With the rapid development of virtual reality, omnidirectional images (ODIs) have attracted much attention from both the industrial community and academia. However, due to storage and transmission limitations, the resolution of current ODIs is often insufficient to provide an immersive virtual reality experience. Previous approaches address this issue using conventional 2D super-resolution techniques on equirectangular projection without exploiting the unique geometric properties of ODIs. In particular, the equirectangular projection (ERP) provides a complete field-of-view but introduces significant distortion, while the cubemap projection (CMP) can reduce distortion yet has a limited field-of-view. In this paper, we present a novel Bi-Projection Omnidirectional Image Super-Resolution (BPOSR) network to take advantage of the geometric properties of the above two projections. Then, we design two tailored attention methods for these projections: Horizontal Striped Transformer Block (HSTB) for ERP and Perspective Shift Transformer Block (PSTB) for CMP. Furthermore, we propose a fusion module to make these projections complement each other. Extensive experiments demonstrate that BPOSR achieves state-of-the-art performance on omnidirectional image super-resolution. The code is available at https://github.com/W-JG/BPOSR.
论文检索
输入标题、作者或关键词，从 2,866 篇学术成果中精准定位
Zero-shot object detection (ZSD) aims to localize and classify unseen objects without access to their training annotations. As a prevailing solution to ZSD, generation-based methods synthesize unseen visual features by taking seen features as reference and class semantic embeddings as guideline. Although previous works continuously improve the synthesis quality, they fail to consider the scale-varying nature of unseen objects. The generation process is preformed over a single scale of object features and thus lacks scale-diversity among synthesized features. In this paper, we reveal the scale-varying challenge in ZSD and propose a Scale-Aware Unseen Imagineer (SAUI) to lead the way of a novel scale-aware ZSD paradigm. To obtain multi-scale features of seen-class objects, we design a specialized coarse-to-fine extractor to capture features through multiple scale-views. To generate unseen features scale by scale, we innovate a Series-GAN synthesizer along with three scale-aware contrastive components to imagine separable, diverse and robust scale-wise unseen features. Extensive experiments on PASCAL VOC, COCO and DIOR datasets demonstrate SAUI's better performance in different scenarios, especially for scale-varying and small objects. Notably, SAUI achieves the new state-of-the art performance on COCO and DIOR.
RGBT tracking has been widely used in various fields such as robotics, surveillance processing, and autonomous driving. Existing RGBT trackers fully explore the spatial information between the template and the search region and locate the target based on the appearance matching results. However, these RGBT trackers have very limited exploitation of temporal information, either ignoring temporal information or exploiting it through online sampling and training. The former struggles to cope with the object state changes, while the latter neglects the correlation between spatial and temporal information. To alleviate these limitations, we propose a novel Temporal Adaptive RGBT Tracking framework, named as TATrack. TATrack has a spatio-temporal two-stream structure and captures temporal information by an online updated template, where the two-stream structure refers to the multi-modal feature extraction and cross-modal interaction for the initial template and the online update template respectively. TATrack contributes to comprehensively exploit spatio-temporal information and multi-modal information for target localization. In addition, we design a spatio-temporal interaction (STI) mechanism that bridges two branches and enables cross-modal interaction to span longer time scales. Extensive experiments on three popular RGBT tracking benchmarks show that our method achieves state-of-the-art performance, while running at real-time speed.
Image animation aims to bring static images to life according to driving videos and create engaging visual content that can be used for various purposes such as animation, entertainment, and education. Recent unsupervised methods utilize affine and thin-plate spline transformations based on keypoints to transfer the motion in driving frames to the source image. However, limited by the expressive power of the transformations used, these methods always produce poor results when the gap between the motion in the driving frame and the source image is large. To address this issue, we propose to model motion from the source image to the driving frame in highly-expressive diffeomorphism spaces. Firstly, we introduce Continuous Piecewise-Affine based (CPAB) transformation to model the motion and present a well-designed inference algorithm to generate CPAB transformation from control keypoints. Secondly, we propose a SAM-guided keypoint semantic loss to further constrain the keypoint extraction process and improve the semantic consistency between the corresponding keypoints on the source and driving images. Finally, we design a structure alignment loss to align the structure-related features extracted from driving and generated images, thus helping the generator generate results that are more consistent with the driving action. Extensive experiments on four datasets demonstrate the effectiveness of our method against state-of-the-art competitors quantitatively and qualitatively. Code will be publicly available at: https://github.com/DevilPG/AAAI2024-CPABMM.
Existing deep pan-sharpening methods lack the learning of complementary information between PAN and MS modalities in the intermediate layers, and exhibit low interpretability due to their black-box designs. To this end, an interpretable deep unfolded network with intrinsic supervision for pan-sharpening is proposed. Building upon the observation degradation process, it formulates the pan-sharpening task as a variational model minimization with spatial consistency prior and spectral projection prior. The former prior requires a joint component decomposition of PAN and MS images to extract intrinsic features. By being supervised in the intermediate layers, it can selectively provide high-frequency information for spatial enhancement. The latter prior constrains the intensity correlation between MS and PAN images derived from physical observations, so as to improve spectral fidelity. To further enhance the transparency of network design, we develop an iterative solution algorithm following the half-quadratic splitting to unfold the deep model. It rigorously adheres to the variational model, significantly enhancing the interpretability behind network design and efficiently alternating the optimization of the network. Extensive experiments demonstrate the advantages of our method compared to state-of-the-arts, showcasing its remarkable generalization capability to real-world scenes. Our code is publicly available at https://github.com/Baixuzx7/DISPNet.
We explore the generalization of the implicit representation in the physical simulation task. Traditional time-dependent partial differential equations (PDEs) solvers for physical simulation often adopt the grid or mesh for spatial discretization, which is memory-consuming for high resolution and lack of adaptivity. Many implicit representations like local extreme machine or Siren are proposed but they are still too compact to suffer from limited accuracy in handling local details and a long time of convergence. We contribute a neural simulation framework based on multi-resolution hash grid representation to introduce hierarchical consideration of global and local information, simultaneously. Furthermore, we propose two key strategies: 1) a numerical gradient method for computing high-order derivatives with boundary conditions; 2) a range analysis sample method for fast neural geometry boundary sampling with dynamic topologies. Our method shows much higher accuracy and strong flexibility for various simulation problems: e.g., large elastic deformations, complex fluid dynamics, and multi-scale phenomena which remain challenging for existing neural physical solvers.
In recent advancements concerning Domain Adaptive Object Detection (DAOD), unsupervised domain adaptation techniques have proven instrumental. These methods enable enhanced detection capabilities within unlabeled target domains by mitigating distribution differences between source and target domains. A subset of DAOD methods employs disentangled learning to segregate Domain-Specific Representations (DSR) and Domain-Invariant Representations (DIR), with ultimate predictions relying on the latter. Current practices in disentanglement, however, often lead to DIR containing residual domain-specific information. To address this, we introduce the Multi-level Disentanglement Module (MDM) that progressively disentangles DIR, enhancing comprehensive disentanglement. Additionally, our proposed Cyclic Disentanglement Module (CDM) facilitates DSR separation. To refine the process further, we employ the Categorical Features Disentanglement Module (CFDM) to isolate DIR and DSR, coupled with category alignment across scales for improved source-target domain alignment. Given its practical suitability, our model is constructed upon the foundational framework of the Single Shot MultiBox Detector (SSD), which is a one-stage object detection approach. Experimental validation highlights the effectiveness of our method, demonstrating its state-of-the-art performance across three benchmark datasets.
ViLT-CLIP: Video and Language Tuning CLIP with Multimodal Prompt Learning and Scenario-Guided Optimization
PDF ↗Pre-trained vision-language(V-L) models such as CLIP have demonstrated impressive Zero-Shot performance in many downstream tasks. Since adopting contrastive video-text pairs methods like CLIP to video tasks is limited by its high cost and scale, recent approaches focus on efficiently transferring the image-based CLIP to the video domain. A major finding is that fine-tuning the pre-trained model to achieve strong fully supervised performance leads to low zero shot, few shot, and base to novel generalization. Instead, freezing the backbone network to maintain generalization ability weakens fully supervised performance. Otherwise, no single prompt tuning branch consistently performs optimally. In this work, we proposed a multimodal prompt learning scheme that balances supervised and generalized performance. Our prompting approach contains three sections: 1) Independent prompt on both the vision and text branches to learn the language and visual contexts. 2) Inter-modal prompt mapping to ensure mutual synergy. 3) Reducing the discrepancy between the hand-crafted prompt (a video of a person doing [CLS]) and the learnable prompt, to alleviate the forgetting about essential video scenarios. Extensive validation of fully supervised, zero-shot, few-shot, base-to-novel generalization settings for video recognition indicates that the proposed approach achieves competitive performance with less commute cost.
B-spine: Learning B-spline Curve Representation for Robust and Interpretable Spinal Curvature Estimation
PDF ↗Spinal curvature estimation is important to the diagnosis and treatment of the scoliosis. Existing methods face several issues such as the need of expensive annotations on the vertebral landmarks and being sensitive to the image quality. It is challenging to achieve robust estimation and obtain interpretable results, especially for low-quality images which are blurry and hazy. In this paper, we propose B-Spine, a novel deep learning pipeline to learn B-spline curve representation of the spine and estimate the Cobb angles for spinal curvature estimation from low-quality X-ray images. Given a low quality input, a novel SegRefine network which employs the unpaired image-to-image translation is proposed to generate a high quality spine mask from the initial segmentation result. Next, a novel mask-based B-spline prediction model is proposed to predict the B-spline curve for the spine centerline. Finally, the Cobb angles are estimated by a hybrid approach which combines the curve slope analysis and a curve based regression model. We conduct quantitative and qualitative comparisons with the representative and SOTA learning-based methods on the public AASCE2019 dataset and our new proposed JLU-CJUH dataset which contains more challenging low-quality images. The superior performance on both datasets shows our method can achieve both robustness and interpretability for spinal curvature estimation.
Despite recent promising performances across a range of vision tasks, vision Transformers still have an issue of high computational costs. Recently, vision prompt learning has provided an economical solution to this problem without fine-tuning the whole large-scale model. However, the efficiency and effectiveness of existing models are still far from satisfactory due to the parameter cost of extensive prompt blocks and tricky prompt framework designs. In this paper, we propose a light-weight prompt framework named impLicit vIsion prOmpt tuNing (LION), which is motivated by deep implicit models with stable low memory costs for various complex tasks. In particular, we merely insect two equilibrium implicit layers in two ends of the pre-trained backbone with parameters frozen. Moreover, according to the lottery hypothesis, we further prune the parameters to relieve the computation burden in implicit layers. Various experiments have validated that our LION obtains promising performances on a wide range of datasets. Most importantly, LION reduces up to 11.5 % of training parameter numbers while obtaining higher performance than the state-of-the-art VPT, especially under challenging scenes. Furthermore, we find that our proposed LION has an excellent generalization performance, making it an easy way to boost transfer learning in the future.
In recent years, with the popularity of social media applications, massive digital images are available online, which brings great convenience to image recreation. However, the use of unauthorized image materials in multi-source composite images is still inadequately regulated, which may cause significant loss and discouragement to the copyright owners of the source image materials. Ideally, deep watermarking techniques could provide a solution for protecting these copyrights based on their encoder-noise-decoder training strategy. Yet existing image watermarking schemes, which are mostly designed for single images, cannot well address the copyright protection requirements in this scenario, since the multi-source image composing process commonly includes distortions that are not well investigated in previous methods, e.g., the extreme downsizing. To meet such demands, we propose MuST, a multi-source tracing robust watermarking scheme, whose architecture includes a multi-source image detector and minimum external rectangle operation for multiple watermark resynchronization and extraction. Furthermore, we constructed an image material dataset covering common image categories and designed the simulation model of the multi-source image composing process as the noise layer. Experiments demonstrate the excellent performance of MuST in tracing sources of image materials from the composite images compared with SOTA watermarking methods, which could maintain the extraction accuracy above 98% to trace the sources of at least 3 different image materials while keeping the average PSNR of watermarked image materials higher than 42.51 dB. We released our code on https://github.com/MrCrims/MuST
Prompt tuning provides a low-cost way of adapting vision-language models (VLMs) for various downstream vision tasks without requiring updating the huge pre-trained parameters. Dispensing with the conventional manual crafting of prompts, the recent prompt tuning method of Context Optimization (CoOp) introduces adaptable vectors as text prompts. Nevertheless, several previous works point out that the CoOp-based approaches are easy to overfit to the base classes and hard to generalize to novel classes. In this paper, we reckon that the prompt tuning works well only in the base classes because of the limited capacity of the adaptable vectors. The scale of the pre-trained model is hundreds times the scale of the adaptable vector, thus the learned vector has a very limited ability to absorb the knowledge of novel classes. To minimize this excessive overfitting of textual knowledge on the base class, we view prompt tuning as learning to learn (LoL) and learn the prompt in the way of meta-learning, the training manner of dividing the base classes into many different subclasses could fully exert the limited capacity of prompt tuning and thus transfer it power to recognize the novel classes. To be specific, we initially perform fine-tuning on the base class based on the CoOp method for pre-trained CLIP. Subsequently, predicated on the fine-tuned CLIP model, we carry out further fine-tuning in an N-way K-shot manner from the perspective of meta-learning on the base classes. We finally apply the learned textual vector and VLM for unseen classes.Extensive experiments on benchmark datasets validate the efficacy of our meta-learning-informed prompt tuning, affirming its role as a robust optimization strategy for VLMs.
Video Motion Magnification (VMM) aims to break the resolution limit of human visual perception capability and reveal the imperceptible minor motion that contains valuable information in the macroscopic domain. However, challenges arise in this task due to photon noise inevitably introduced by photographic devices and spatial inconsistency in amplification, leading to flickering artifacts in static fields and motion blur and distortion in dynamic fields in the video. Existing methods focus on explicit motion modeling without emphasizing prioritized denoising during the motion magnification process. This paper proposes a novel dynamic filtering strategy to achieve static-dynamic field adaptive denoising. Specifically, based on Eulerian theory, we separate texture and shape to extract motion representation through inter-frame shape differences, expecting to leverage these subdivided features to solve this task finely. Then, we introduce a novel dynamic filter that eliminates noise cues and preserves critical features in the motion magnification and amplification generation phases. Overall, our unified framework, EulerMormer, is a pioneering effort to first equip with Transformer in learning-based VMM. The core of the dynamic filter lies in a global dynamic sparse cross-covariance attention mechanism that explicitly removes noise while preserving vital information, coupled with a multi-scale dual-path gating mechanism that selectively regulates the dependence on different frequency features to reduce spatial attenuation and complement motion boundaries. We demonstrate extensive experiments that EulerMormer achieves more robust video motion magnification from the Eulerian perspective, significantly outperforming state-of-the-art methods. The source code is available at https://github.com/VUT-HFUT/EulerMormer.
This paper proposes UHDformer, a general Transformer for Ultra-High-Definition (UHD) image restoration. UHDformer contains two learning spaces: (a) learning in high-resolution space and (b) learning in low-resolution space. The former learns multi-level high-resolution features and fuses low-high features and reconstructs the residual images, while the latter explores more representative features learning from the high-resolution ones to facilitate better restoration. To better improve feature representation in low-resolution space, we propose to build feature transformation from the high-resolution space to the low-resolution one. To that end, we propose two new modules: Dual-path Correlation Matching Transformation module (DualCMT) and Adaptive Channel Modulator (ACM). The DualCMT selects top C/r (r is greater or equal to 1 which controls the squeezing level) correlation channels from the max-pooling/mean-pooling high-resolution features to replace low-resolution ones in Transformers, which can effectively squeeze useless content to improve the feature representation in low-resolution space to facilitate better recovery. The ACM is exploited to adaptively modulate multi-level high-resolution features, enabling to provide more useful features to low-resolution space for better learning. Experimental results show that our UHDformer reduces about ninety-seven percent model sizes compared with most state-of-the-art methods while significantly improving performance under different training sets on 3 UHD image restoration tasks, including low-light image enhancement, image dehazing, and image deblurring. The source codes will be made available at https://github.com/supersupercong/UHDformer.
This work presents an effective depth-consistency Self-Prompt Transformer, terms as SelfPromer, for image dehazing. It is motivated by an observation that the estimated depths of an image with haze residuals and its clear counterpart vary. Enforcing the depth consistency of dehazed images with clear ones, therefore, is essential for dehazing. For this purpose, we develop a prompt based on the features of depth differences between the hazy input images and corresponding clear counterparts that can guide dehazing models for better restoration. Specifically, we first apply deep features extracted from the input images to the depth difference features for generating the prompt that contains the haze residual information in the input. Then we propose a prompt embedding module that is designed to perceive the haze residuals, by linearly adding the prompt to the deep features. Further, we develop an effective prompt attention module to pay more attention to haze residuals for better removal. By incorporating the prompt, prompt embedding, and prompt attention into an encoder-decoder network based on VQGAN, we can achieve better perception quality. As the depths of clear images are not available at inference, and the dehazed images with one-time feed-forward execution may still contain a portion of haze residuals, we propose a new continuous self-prompt inference that can iteratively correct the dehazing model towards better haze-free image generation. Extensive experiments show that our SelfPromer performs favorably against the state-of-the-art approaches on both synthetic and real-world datasets in terms of perception metrics including NIQE, PI, and PIQE. The source codes will be made available at https://github.com/supersupercong/SelfPromer.
Low-Light Face Super-resolution via Illumination, Structure, and Texture Associated Representation
PDF ↗Human face captured at night or in dimly lit environments has become a common practice, accompanied by complex low-light and low-resolution degradations. However, the existing face super-resolution (FSR) technologies and derived cascaded schemes are inadequate to recover credible textures. In this paper, we propose a novel approach that decomposes the restoration task into face structural fidelity maintaining and texture consistency learning. The former aims to enhance the quality of face images while improving the structural fidelity, while the latter focuses on eliminating perturbations and artifacts caused by low-light degradation and reconstruction. Based on this, we develop a novel low-light low-resolution face super-resolution framework. Our method consists of two steps: an illumination correction face super-resolution network (IC-FSRNet) for lighting the face and recovering the structural information, and a detail enhancement model (DENet) for improving facial details, thus making them more visually appealing and easier to analyze. As the relighted regions could provide complementary information to boost face super-resolution and vice versa, we introduce the mutual learning to harness the informative components from relighted regions and reconstruction, and achieve the iterative refinement. In addition, DENet equipped with diffusion probabilistic model is built to further improve face image visual quality. Experiments demonstrate that the proposed joint optimization framework achieves significant improvements in reconstruction quality and perceptual quality over existing two-stage sequential solutions. Code is available at https://github.com/wcy-cs/IC-FSRDENet.
The integration of visual encoders and large language models (LLMs) has driven recent progress in multimodal large language models (MLLMs). However, the scarcity of high-quality instruction-tuning data for vision-language tasks remains a challenge. The current leading paradigm, such as LLaVA, relies on language-only GPT-4 to generate data, which requires pre-annotated image captions and detection bounding boxes, suffering from understanding image details. A practical solution to this problem would be to utilize the available multimodal large language models to generate instruction data for vision-language tasks. However, it's worth noting that the currently accessible MLLMs are not as powerful as their LLM counterparts, as they tend to produce inadequate responses and generate false information. As a solution for addressing the current issue, this paper proposes the Visual Instruction Generation and Correction (VIGC) framework that enables multimodal large language models to generate instruction-tuning data and progressively enhance its quality on-the-fly. Specifically, Visual Instruction Generation (VIG) guides the vision-language model to generate diverse instruction-tuning data. To ensure generation quality, Visual Instruction Correction (VIC) adopts an iterative update mechanism to correct any inaccuracies in data produced by VIG, effectively reducing the risk of hallucination. Leveraging the diverse, high-quality data generated by VIGC, we finetune mainstream models and validate data quality based on various evaluations. Experimental results demonstrate that VIGC not only compensates for the shortcomings of language-only data generation methods, but also effectively enhances the benchmark performance. The models, datasets, and code are available at https://opendatalab.github.io/VIGC
Neural reconstruction and rendering strategies have demonstrated state-of-the-art performances due, in part, to their ability to preserve high level shape details. Existing approaches, however, either represent objects as implicit surface functions or neural volumes and still struggle to recover shapes with heterogeneous materials, in particular human skin, hair or clothes. To this aim, we present a new hybrid implicit surface representation to model human shapes. This representation is composed of two surface layers that represent opaque and translucent regions on the clothed human body. We segment different regions automatically using visual cues and learn to reconstruct two signed distance functions (SDFs). We perform surface-based rendering on opaque regions (e.g., body, face, clothes) to preserve high-fidelity surface normals and volume rendering on translucent regions (e.g., hair). Experiments demonstrate that our approach obtains state-of-the-art results on 3D human reconstructions, and also shows competitive performances on other objects.
Attribution algorithms are frequently employed to explain the decisions of neural network models. Integrated Gradients (IG) is an influential attribution method due to its strong axiomatic foundation. The algorithm is based on integrating the gradients along a path from a reference image to the input image. Unfortunately, it can be observed that gradients computed from regions where the output logit changes minimally along the path provide poor explanations for the model decision, which is called the saturation effect problem. In this paper, we propose an attribution algorithm called integrated decision gradients (IDG). The algorithm focuses on integrating gradients from the region of the path where the model makes its decision, i.e., the portion of the path where the output logit rapidly transitions from zero to its final value. This is practically realized by scaling each gradient by the derivative of the output logit with respect to the path. The algorithm thereby provides a principled solution to the saturation problem. Additionally, we minimize the errors within the Riemann sum approximation of the path integral by utilizing non-uniform subdivisions determined by adaptive sampling. In the evaluation on ImageNet, it is demonstrated that IDG outperforms IG, Left-IG, Guided IG, and adversarial gradient integration both qualitatively and quantitatively using standard insertion and deletion metrics across three common models.
The success of data mixing augmentations in image classification tasks has been well-received. However, these techniques cannot be readily applied to object detection due to challenges such as spatial misalignment, foreground/background distinction, and plurality of instances. To tackle these issues, we first introduce a novel conceptual framework called Supervision Interpolation (SI), which offers a fresh perspective on interpolation-based augmentations by relaxing and generalizing Mixup. Based on SI, we propose LossMix, a simple yet versatile and effective regularization that enhances the performance and robustness of object detectors and more. Our key insight is that we can effectively regularize the training on mixed data by interpolating their loss errors instead of ground truth labels. Empirical results on the PASCAL VOC and MS COCO datasets demonstrate that LossMix can consistently outperform state-of-the-art methods widely adopted for detection. Furthermore, by jointly leveraging LossMix with unsupervised domain adaptation, we successfully improve existing approaches and set a new state of the art for cross-domain object detection.