP, that integrates segment-aware causal masking, positional debiasing, and token deduplication for enhanced token selection. It enables effective pruning at shallow layers while maintaining stable performance under high compression rates without retraining. Extensive experiments demonstrate that ShaRP achieves competitive performance across multiple video understanding benchmarks, establishing a new paradigm for accelerating VLLM inference.

Wenjie Li, Jinglei Shi, Jin Han et al.

Clean images are crucial for visual tasks such as small object detection, especially at high resolutions. However, real-world images are often degraded by adverse weather, and weather restoration methods may sacrifice high-frequency details critical for analyzing small objects. A natural solution is to apply super-resolution (SR) after weather removal to recover both clarity and fine structures. However, simply cascading restoration and SR struggle to bridge their inherent conflict: removal aims to remove high-frequency weather-induced noise, while SR aims to hallucinate high-frequency textures from existing details, leading to inconsistent restoration contents. In this paper, we take deraining as a case study and propose DHGM, a Diffusion-based High-frequency Guided Model for generating clean and high-resolution images. DHGM integrates pre-trained diffusion priors with high-pass filters to simultaneously remove rain artifacts and enhance structural details. Extensive experiments demonstrate that DHGM achieves superior performance over existing methods, with lower costs.

Lishen Qu, Zhihao Liu, Jinshan Pan et al.

Lens flare occurs when shooting towards strong light sources, significantly degrading the visual quality of images. Due to the difficulty in capturing flare-corrupted and flare-free image pairs in the real world, existing datasets are typically synthesized in 2D by overlaying artificial flare templates onto background images. However, the lack of flare diversity in templates and the neglect of physical principles in the synthesis process hinder models trained on these datasets from generalizing well to real-world scenarios. To address these challenges, we propose a new physics-informed method for flare data generation, which consists of three stages: parameterized template creation, the laws of illumination-aware 2D synthesis, and physical engine-based 3D rendering, which finally gives us a mixed flare dataset that incorporates both 2D and 3D perspectives, namely FlareX. This dataset offers 9,500 2D templates derived from 95 flare patterns and 3,000 flare image pairs rendered from 60 3D scenes. Furthermore, we design a masking approach to obtain real-world flare-free images from their corrupted counterparts to measure the performance of the model on real-world images. Extensive experiments demonstrate the effectiveness of our method and dataset.

Duosheng Chen, Shihao Zhou, Jinshan Pan et al.

Exploring motion information is important for the motion deblurring task. Recent the window-based transformer approaches have achieved decent performance in image deblurring. Note that the motion causing blurry results is usually composed of translation and rotation movements and the window-shift operation in the Cartesian coordinate system by the window-based transformer approaches only directly explores translation motion in orthogonal directions. Thus, these methods have the limitation of modeling the rotation part. To alleviate this problem, we introduce the polar coordinate-based transformer, which has the angles and distance to explore rotation motion and translation information together. In this paper, we propose a Radial Strip Transformer (RST), which is a transformer-based architecture that restores the blur images in a polar coordinate system instead of a Cartesian one. RST contains a dynamic radial embedding module (DRE) to extract the shallow feature by a radial deformable convolution. We design a polar mask layer to generate the offsets for the deformable convolution, which can reshape the convolution kernel along the radius to better capture the rotation motion information. Furthermore, we proposed a radial strip attention solver (RSAS) as deep feature extraction, where the relationship of windows is organized by azimuth and radius. This attention module contains radial strip windows to reweight image features in the polar coordinate, which preserves more useful information in rotation and translation motion together for better recovering the sharp images. Experimental results on six synthesis and real-world datasets prove that our method performs favorably against other SOTA methods for the image deblurring task.

Zhaolin Xiao, Jinglei Shi, Xiaoran Jiang et al.

Axial light field resolution refers to the ability to distinguish features at different depths by refocusing. The axial refocusing precision corresponds to the minimum distance in the axial direction between two distinguishable refocusing planes. High refocusing precision can be essential for some light field applications like microscopy. In this paper, we propose a learning-based method to extrapolate novel views from axial volumes of sheared epipolar plane images (EPIs). As extended numerical aperture (NA) in classical imaging, the extrapolated light field gives re-focused images with a shallower depth of field (DOF), leading to more accurate refocusing results. Most importantly, the proposed approach does not need accurate depth estimation. Experimental results with both synthetic and real light fields show that the method not only works well for light fields with small baselines as those captured by plenoptic cameras (especially for the plenoptic 1.0 cameras), but also applies to light fields with larger baselines.