Detecting mirror regions in RGB videos is essential for scene understanding in applications such as scene reconstruction and robotic navigation. Existing video mirror detectors typically rely on cues like inside-outside mirror correspondences and 2D motion inconsistencies. However, these methods often yield noisy or incomplete predictions when confronted with complex real-world video scenes, especially in areas with occlusion or limited visual features and motions. We observe that human perceive and navigate 3D occluded environments with remarkable ease, owing to Motion-in-Depth (MiD) perception. MiD integrates information from visual appearance (image colors and textures), the way objects move around us in 3D space (3D motions), and their relative distance from us (depth) to determine if something is approaching or receding and to support navigation. Motivated by this neuroscience mechanism, we introduce MiD-VMD, the first approach to explicitly model MiD for video mirror detection. MiD-VMD jointly utilizes contrastive 3D motion, depth, and image features through two novel modules based on a combinational QKV transformer architecture. The Motion-in-Depth Attention Learning (MiD-AL) module captures complementary relationships across these modalities with combinatorial attention and enforces a compact encoding to represent global 3D transformations, resulting in more accurate mirror detection and reduced motion artifacts. The Motion-in-Depth Boundary Detection (MiD-BD) module further sharpens mirror boundaries by leveraging cross-modal attention on 3D motion and depth features. Extensive experiments show that MiD-VMD outperforms current SOTAs.

Personalized search ranking systems are critical for driving engagement and revenue in modern e-commerce platforms. Existing methods primarily model users' broad interests from historical behaviors but often fail to explicitly align these with real-time intent expressed in user queries. In this paper, we propose DiffusionGS, a scalable generative framework that treats user queries as explicit intent anchors to extract user interests from long-term, noisy behavior histories. Specifically, we formulate interest extraction as a conditional denoising task, where the user's query guides a conditional diffusion process to produce a robust, user intent-aware representation from their behavioral sequence. A User-aware Denoising Layer (UDL) further refines attention distribution using user-specific profiles. By reframing queries as intent priors and leveraging diffusion-based denoising, our method provides a powerful mechanism for capturing dynamic user interest shifts. Extensive offline and online experiments demonstrate the superiority of DiffusionGS over state-of-the-art methods. © 2026 Copyright held by the owner/author(s).

Salient Object Ranking (SOR) aims to study human attention shifts across different objects in the scene. It is a challenging task, as it requires comprehension of the relations among the salient objects in the scene. However, existing works often overlook such relations or model them implicitly. In this work, we observe that when Large Vision-Language Models (LVLMs) describe a scene, they usually focus on the most salient object first, and then discuss the relations as they move on to the next (less salient) one. Based on this observation, we propose a novel Language-Guided Salient Object Ranking approach (named LG-SOR), which utilizes the internal knowledge within the LVLM-generated language descriptions, i.e., semantic relation cues and the implicit entity order cues, to facilitate saliency ranking. Specifically, we first propose a novel Text-Guided Visual Modulation (TGVM) module to incorporate semantic information in the description for saliency ranking. TGVM controls the flow of linguistic information to the visual features, suppresses noisy background image features, and enables the propagation of useful textual features. We then propose a novel Text-Aware Visual Reasoning (TAVR) module to enhance model reasoning in object ranking, by explicitly learning a multimodal graph based on the entity and relation cues derived from the description. Extensive experiments demonstrate superior performances of our model on two SOR benchmarks.

Advances in medical imaging technologies have enabled the collection of longitudinal images, which involve repeated scanning of the same patients over time, to monitor disease progression. However, predictive modeling of such data remains challenging due to high dimensionality, irregular sampling, and data sparsity. To address these issues, we propose ImageFlowNet, a novel model designed to forecast disease trajectories from initial images while preserving spatial details. ImageFlowNet first learns multiscale joint representation spaces across patients and time points, then optimizes deterministic or stochastic flow fields within these spaces using a position-parameterized neural ODE/SDE framework. The model leverages a UNet architecture to create robust multiscale representations and mitigates data scarcity by combining knowledge from all patients. We provide theoretical insights that support our formulation of ODEs, and motivate our regularizations involving high-level visual features, latent space organization, and trajectory smoothness. We validate ImageFlowNet on three longitudinal medical image datasets depicting progression in geographic atrophy, multiple sclerosis, and glioblastoma, demonstrating its ability to effectively forecast disease progression and outperform existing methods. Our contributions include the development of ImageFlowNet, its theoretical underpinnings, and empirical validation on real-world datasets.

This paper presents SeHDR, a novel high dynamic range 3D Gaussian Splatting (HDR-3DGS) approach for generating HDR novel views given multi-view LDR images. Unlike existing methods that typically require the multi-view LDR input images to be captured from different exposures, which are tedious to capture and more likely to suffer from errors (e.g., object motion blurs and calibration/alignment inaccuracies), our approach learns the HDR scene representation from multi-view LDR images of a single exposure. Our key insight to this ill-posed problem is that by first estimating Bracketed 3D Gaussians (i.e., with different exposures) from single-exposure multi-view LDR images, we may then be able to merge these bracketed 3D Gaussians into an HDR scene representation. Specifically, SeHDR first learns base 3D Gaussians from single-exposure LDR inputs, where the spherical harmonics parameterize colors in a linear color space. We then estimate multiple 3D Gaussians with identical geometry but varying linear colors conditioned on exposure manipulations. Finally, we propose the Differentiable Neural Exposure Fusion (NeEF) to integrate the base and estimated 3D Gaussians into HDR Gaussians for novel view rendering. Extensive experiments demonstrate that SeHDR outperforms existing methods as well as carefully designed baselines.

Creating 3D assets that follow the texture and geometry style of existing ones is often desirable or even inevitable in practical applications like video gaming and virtual reality.While impressive progress has been made in generating 3D objects from text or images, creating style-controllable 3D assets remains a complex and challenging problem. In this work, we propose StyleSculptor, a novel training-free approach for generating style-guided 3D assets from a content image and one or more style images.Unlike previous works, StyleSculptor achieves style-guided 3D generation in a zero-shot manner, enabling fine-grained 3D style control that captures the texture, geometry, or both styles of user-provided style images. At the core of StyleSculptor is a novel Style Disentangled Attention (SD-Attn) module, which establishes a dynamic interaction between the input content image and style image for style-guided 3D asset generation via a cross-3D attention mechanism, enabling stable feature fusion and effective style-guided generation.To alleviate semantic content leakage, we also introduce a style-disentangled feature selection strategy within the SD-Attn module, which leverages the variance of 3D feature patches to disentangle style- and content-significant channels, allowing selective feature injection within the attention framework. With SD-Attn, the network can dynamically compute texture-, geometry-, or both-guided features to steer the 3D generation process. Built upon this, we further propose the Style Guided Control (SGC) mechanism, which enables exclusive geometry- or texture-only stylization, as well as adjustable style intensity control. StyleSculptor does not require prior training and enables instant adaptation to any reference models while maintaining strict user-specified style consistency. Extensive experiments demonstrate that StyleSculptor outperforms existing baseline methods in producing high-fidelity 3D assets. Code will be available at the project page.

Ghosting effects typically appear on glass surfaces, as each piece of glass has two contact surfaces causing two slightly offset layers of reflections. In this paper, we propose to take advantage of this intrinsic property of glass surfaces and apply it to glass surface detection, with two main technical novelties. First, we formulate a ghosting image formation model to describe the intensity and spatial relations among the main reflections and the background transmission within the glass region. Based on this model, we construct a new Glass Surface Ghosting Dataset (GSGD) to facilitate glass surface detection, with glass images and corresponding ghosting masks and glass surface masks. Second, we propose a novel method, called GhostingNet, for glass surface detection. Our method consists of a Ghosting Effects Detection (GED) module and a Glass Surface Detection (GSD) module. The key component of our GED module is a novel Double Reflection Estimation (DRE) block that models the spatial offsets of reflection layers for ghosting effect detection. The detected ghosting effects are then used to guide the GSD module for glass surface detection. Extensive experiments demonstrate that our method outperforms the state-of-the-art methods. We will release our code and dataset.

Online free-view navigation in volumetric videos requires high-quality rendering and real-time streaming in order to provide immersive user experiences. However, existing methods ( e.g. , dynamic NeRF and 3DGS) may not handle dynamic scenes with complex motions, and their models may not be streamable due to storage and bandwidth constraints. In this paper, we propose a novel 4D Gaussian Video (4DGV) approach that enables the creation and streaming of photorealistic, volumetric videos for dynamic scenes over the Internet. The core of our 4DGV is a novel streamable group of Gaussians (GOG) representation based on motion layering. Each GOG consists of static and dynamic points obtained via lifting 2D segmentation into 3D in motion layering, where the deformation of each dynamic point is represented as the temporal offset of its attributes. We also adaptively convert static points back to dynamic points to handle the appearance change, (e.g. , moving shadows and reflections), of static objects through optimization. To support real-time streaming of 4DGVs, we show that by applying quantization on Gaussian attributes and H.265 encoding on deformation offsets, our GOG representation can be significantly compressed (to around 6% of the original model size) without sacrificing the accuracy (PSNR loss less than 0.01dB). Extensive experiments on standard benchmarks demonstrate that our method outperforms state-of-the-art volumetric video approaches, with superior rendering quality and minimum storage overheads.

Multi-domain image inpainting utilizes complementary contextual information from auxiliary domain images to restore corrupted regions. While existing methods reconstruct auxiliary images to provide additional guidance, they face fundamental limitations: recovered pixels with complex patterns often lack representative details, while oversimplified patterns offer insufficient contextual information. To address these challenges, we propose HRC-Net, a novel framework incorporating three generative sub-networks for the comprehensive image inpainting task. Our architecture consists of: (1) A Hypothesis Sub-network that enables robust samplings of pixel-wise hypotheses from multi-domain inputs; (2) A Representative Sub-network that learns to score hypothesis quality based on contextual relevance; and (3) a Collaboration Sub-network that optimizes adaptive fusion kernels to integrate the most pertinent details. Together, these components model the joint distribution of representative scores and convolutional kernels, fostering a precise interaction between auxiliary hypotheses and target image corruption to meticulously repair the target image. Extensive evaluations across multiple benchmark datasets demonstrate HRC-Net's superior performance, significantly outperforming state-of-the-art methods in both quantitative metrics and visual quality.

Mirror detection is an active research topic in computer vision. However, all existing mirror detectors learn mirror representations from large-scale pixel-wise datasets, which are tedious and expensive to obtain. Although weakly-supervised learning has been widely explored in related topics, we note that popular weak supervision signals (e.g., bounding boxes, scribbles, points) still require some efforts from the user to locate the target objects, with a strong assumption that the images to annotate always contain the target objects. Such an assumption may result in the over-segmentation of mirrors. Our key idea of this work is that the existence of mirrors over a time period may serve as a weak supervision to train a mirror detector, for two reasons. First, if a network can predict the existence of mirrors, it can essentially locate the mirrors. Second, we observe that the reflected contents of a mirror tend to be similar to those in adjacent frames, but exhibit considerable contrast to regions in far-away frames (e.g., non-mirror frames). To this end, in this paper, we propose ZOOM, the first method to learn robust mirror representations from extremely-weak annotations of per-frame ZerO-One Mirror indicators in videos. The key insight of ZOOM is to model the similarity and contrast (between mirror and non-mirror regions) in temporal variations to locate and segment the mirrors. To this end, we propose a novel fusion strategy to leverage temporal consistency information for mirror localization, and a novel temporal similarity-contrast modeling module for mirror segmentation. We construct a new video mirror dataset for training and evaluation. Experimental results under new and standard metrics show that ZOOM performs favorably against existing fully-supervised mirror detection methods.

Removing shadows requires an understanding of both lighting conditions and object textures in a scene. Existing methods typically learn pixel-level color mappings between shadow and non-shadow images, in which the joint modeling of lighting and object textures is implicit and inadequate. We observe that in a shadow region, the degradation degree of object textures depends on the local illumination, while simply enhancing the local illumination cannot fully recover the attenuated textures. Based on this observation, we propose to condition the restoration of attenuated textures on the corrected local lighting in the shadow region. Specifically, We first design a shadow-aware decomposition network to estimate the illumination and reflectance layers of shadow regions explicitly. We then propose a novel bilateral correction network to recast the lighting of shadow regions in the illumination layer via a novel local lighting correction module, and to restore the textures conditioned on the corrected illumination layer via a novel illumination-guided texture restoration module. We further annotate pixel-wise shadow masks for the public SRD dataset, which originally contains only image pairs. Experiments on three benchmarks show that our method outperforms existing state-of-the-art shadow removal methods. Project page in: yuhaoliu7456.github.io/RRL-Net.

Recent research has shown significant interest in image-based glass surface detection (GSD). However, detecting glass surfaces in dynamic scenes remains largely unexplored due to the lack of a high-quality dataset and an effective video glass surface detection (VGSD) method. In this paper, we propose the first VGSD approach. Our key observation is that reflections frequently appear on glass surfaces, but they change dynamically as the camera moves. Based on this observation, we propose to offset the excessive dependence on a single uncertainty reflection via joint modeling of temporal and spatial reflection cues. To this end, we propose the VGSD-Net with two novel modules: a Location-aware Reflection Extraction (LRE) module and a Context-enhanced Reflection Integration (CRI) module, for the position-aware reflection feature extraction and the spatial-temporal reflection cues integration, respectively. We have also created the first large-scale video glass surface dataset (VGSD-D), consisting of 19,166 image frames with accurately-annotated glass masks extracted from 297 videos. Extensive experiments demonstrate that VGSD-Net outperforms state-of-the-art approaches adapted from related fields. Code and dataset will be available at https://github.com/fawnliu/VGSD.

Images captured under sub-optimal illumination conditions may contain both over- and under-exposures. Current approaches mainly focus on adjusting image brightness, which may exacerbate color tone distortion in under-exposed areas and fail to restore accurate colors in over-exposed regions. We observe that over- and over-exposed regions display opposite color tone distribution shifts, which may not be easily normalized in joint modeling as they usually do not have “normal-exposed” regions/pixels as reference. In this paper, we propose a novel method to enhance images with both over- and under-exposures by learning to estimate and correct such color shifts. Specifically, we first derive the color feature maps of the bright-ened and darkened versions of the input image via a UNet-based network, followed by a pseudo-normal feature generator to produce pseudo-normal color feature maps. We then propose a novel COlor Shift Estimation (COSE) module to estimate the color shifts between the derived brightened (or darkened) color feature maps and the pseudo-normal color feature maps. The COSE module corrects the estimated color shifts of the over- and under-exposed regions separately. We further propose a novel COlor MOdulation (COMO) module to modulate the separately corrected colors in the over- and under-exposed regions to produce the enhanced image. Comprehensive experiments show that our method outperforms existing approaches. Project web-page: https://github.com/yiyulics/CSEC.

The significant amount of manual efforts in annotating pixel-level labels has triggered the advancement of unsu-pervised saliency learning. However, without supervision signals, state-of-the-art methods can only infer region-level saliency. In this paper, we propose to explore the unsu-pervised salient instance detection (USID) problem, for a more fine-grained visual understanding. Our key obser-vation is that self-supervised transformer features may exhibit local similarities as well as different levels of contrast to other regions, which provide informative cues to iden-tify salient instances. Hence, we propose SCoCo, a novel network that models saliency coherence and contrast for USID. SCoCo includes two novel modules: (1) a global background adaptation (GBA) module with a scene-level contrastive loss to extract salient regions from the scene by searching the adaptive “saliency threshold” in the self-supervised transformer features, and (2) a locality-aware similarity (LAS) module with an instance-level contrastive loss to group salient regions into instances by modeling the in-region saliency coherence and cross-region saliency contrasts. Extensive experiments show that SCoCo outperforms state-of-the-art weakly-supervised SID methods and care-fully designed unsupervised baselines, and has comparable performances to fully-supervised SID methods.

Image-based mirror detection has recently undergone rapid research due to its significance in applications such as robotic navigation, semantic segmentation and scene re-construction. Recently, VMD-Net was proposed as the first video mirror detection technique, by modeling dual correspondences between the inside and outside of the mirror both spatially and temporally. However, this approach is not reliable, as correspondences can occur completely inside or outside of the mirrors. In addition, the proposed dataset VMD-D contains many small mirrors, limiting its applicability to real-world scenarios. To address these problems, we developed a more challenging dataset that includes mirrors of various shapes and sizes at different locations of the frames, providing a better reflection of real-world scenarios. Next, we observed that the motions between the inside and outside of the mirror are often in-consistent. For instance, when moving in front of a mirror, the motion inside the mirror is often much smaller than the motion outside due to increased depth perception. With these observations, we propose modeling inconsistent motion cues to detect mirrors, and a new network with two novel modules. The Motion Attention Module (MAM) ex-plicitly models inconsistent motions around mirrors via optical flow, and the Motion-Guided Edge Detection Module (MEDM) uses motions to guide mirror edge feature learning. Experimental results on our proposed dataset show that our method outperforms state-of-the-arts. The code and dataset are available at ht tps: // gi th ub. com/ AlexAnthonyWarren/MG-VMD.

Neural Radiance Fields (NeRFs) have shown remarkable performances in producing novel-view images from high-quality scene images. However, hand-held low-light photography challenges NeRFs as the captured images may simultaneously suffer from low visibility, noise, and camera shakes. While existing NeRF methods may handle either low light or motion, directly combining them or incorporating additional image-based enhancement methods does not work as these degradation factors are highly coupled. We observe that noise in low-light images is always sharp regardless of camera shakes, which implies an implicit order of these degradation factors within the image formation process. This inspires us to explore such an order to decouple and remove these degradation factors while training the NeRF. To this end, we propose in this paper a novel model, named LuSh-NeRF, which can reconstruct a clean and sharp NeRF from a group of hand-held low-light images. The key idea of LuSh-NeRF is to sequentially model noise and blur in the images via multi-view feature consistency and frequency information of NeRF, respectively. Specifically, LuSh-NeRF includes a novel Scene-Noise Decomposition (SND) module for decoupling the noise from the scene representation and a novel Camera Trajectory Prediction (CTP) module for the estimation of camera motions based on low-frequency scene information. To facilitate training and evaluations, we construct a new dataset containing both synthetic and real images. Experiments show that LuSh-NeRF outperforms existing approaches. Our code and dataset can be found here: https://github.com/quzefan/LuSh-NeRF.

High-quality real-time rendering using user-affordable capture rigs is an essential property of human performance capture systems for real-world applications. However, state-of-the-art performance capture methods may not yield satisfactory rendering results under a very sparse (e.g., four) capture setting. Specifically, neural radiance field (NeRF)-based methods and 3D Gaussian Splatting (3DGS)-based methods tend to produce local geometry errors for unseen performers, while occupancy field (PIFu)-based methods often produce unrealistic rendering results. In this paper, we propose a novel generalizable neural approach to reconstruct and render the performers from very sparse RGBD streams in high quality. The core of our method is a novel point-based generalizable human (PGH) representation conditioned on the pixel-aligned RGBD features. The PGH representation learns a surface implicit function for the regression of surface points and a Gaussian implicit function for parameterizing the radiance fields of the regressed surface points with 2D Gaussian surfels, and uses surfel splatting for fast rendering. We learn this hybrid human representation via two novel networks. First, we propose a novel point-regressing network (PRNet) with a depth-guided point cloud initialization (DPI) method to regress an accurate surface point cloud based on the denoised depth information. Second, we propose a novel neural blending-based surfel splatting network (SPNet) to render high-quality geometries and appearances in novel views based on the regressed surface points and high-resolution RGBD features of adjacent views. Our method produces free-view human performance videos of 1K resolution at 12 fps on average. Experiments on two benchmarks show that our method outperforms state-of-the-art human performance capture methods.

Harmonizing cut-and-paste images into perceptually realistic ones is challenging, as it requires a full understanding of the discrepancies between the background of the target image and the inserted object. Existing methods mainly adjust the appearances of the inserted object via pixel-level manipulations. They are not effective in correcting color discrepancy caused by different scene illuminations and the image formation processes. We note that image colors are essentially camera ISP projection of the scene radiance. If we can trace the image colors back to the radiance field, we may be able to model the scene illumination and harmonize the discrepancy better. In this paper, we propose a novel neural approach to harmonize the image colors in a camera-independent color space, in which color values are proportional to the scene radiance. To this end, we propose a novel image unprocessing module to estimate an intermediate high dynamic range version of the object to be inserted. We then propose a novel color harmonization module that harmonizes the colors of the inserted object by querying the estimated scene radiance and re-rendering the harmonized object in the output color space. Extensive experiments demonstrate that our method outperforms the state-of-the-art approaches.

Existing Referring Image Segmentation (RIS) methods typically require expensive pixel-level or box-level annotations for supervision. In this paper, we observe that the referring texts used in RIS already provide sufficient information to localize the target object. Hence, we propose a novel weakly-supervised RIS framework to formulate the target localization problem as a classification process to differentiate between positive and negative text expressions. While the referring text expressions for an image are used as positive expressions, the referring text expressions from other images can be used as negative expressions for this image. Our framework has three main novelties. First, we propose a bilateral prompt method to facilitate the classification process, by harmonizing the domain discrepancy between visual and linguistic features. Second, we propose a calibration method to reduce noisy background information and improve the correctness of the response maps for target object localization. Third, we propose a positive response map selection strategy to generate high-quality pseudo-labels from the enhanced response maps, for training a segmentation network for RIS inference. For evaluation, we propose a new metric to measure localization accuracy. Experiments on four benchmarks show that our framework achieves promising performances to existing fully-supervised RIS methods while outperforming state-of-the-art weakly-supervised methods adapted from related areas. Code is available at https://github.com/fawnliu/TRIS.

Shadow detection methods rely on multi-scale contrast, especially global contrast, information to locate shadows correctly. However, we observe that the camera image signal processor (ISP) tends to preserve more local contrast information by sacrificing global contrast information during the raw-to-sRGB conversion process. This often causes existing methods to fail in scenes with high global contrast but low local contrast in shadow regions. In this paper, we propose a novel method to detect shadows from raw images. Our key idea is that instead of performing a many-to-one mapping like the ISP process, we can learn a many-to-many mapping from the high dynamic range raw images to the sRGB images of different illumination, which is able to preserve multi-scale contrast for accurate shadow detection. To this end, we first construct a new shadow dataset with ~ 7000 raw images and shadow masks. We then propose a novel network, which includes a novel adaptive illumination mapping (AIM) module to project the input raw images into sRGB images of different intensity ranges and a shadow detection module to leverage the preserved multi-scale contrast information to detect shadows. To learn the shadow-aware adaptive illumination mapping process, we propose a novel feedback mechanism to guide the AIM during training. Experiments show that our method outperforms state- of-the-art shadow detectors. Code and dataset are available at https://github.com/jiayusun/SARA.

Neural Radiance Field (NeRF) is a promising approach for synthesizing novel views, given a set of images and the corresponding camera poses of a scene. However, images photographed from a low-light scene can hardly be used to train a NeRF model to produce high-quality results, due to their low pixel intensities, heavy noise, and color distortion. Combining existing low-light image enhancement methods with NeRF methods also does not work well due to the view inconsistency caused by the individual 2D enhancement process. In this paper, we propose a novel approach, called Low-Light NeRF (or LLNeRF), to enhance the scene representation and synthesize normal-light novel views directly from sRGB low-light images in an unsupervised manner. The core of our approach is a decomposition of radiance field learning, which allows us to enhance the illumination, reduce noise and correct the distorted colors jointly with the NeRF optimization process. Our method is able to produce novel view images with proper lighting and vivid colors and details, given a collection of camera-finished low dynamic range (8-bits/channel) images from a low-light scene. Experiments demonstrate that our method outperforms existing low-light enhancement methods and NeRF methods.

Mirror detection is challenging because the visual appearances of mirrors change depending on those of their surroundings. As existing mirror detection methods are mainly based on extracting contextual contrast and relational similarity between mirror and non-mirror regions, they may fail to identify a mirror region if these assumptions are violated. Inspired by a recent study of applying a CNN to help distinguish whether an image is flipped or not based on the visual chirality property, in this paper, we rethink this image-level visual chirality property and reformulate it as a learnable pixel level cue for mirror detection. Specifically, we first propose a novel flipping-convolution-flipping (FCF) transformation to model visual chirality as learnable commutative residual. We then propose a novel visual chirality embedding (VCE) module to exploit this commutative residual in multi-scale feature maps, to embed the visual chirality features into our mirror detection model. Besides, we also propose a visual chirality-guided edge detection (CED) module to integrate the visual chirality features with contextual features for detection refinement. Extensive experiments show that the proposed method outperforms state-of-the-art methods on three benchmark datasets.

Existing deep learning-based shadow removal methods still produce images with shadow remnants. These shadow remnants typically exist in homogeneous regions with low-intensity values, making them untraceable in the existing image-to-image mapping paradigm. We observe that shadows mainly degrade images at the image-structure level (in which humans perceive object shapes and continuous colors). Hence, in this paper, we propose to remove shadows at the image structure level. Based on this idea, we propose a novel structure-informed shadow removal network (StructNet) to leverage the image-structure information to address the shadow remnant problem. Specifically, StructNet first reconstructs the structure information of the input image without shadows and then uses the restored shadow-free structure prior to guiding the image-level shadow removal. StructNet contains two main novel modules: 1) a mask-guided shadow-free extraction (MSFE) module to extract image structural features in a non-shadow-to-shadow directional manner; and 2) a multi-scale feature & residual aggregation (MFRA) module to leverage the shadow-free structure information to regularize feature consistency. In addition, we also propose to extend StructNet to exploit multi-level structure information (MStructNet), to further boost the shadow removal performance with minimum computational overheads. Extensive experiments on three shadow removal benchmarks demonstrate that our method outperforms existing shadow removal methods, and our StructNet can be integrated with existing methods to improve them further.

Night-Time Scene Parsing (NTSP) is essential to many vision applications, especially for autonomous driving. Most of the existing methods are proposed for day-time scene parsing. They rely on modeling pixel intensity-based spatial contextual cues under even illumination. Hence, these methods do not perform well in night-time scenes as such spatial contextual cues are buried in the over-/under-exposed regions in night-time scenes. In this paper, we first conduct an image frequency-based statistical experiment to interpret the day-time and night-time scene discrepancies. We find that image frequency distributions differ significantly between day-time and night-time scenes, and understanding such frequency distributions is critical to NTSP problem. Based on this, we propose to exploit the image frequency distributions for night-time scene parsing. First, we propose a Learnable Frequency Encoder (LFE) to model the relationship between different frequency coefficients to measure all frequency components dynamically. Second, we propose a Spatial Frequency Fusion module (SFF) that fuses both spatial and frequency information to guide the extraction of spatial context features. Extensive experiments show that our method performs favorably against the state-of-the-art methods on the NightCity, NightCity+ and BDD100K-night datasets. In addition, we demonstrate that our method can be applied to existing day-time scene parsing methods and boost their performance on night-time scenes. The code is available at https://github.com/wangsen99/FDLNet.

Immersive user experiences in live VR/AR performances require a fast and accurate free-view rendering of the performers. Existing methods are mainly based on Pixel-aligned Implicit Functions (PIFu) or Neural Radiance Fields (NeRF). However, while PIFu-based methods usually fail to produce photorealistic view-dependent textures, NeRF-based methods typically lack local geometry accuracy and are computationally heavy ( e.g. , dense sampling of 3D points, additional fine-tuning, or pose estimation). In this work, we propose a novel generalizable method, named SAILOR, to create high-quality human free-view videos from very sparse RGBD live streams. To produce view-dependent textures while preserving locally accurate geometry, we integrate PIFu and NeRF such that they work synergistically by conditioning the PIFu on depth and then rendering view-dependent textures through NeRF. Specifically, we propose a novel network, named SRONet, for this hybrid representation. SRONet can handle unseen performers without fine-tuning. Besides, a neural blending-based ray interpolation approach, a tree-based voxel-denoising scheme, and a parallel computing pipeline are incorporated to reconstruct and render live free-view videos at 10 fps on average. To evaluate the rendering performance, we construct a real-captured RGBD benchmark from 40 performers. Experimental results show that SAILOR outperforms existing human reconstruction and performance capture methods.

Camouflaged object detection (COD) is important as it has various potential applications. Unlike salient object detection (SOD), which tries to identify visually salient objects, COD tries to detect objects that are visually very similar to the surrounding background. We observe that recent COD methods try to fuse features from different levels using some context aggregation strategies originally developed for SOD. Such an approach, however, may not be appropriate for COD as these existing context aggregation strategies are good at detecting distinctive objects while weakening the features from less discriminative objects. To address this problem, we propose in this article to exploit frequency learning to suppress the confusing high-frequency texture information, to help separate camouflaged objects from their surrounding background, and a frequency-based method, called FBNet, for camouflaged object detection. Specifically, we design a frequency-aware context aggregation (FACA) module to suppress high-frequency information and aggregate multi-scale features from a frequency perspective, an adaptive frequency attention (AFA) module to enhance the features of the learned important frequency components, and a gradient-weighted loss function to guide the proposed method to pay more attention to contour details. Experimental results show that our model outperforms relevant state-of-the-art methods.

Mirrors are everywhere in our daily lives. Existing computer vision systems do not consider mirrors, and hence may get confused by the reflected content inside a mirror, resulting in a severe performance degradation. However, separating the real content outside a mirror from the reflected content inside it is non-trivial. The key challenge is that mirrors typically reflect contents similar to their surroundings, making it very difficult to differentiate the two. In this article, we present a novel method to segment mirrors from a single RGB image. To the best of our knowledge, this is the first work to address the mirror segmentation problem with a computational approach. We make the following contributions: First, we propose a novel network, called MirrorNet+, for mirror segmentation, by modeling both contextual contrasts and semantic associations. Second, we construct the first large-scale mirror segmentation dataset, which consists of 4,018 pairs of images containing mirrors and their corresponding manually annotated mirror masks, covering a variety of daily-life scenes. Third, we conduct extensive experiments to evaluate the proposed method and show that it outperforms the related state-of-the-art detection and segmentation methods. Fourth, we further validate the effectiveness and generalization capability of the proposed semantic awareness contextual contrasted feature learning by applying MirrorNet+ to other vision tasks, i.e., salient object detection and shadow detection. Finally, we provide some applications of mirror segmentation and analyze possible future research directions. Project homepage: https://mhaiyang.github.io/TOMM2022-MirrorNet+/index.html .

Deep neural networks (DNNs) are widely used for computer vision tasks. However, it has been shown that deep models are vulnerable to adversarial attacks—that is, their performances drop when imperceptible perturbations are made to the original inputs, which may further degrade the following visual tasks or introduce new problems such as data and privacy security. Hence, metrics for evaluating the robustness of deep models against adversarial attacks are desired. However, previous metrics are mainly proposed for evaluating the adversarial robustness of shallow networks on the small-scale datasets. Although the Cross Lipschitz Extreme Value for nEtwork Robustness (CLEVER) metric has been proposed for large-scale datasets (e.g., the ImageNet dataset), it is computationally expensive and its performance relies on a tractable number of samples. In this article, we propose the Adversarial Converging Time Score (ACTS), an attack-dependent metric that quantifies the adversarial robustness of a DNN on a specific input. Our key observation is that local neighborhoods on a DNN’s output surface would have different shapes given different inputs. Hence, given different inputs, it requires different time for converging to an adversarial sample. Based on this geometry meaning, the ACTS measures the converging time as an adversarial robustness metric. We validate the effectiveness and generalization of the proposed ACTS metric against different adversarial attacks on the large-scale ImageNet dataset using state-of-the-art deep networks. Extensive experiments show that our ACTS metric is an efficient and effective adversarial metric over the previous CLEVER metric.

This paper presents a novel parametric curve-based method for lane detection in RGB images. Unlike state-of-the-art segmentation-based and point detection-based methods that typically require heuristics to either decode predictions or formulate a large sum of anchors, the curve-based methods can learn holistic lane representations naturally. To handle the optimization difficulties of existing poly-nomial curve methods, we propose to exploit the parametric Bézier curve due to its ease of computation, stability, and high freedom degrees of transformations. In addition, we propose the deformable convolution-based feature flip fusion, for exploiting the symmetry properties of lanes in driving scenes. The proposed method achieves a new state-of-the-art performance on the popular LLAMAS benchmark. It also achieves favorable accuracy on the TuSimple and CULane datasets, while retaining both low latency (>150 FPS) and small model size (<10M). Our method can serve as a new baseline, to shed the light on the parametric curves modeling for lane detection. Codes of our model and PytorchAutoDrive: a unified framework for self-driving perception, are available at: https://github.com/voldemortX/pytorch-auto-drive.

The huge burden of computation and memory are two obstacles in ultra-high resolution image segmentation. To tackle these issues, most of the previous works follow the global-local refinement pipeline, which pays more attention to the memory consumption but neglects the inference speed. In comparison to the pipeline that partitions the large image into small local regions, we focus on inferring the whole image directly. In this paper, we propose ISDNet, a novel ultra-high resolution segmentation framework that integrates the shallow and deep networks in a new manner, which significantly accelerates the inference speed while achieving accurate segmentation. To further exploit the relationship between the shallow and deep features, we propose a novel Relational-Aware feature Fusion module, which ensures high performance and robustness of our framework. Extensive experiments on Deepglobe, Inria Aerial, and Cityscapes datasets demonstrate our performance is consistently superior to state-of-the-arts. Specifically, it achieves 73.30 mIoU with a speed of 27.70 FPS on Deepglobe, which is more accurate and 172 × faster than the recent competitor. Code available at https://github.com/cedricgsh/ISDNet.

The saliency ranking task is recently proposed to study the visual behavior that humans would typically shift their attention over different objects of a scene based on their degrees of saliency. Existing approaches focus on learning either object-object or object-scene relations. Such a strategy follows the idea of object-based attention in Psychology, but it tends to favor objects with strong semantics (e.g., humans), resulting in unrealistic saliency ranking. We observe that spatial attention works concurrently with object-based attention in the human visual recognition system. During the recognition process, the human spatial attention mechanism would move, engage, and disengage from region to region (i.e., context to context). This inspires us to model region-level interactions, in addition to object-level reasoning, for saliency ranking. Hence, we propose a novel bi-directional method to unify spatial attention and object-based attention for saliency ranking. Our model has two novel modules: (1) a selective object saliency (SOS) module to model object-based attention via inferring the semantic representation of salient objects, and (2) an object-context-object relation (OCOR) module to allocate saliency ranks to objects by jointly modeling object-context and context-object interactions of salient objects. Extensive experiments show that our approach outperforms existing state-of-the-art methods. Code and pretrained model are available at https://github.com/GrassBro/OCOR.

Although PIFu-based 3D human reconstruction methods are popular, the quality of recovered details is still unsatisfactory. In a sparse (e.g., 3 RGBD sensors) capture setting, the depth noise is typically amplified in the PIFu representation, resulting in flat facial surfaces and geometry-fallible bodies. In this paper, we propose a novel geometry-aware two-scale PIFu for 3D human reconstruction from sparse, noisy inputs. Our key idea is to exploit the complementary properties of depth denoising and 3D reconstruction, for learning a two-scale PIFu representation to reconstruct high-frequency facial details and consistent bodies separately. To this end, we first formulate depth denoising and 3D reconstruction as a multi-task learning problem. The depth denoising process enriches the local geometry information of the reconstruction features, while the reconstruction process enhances depth denoising with global topology information. We then propose to learn the two-scale PIFu representation using two MLPs based on the denoised depth and geometry-aware features. Extensive experiments demonstrate the effectiveness of our approach in reconstructing facial details and bodies of different poses and its superiority over state-of-the-art methods.

Early and accurate detection of viruses in clinical and environmental samples is essential for effective public healthcare, treatment, and therapeutics. While PCR detects potential pathogens with high sensitivity, it is difficult to scale and requires knowledge of the exact sequence of the pathogen. With the advent of next-gen single-cell sequencing, it is now possible to scrutinize viral transcriptomics at the finest possible resolution-cells. This newfound ability to investigate individual cells opens new avenues to understand viral pathophysiology with unprecedented resolution. To leverage this ability, we propose an efficient and accurate computational pipeline, named Venus, for virus detection and integration site discovery in both single-cell and bulk-tissue RNA-seq data. Specifically, Venus addresses two main questions: whether a tissue/cell type is infected by viruses or a virus of interest? And if infected, whether and where has the virus inserted itself into the human genome? Our analysis can be broken into two parts-validation and discovery. Firstly, for validation, we applied Venus on well-studied viral datasets, such as HBV- hepatocellular carcinoma and HIV-infection treated with antiretroviral therapy. Secondly, for discovery, we analyzed datasets such as HIV-infected neurological patients and deeply sequenced T-cells. We detected viral transcripts in the novel target of the brain and high-confidence integration sites in immune cells. In conclusion, here we describe Venus, a publicly available software which we believe will be a valuable virus investigation tool for the scientific community at large.

Most existing salient object detection (SOD) methods are designed for RGB images and do not take advantage of the abundant information provided by light fields. Hence, they may fail to detect salient objects of complex structures and delineate their boundaries. Although some methods have explored multi-view information of light field images for saliency detection, they require tedious pixel-level manual annotations of ground truths. In this paper, we propose a novel weakly-supervised learning framework for salient object detection on light field images based on bounding box annotations. Our method has two major novelties. First, given an input light field image and a bounding-box annotation indicating the salient object, we propose a ground truth label hallucination method to generate a pixel-level pseudo saliency map, to avoid heavy cost of pixel-level annotations. This method generates high quality pseudo ground truth saliency maps to help supervise the training, by exploiting information obtained from the light field (including depths and RGB images). Second, to exploit the multi-view nature of the light field data in learning, we propose a fusion attention module to calibrate the spatial and channel-wise light field representations. It learns to focus on informative features and suppress redundant information from the multi-view inputs. Based on these two novelties, we are able to train a new salient object detector with two branches in a weakly-supervised manner. While the RGB branch focuses on modeling the color contrast in the all-in-focus image for locating the salient objects, the Focal branch exploits the depth and the background spatial redundancy of focal slices for eliminating background distractions. Extensive experiments show that our method outperforms existing weakly-supervised methods and most fully supervised methods.

This paper proposes a novel location-aware deep-learning-based single image reflection removal method. Our network has a reflection detection module to regress a probabilistic reflection confidence map, taking multi-scale Laplacian features as inputs. This probabilistic map tells if a region is reflection-dominated or transmission-dominated, and it is used as a cue for the network to control the feature flow when predicting the reflection and transmission layers. We design our network as a recurrent network to progressively refine reflection removal results at each iteration. The novelty is that we leverage Laplacian kernel parameters to emphasize the boundaries of strong reflections. It is beneficial to strong reflection detection and substantially improves the quality of reflection removal results. Extensive experiments verify the superior performance of the proposed method over state-of-the-art approaches. Our code and the pre-trained model can be found at https://github.com/zdlarr/Location-aware-SIRR.

Although CNNs have achieved remarkable progress on the shadow detection task, they tend to make mistakes in dark non-shadow regions and relatively bright shadow regions. They are also susceptible to brightness change. These two phenomenons reveal that deep shadow detectors heavily depend on the intensity cue, which we refer to as intensity bias. In this paper, we propose a novel feature decomposition and reweighting scheme to mitigate this intensity bias, in which multi-level integrated features are decomposed into intensity-variant and intensity-invariant components through self-supervision. By reweighting these two types of features, our method can reallocate the attention to the corresponding latent semantics and achieves balanced exploitation of them. Extensive experiments on three popular datasets show that the proposed method outperforms state-of-the-art shadow detectors.

Although huge progress has been made on scene analysis in recent years, most existing works assume the input images to be in day-time with good lighting conditions. In this work, we aim to address the night-time scene parsing (NTSP) problem, which has two main challenges: 1) labeled night-time data are scarce, and 2) over- and under-exposures may co-occur in the input night-time images and are not explicitly modeled in existing pipelines. To tackle the scarcity of night-time data, we collect a novel labeled dataset, named NightCity, of 4,297 real night-time images with ground truth pixel-level semantic annotations. To our knowledge, NightCity is the largest dataset for NTSP. In addition, we also propose an exposure-aware framework to address the NTSP problem through augmenting the segmentation process with explicitly learned exposure features. Extensive experiments show that training on NightCity can significantly improve NTSP performances and that our exposure-aware model outperforms the state-of-the-art methods, yielding top performances on our dataset as well as existing datasets.

Rain degrades image visual quality and disrupts object structures, obscuring their details and erasing their colors. Existing deraining methods are primarily based on modeling either visual appearances of rain or its physical characteristics (e.g., rain direction and density), and thus suffer from two common problems. First, due to the stochastic nature of rain, they tend to fail in recognizing rain streaks correctly, and wrongly remove image structures and details. Second, they fail to recover the image colors erased by heavy rain. In this paper, we address these two problems with the following three contributions. First, we propose a novel PHP block to aggregate comprehensive spatial and hierarchical information for removing rain streaks of different sizes. Second, we propose a novel network to first remove rain streaks, then recover objects structures/colors, and finally enhance details. Third, to train the network, we prepare a new dataset, and propose a novel loss function to introduce semantic and color regularization for deraining. Extensive experiments demonstrate the superiority of the proposed method over state-of-the-art deraining methods on both synthesized and real-world data, in terms of visual quality, quantitative accuracy, and running speed.

Low-light images typically suffer from two problems. First, they have low visibility (i.e., small pixel values). Second, noise becomes significant and disrupts the image content, due to low signal-to-noise ratio. Most existing low-light image enhancement methods, however, learn from noise-negligible datasets. They rely on users having good photographic skills in taking images with low noise. Unfortunately, this is not the case for majority of the low-light images. While concurrently enhancing a low-light image and removing its noise is ill-posed, we observe that noise exhibits different levels of contrast in different frequency layers, and it is much easier to detect noise in the low-frequency layer than in the high one. Inspired by this observation, we propose a frequency-based decomposition- and- enhancement model for low-light image enhancement. Based on this model, we present a novel network that first learns to recover image objects in the low-frequency layer and then enhances high-frequency details based on the recovered image objects. In addition, we have prepared a new low-light image dataset with real noise to facilitate learning. Finally, we have conducted extensive experiments to show that the proposed method outperforms state-of-the-art approaches in enhancing practical noisy low-light images.

Removing rain streaks from a single image has been drawing considerable attention as rain streaks can severely degrade the image quality and affect the performance of existing outdoor vision tasks. While recent CNN-based derainers have reported promising performances, deraining remains an open problem for two reasons. First, existing synthesized rain datasets have only limited realism, in terms of modeling real rain characteristics such as rain shape, direction and intensity. Second, there are no public benchmarks for quantitative comparisons on real rain images, which makes the current evaluation less objective. The core challenge is that real world rain/clean image pairs cannot be captured at the same time. In this paper, we address the single image rain removal problem in two ways. First, we propose a semi-automatic method that incorporates temporal priors and human supervision to generate a high-quality clean image from each input sequence of real rain images. Using this method, we construct a large-scale dataset of ∼29.5K rain/rain-free image pairs that covers a wide range of natural rain scenes. Second, to better cover the stochastic distribution of real rain streaks, we propose a novel SPatial Attentive Network (SPANet) to remove rain streaks in a local-to-global manner. Extensive experiments demonstrate that our network performs favorably against the state-of-the-art deraining methods.

Recently, single-image super-resolution has made great progress due to the development of deep convolutional neural networks (CNNs). The vast majority of CNN-based models use a predefined upsampling operator, such as bicubic interpolation, to upscale input low-resolution images to the desired size and learn nonlinear mapping between the interpolated image and ground truth high-resolution (HR) image. However, interpolation processing can lead to visual artifacts as details are over smoothed, particularly when the super-resolution factor is high. In this paper, we propose a deep recurrent fusion network (DRFN), which utilizes transposed convolution instead of bicubic interpolation for upsampling and integrates different-level features extracted from recurrent residual blocks to reconstruct the final HR images. We adopt a deep recurrence learning strategy and, thus, have a larger receptive field, which is conducive to reconstructing an image more accurately. Furthermore, we show that the multilevel fusion structure is suitable for dealing with image super-resolution problems. Extensive benchmark evaluations demonstrate that the proposed DRFN performs better than most current deep learning methods in terms of accuracy and visual effects, especially for large-scale images, while using fewer parameters.

Image correction aims to adjust an input image into a visually pleasing one. Existing approaches are proposed mainly from the perspective of image pixel manipulation. They are not effective to recover the details in the under/over exposed regions. In this paper, we revisit the image formation procedure and notice that the missing details in these regions exist in the corresponding high dynamic range (HDR) data. These details are well perceived by the human eyes but diminished in the low dynamic range (LDR) domain because of the tone mapping process. Therefore, we formulate the image correction task as an HDR transformation process and propose a novel approach called Deep Reciprocating HDR Transformation (DRHT). Given an input LDR image, we first reconstruct the missing details in the HDR domain. We then perform tone mapping on the predicted HDR data to generate the output LDR image with the recovered details. To this end, we propose a united framework consisting of two CNNs for HDR reconstruction and tone mapping. They are integrated end-to-end for joint training and prediction. Experiments on the standard benchmarks demonstrate that the proposed method performs favorably against state-of-the-art image correction methods.

Image matting is an ill-posed problem. It requires a user input trimap or some strokes to obtain an alpha matte of the foreground object. A fine user input is essential to obtain a good result, which is either time consuming or suitable for experienced users who know where to place the strokes. In this paper, we explore the intrinsic relationship between the user input and the matting algorithm to address the problem of where and when the user should provide the input. Our aim is to discover the most informative sequence of regions for user input in order to produce a good alpha matte with minimum labeling efforts. To this end, we propose an active matting method with recurrent reinforcement learning. The proposed framework involves human in the loop by sequentially detecting informative regions for trivial human judgement. Comparing to traditional matting algorithms, the proposed framework requires much less efforts, and can produce satisfactory results with just 10 regions. Through extensive experiments, we show that the proposed model reduces user efforts significantly and achieves comparable performance to dense trimaps in a user-friendly manner. We further show that the learned informative knowledge can be generalized across different matting algorithms.