Salient Object Ranking (SOR) involves ranking the degree of saliency of multiple salient objects in an input image. Most recently, a method is proposed for ranking salient objects in an input video based on a predicted fixation map. It relies solely on the density of the fixations within the salient objects to infer their saliency ranks, which is incompatible with human perception of saliency ranking. In this work, we propose to explicitly learn the spatial and temporal relations between different salient objects to produce the saliency ranks. To this end, we propose an end-to-end method for video salient object ranking (VSOR), with two novel modules: an intra-frame adaptive relation (IAR) module to learn the spatial relation among the salient objects in the same frame locally and globally, and an inter-frame dynamic relation (IDR) module to model the temporal relation of saliency across different frames. In addition, to address the limited video types (just sports and movies) and scene diversity in the existing VSOR dataset, we propose a new dataset that covers different video types and diverse scenes on a large scale. Experimental results demonstrate that our method outperforms state-of-the-art methods in relevant fields. We will make the source code and our proposed dataset available.
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 those 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 the region-level interactions, in addition to the object-level reasoning, for saliency ranking. To this end, we propose a novel bi-directional method to unify spatial attention and object-based attention for saliency ranking. Our model includes two novel modules: (1) a selective object saliency (SOS) module that models objectbased attention via inferring the semantic representation of the salient object, and (2) an object-context-object relation (OCOR) module that allocates saliency ranks to objects by jointly modeling the object-context and context-object interactions of the salient objects. Extensive experiments show that our approach outperforms existing state-of-theart methods. Our code and pretrained model are available at https://github.com/GrassBro/OCOR.
While the 3D human reconstruction methods using Pixel-aligned implicit function (PIFu) develop fast, we observe that the quality of reconstructed details is still not satisfactory. Flat facial surfaces frequently occur in the PIFu-based reconstruction results. To this end, we propose a two-scale PIFu representation to enhance the quality of the reconstructed facial details. Specifically, we utilize two MLPs to separately represent the PIFus for the face and human body. An MLP dedicated to the reconstruction of 3D faces can increase the network capacity and reduce the difficulty of the reconstruction of facial details as in the previous one-scale PIFu representation. To remedy the topology error, we leverage 3 RGBD sensors to capture multiview RGBD data as the input to the network, a sparse, lightweight capture setting. Since the depth noise severely influences the reconstruction results, we design a depth refinement module to reduce the noise of the raw depths under the guidance of the input RGB images. We also propose an adaptive fusion scheme to fuse the predicted occupancy field of the body and face to eliminate the discontinuity artifact at their boundaries. Experiments demonstrate the effectiveness of our approach in reconstructing vivid facial details and deforming body shapes, and verify its superiority over state-of-the-art methods.
Existing salient instance detection (SID) methods typically learn from pixel-level annotated datasets. In this paper, we present the first weakly-supervised approach to the SID problem. Although weak supervision has been considered in general saliency detection, it is mainly based on using class labels for object localization. However, it is non-trivial to use only class labels to learn instance-aware saliency information, as salient instances with high semantic affinities may not be easily separated by the labels. As the subitizing information provides an instant judgement on the number of salient items, it is naturally related to detecting salient instances and may help separate instances of the same class while grouping different parts of the same instance. Inspired by this observation, we propose to use class and subitizing labels as weak supervision for the SID problem. We propose a novel weakly-supervised network with three branches: a Saliency Detection Branch leveraging class consistency information to locate candidate objects; a Boundary Detection Branch exploiting class discrepancy information to delineate object boundaries; and a Centroid Detection Branch using subitizing information to detect salient instance centroids. This complementary information is then fused to produce a salient instance map. To facilitate the learning process, we further propose a progressive training scheme to reduce label noise and the corresponding noise learned by the model, via reciprocating the model with progressive salient instance prediction and model refreshing. Our extensive evaluations show that the proposed method plays favorably against carefully designed baseline methods adapted from related tasks.
To address the challenging portrait video matting problem more precisely, existing works typically apply some matting priors that require additional user efforts to obtain, such as annotated trimaps or background images. In this work, we observe that instead of asking the user to explicitly provide a background image, we may recover it from the input video itself. To this end, we first propose a novel background restoration module (BRM) to recover the background image dynamically from the input video. BRM is extremely lightweight and can be easily integrated into existing matting models. By combining BRM with a recent image matting model, MODNet, we then present MODNet-V for portrait video matting. Benefited from the strong background prior provided by BRM, MODNet-V has only 1/3 of the parameters of MODNet but achieves comparable or even better performances. Our design allows MODNet-V to be trained in an end-to-end manner on a single NVIDIA 3090 GPU. Finally, we introduce a new patch refinement module (PRM) to adapt MODNet-V for high-resolution videos while keeping MODNet-V lightweight and fast.
Image matting is an ill-posed problem that usually requires additional user input, such as trimaps or scribbles. Drawing a fne trimap requires a large amount of user effort, while using scribbles can hardly obtain satisfactory alpha mattes for non-professional users. Some recent deep learning-based matting networks rely on large-scale composite datasets for training to improve performance, resulting in the occasional appearance of obvious artifacts when processing natural images. In this article, we explore the intrinsic relationship between user input and alpha mattes and strike a balance between user effort and the quality of alpha mattes. In particular, we propose an interactive framework, referred to as smart scribbles, to guide users to draw few scribbles on the input images to produce high-quality alpha mattes. It frst infers the most informative regions of an image for drawing scribbles to indicate different categories (foreground, background, or unknown) and then spreads these scribbles (i.e., the category labels) to the rest of the image via our well-designed two-phase propagation. Both neighboring low-level afnities and high-level semantic features are considered during the propagation process. Our method can be optimized without large-scale matting datasets and exhibits more universality in real situations. Extensive experiments demonstrate that smart scribbles can produce more accurate alpha mattes with reduced additional input, compared to the state-of-the-art matting methods.
In this paper, we propose a fully automatic system for generating comic books from videos without any human intervention. Given an input video along with its subtitles, our approach first extracts informative keyframes by analyzing the subtitles, and stylizes keyframes into comic-style images. Then, we propose a novel automatic multi-page layout framework, which can allocate the images across multiple pages and synthesize visually interesting layouts based on the rich semantics of the images (e.g., importance and inter-image relation). Finally, as opposed to using the same type of balloon as in previous works, we propose an emotion-aware balloon generation method to create different types of word balloons by analyzing the emotion of subtitles and audios. Our method is able to vary balloon shapes and word sizes in balloons in response to different emotions, leading to more enriched reading experience. Once the balloons are generated, they are placed adjacent to their corresponding speakers via speaker detection. Our results show that our method, without requiring any user inputs, can generate high-quality comic pages with visually rich layouts and balloons. Our user studies also demonstrate that users prefer our generated results over those by state-of-the-art comic generation systems.
Salient object detection aims at detecting the most visually distinct objects and producing the corresponding masks. As the cost of pixel-level annotations is high, image tags are usually used as weak supervisions. However, an image tag can only be used to annotate one class of objects. In this paper, we introduce saliency subitizing as the weak supervision since it is class-agnostic. This allows the supervision to be aligned with the property of saliency detection, where the salient objects of an image could be from more than one class. To this end, we propose a model with two modules, Saliency Subitizing Module (SSM) and Saliency Updating Module (SUM). While SSM learns to generate the initial saliency masks using the subitizing information, without the need for any unsupervised methods or some random seeds, SUM helps iteratively refine the generated saliency masks. We conduct extensive experiments on five benchmark datasets. The experimental results show that our method outperforms other weakly-supervised methods and even performs comparably to some 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 whether a region is reflection-dominated or transmission-dominated. The novelty is that we use the reflection confidence map as the cues for the network to learn how to encode the reflection information adaptively and control the feature flow when predicting reflection and transmission layers. The integration of location information into the network significantly improves the quality of reflection removal results. Besides, a set of learnable Laplacian kernel parameters is introduced to facilitate the extraction of discriminative Laplacian features for reflection detection. We design our network as a recurrent network to progressively refine each iteration's reflection removal results. Extensive experiments verify the superior performance of the proposed method over state-of-the-art approaches.
For portrait matting without the green screen, existing works either require auxiliary inputs that are costly to obtain or use multiple models that are computationally expensive. Consequently, they are unavailable in real-time applications. In contrast, we present a light-weight matting objective decomposition network (MODNet), which can process portrait matting from a single input image in real time. The design of MODNet benefits from optimizing a series of correlated sub-objectives simultaneously via explicit constraints. Moreover, since trimap-free methods usually suffer from the domain shift problem in practice, we introduce (1) a self-supervised strategy based on sub-objectives consistency to adapt MODNet to real-world data and (2) a one-frame delay trick to smooth the results when applying MODNet to portrait video sequence. MODNet is easy to be trained in an end-to-end style. It is much faster than contemporaneous matting methods and runs at 63 frames per second. On a carefully designed portrait matting benchmark newly proposed in this work, MODNet greatly outperforms prior trimap-free methods. More importantly, our method achieves remarkable results in daily photos and videos. Now, do you really need a green screen for real-time portrait matting?