Video Scene Parsing (VSP) has emerged as a cornerstone in computer vision, facilitating the simultaneous segmentation, recognition, and tracking of diverse visual entities in dynamic scenes. In this survey, we present a holistic review of recent advances in VSP, covering a wide array of vision tasks, including Video Semantic Segmentation (VSS), Video Instance Segmentation (VIS), Video Panoptic Segmentation (VPS), as well as Video Tracking and Segmentation (VTS), and Open-Vocabulary Video Segmentation (OVVS). We systematically analyze the evolution from traditional hand-crafted features to modern deep learning paradigms -- spanning from fully convolutional networks to the latest transformer-based architectures -- and assess their effectiveness in capturing both local and global temporal contexts. Furthermore, our review critically discusses the technical challenges, ranging from maintaining temporal consistency to handling complex scene dynamics, and offers a comprehensive comparative study of datasets and evaluation metrics that have shaped current benchmarking standards. By distilling the key contributions and shortcomings of state-of-the-art methodologies, this survey highlights emerging trends and prospective research directions that promise to further elevate the robustness and adaptability of VSP in real-world applications.
RGB-D scene parsing methods effectively capture both semantic and geometric features of the environment, demonstrating great potential under challenging conditions such as extreme weather and low lighting. However, existing RGB-D scene parsing methods predominantly rely on supervised training strategies, which require a large amount of manually annotated pixel-level labels that are both time-consuming and costly. To overcome these limitations, we introduce DepthMatch, a semi-supervised learning framework that is specifically designed for RGB-D scene parsing. To make full use of unlabeled data, we propose complementary patch mix-up augmentation to explore the latent relationships between texture and spatial features in RGB-D image pairs. We also design a lightweight spatial prior injector to replace traditional complex fusion modules, improving the efficiency of heterogeneous feature fusion. Furthermore, we introduce depth-guided boundary loss to enhance the model's boundary prediction capabilities. Experimental results demonstrate that DepthMatch exhibits high applicability in both indoor and outdoor scenes, achieving state-of-the-art results on the NYUv2 dataset and ranking first on the KITTI Semantics benchmark.
Diffusion models have shown excellent performance in text-to-image generation. Nevertheless, existing methods often suffer from performance bottlenecks when handling complex prompts that involve multiple objects, characteristics, and relations. Therefore, we propose a Multi-agent Collaboration-based Compositional Diffusion (MCCD) for text-to-image generation for complex scenes. Specifically, we design a multi-agent collaboration-based scene parsing module that generates an agent system comprising multiple agents with distinct tasks, utilizing MLLMs to extract various scene elements effectively. In addition, Hierarchical Compositional diffusion utilizes a Gaussian mask and filtering to refine bounding box regions and enhance objects through region enhancement, resulting in the accurate and high-fidelity generation of complex scenes. Comprehensive experiments demonstrate that our MCCD significantly improves the performance of the baseline models in a training-free manner, providing a substantial advantage in complex scene generation.
Recent vision foundation models (VFMs), typically based on Vision Transformer (ViT), have significantly advanced numerous computer vision tasks. Despite their success in tasks focused solely on RGB images, the potential of VFMs in RGB-depth driving scene parsing remains largely under-explored. In this article, we take one step toward this emerging research area by investigating a feasible technique to fully exploit VFMs for generalizable RGB-depth driving scene parsing. Specifically, we explore the inherent characteristics of RGB and depth data, thereby presenting a Heterogeneous Feature Integration Transformer (HFIT). This network enables the efficient extraction and integration of comprehensive heterogeneous features without re-training ViTs. Relative depth prediction results from VFMs, used as inputs to the HFIT side adapter, overcome the limitations of the dependence on depth maps. Our proposed HFIT demonstrates superior performance compared to all other traditional single-modal and data-fusion scene parsing networks, pre-trained VFMs, and ViT adapters on the Cityscapes and KITTI Semantics datasets. We believe this novel strategy paves the way for future innovations in VFM-based data-fusion techniques for driving scene parsing. Our source code is publicly available at https://mias.group/HFIT.
Brains perform decision-making by Bayes theorem. The theorem quantifies events as probabilities and, based on probability rules, renders the decisions. Learning from this, Bayes theorem can be applied to enable efficient user-scene interactions. However, given the probabilistic nature, implementing Bayes theorem in hardware using conventional deterministic computing can incur excessive computational cost and decision latency. Though challenging, here we present a probabilistic computing approach based on memristors to implement the Bayes theorem. We integrate memristors with Boolean logics and, by exploiting the volatile stochastic switching of the memristors, realise probabilistic logic operations, key for hardware Bayes theorem implementation. To empirically validate the efficacy of the hardware Bayes theorem in user-scene interactions, we develop lightweight Bayesian inference and fusion hardware operators using the probabilistic logics and apply the operators in road scene parsing for self-driving, including route planning and obstacle detection. The results show our operators can achieve reliable decisions in less than 0.4 ms (or equivalently 2,500 fps), outperforming human decision-making and the existing driving assistance systems.
Multi-object multi-part scene segmentation is a challenging task whose complexity scales exponentially with part granularity and number of scene objects. To address the task, we propose a plug-and-play approach termed OLAF. First, we augment the input (RGB) with channels containing object-based structural cues (fg/bg mask, boundary edge mask). We propose a weight adaptation technique which enables regular (RGB) pre-trained models to process the augmented (5-channel) input in a stable manner during optimization. In addition, we introduce an encoder module termed LDF to provide low-level dense feature guidance. This assists segmentation, particularly for smaller parts. OLAF enables significant mIoU gains of $\mathbf{3.3}$ (Pascal-Parts-58), $\mathbf{3.5}$ (Pascal-Parts-108) over the SOTA model. On the most challenging variant (Pascal-Parts-201), the gain is $\mathbf{4.0}$. Experimentally, we show that OLAF's broad applicability enables gains across multiple architectures (CNN, U-Net, Transformer) and datasets. The code is available at olafseg.github.io
Task-specific data-fusion networks have marked considerable achievements in urban scene parsing. Among these networks, our recently proposed RoadFormer successfully extracts heterogeneous features from RGB images and surface normal maps and fuses these features through attention mechanisms, demonstrating compelling efficacy in RGB-Normal road scene parsing. However, its performance significantly deteriorates when handling other types/sources of data or performing more universal, all-category scene parsing tasks. To overcome these limitations, this study introduces RoadFormer+, an efficient, robust, and adaptable model capable of effectively fusing RGB-X data, where ``X'', represents additional types/modalities of data such as depth, thermal, surface normal, and polarization. Specifically, we propose a novel hybrid feature decoupling encoder to extract heterogeneous features and decouple them into global and local components. These decoupled features are then fused through a dual-branch multi-scale heterogeneous feature fusion block, which employs parallel Transformer attentions and convolutional neural network modules to merge multi-scale features across different scales and receptive fields. The fused features are subsequently fed into a decoder to generate the final semantic predictions. Notably, our proposed RoadFormer+ ranks first on the KITTI Road benchmark and achieves state-of-the-art performance in mean intersection over union on the Cityscapes, MFNet, FMB, and ZJU datasets. Moreover, it reduces the number of learnable parameters by 65\% compared to RoadFormer. Our source code will be publicly available at mias.group/RoadFormerPlus.
The existing contrastive learning methods mainly focus on single-grained representation learning, e.g., part-level, object-level or scene-level ones, thus inevitably neglecting the transferability of representations on other granularity levels. In this paper, we aim to learn multi-grained representations, which can effectively describe the image on various granularity levels, thus improving generalization on extensive downstream tasks. To this end, we propose a novel Multi-Grained Contrast method (MGC) for unsupervised representation learning. Specifically, we construct delicate multi-grained correspondences between positive views and then conduct multi-grained contrast by the correspondences to learn more general unsupervised representations. Without pretrained on large-scale dataset, our method significantly outperforms the existing state-of-the-art methods on extensive downstream tasks, including object detection, instance segmentation, scene parsing, semantic segmentation and keypoint detection. Moreover, experimental results support the data-efficient property and excellent representation transferability of our method. The source code and trained weights are available at \url{https://github.com/visresearch/mgc}.
Night-time scene parsing aims to extract pixel-level semantic information in night images, aiding downstream tasks in understanding scene object distribution. Due to limited labeled night image datasets, unsupervised domain adaptation (UDA) has become the predominant method for studying night scenes. UDA typically relies on paired day-night image pairs to guide adaptation, but this approach hampers dataset construction and restricts generalization across night scenes in different datasets. Moreover, UDA, focusing on network architecture and training strategies, faces difficulties in handling classes with few domain similarities. In this paper, we leverage Prompt Images Guidance (PIG) to enhance UDA with supplementary night knowledge. We propose a Night-Focused Network (NFNet) to learn night-specific features from both target domain images and prompt images. To generate high-quality pseudo-labels, we propose Pseudo-label Fusion via Domain Similarity Guidance (FDSG). Classes with fewer domain similarities are predicted by NFNet, which excels in parsing night features, while classes with more domain similarities are predicted by UDA, which has rich labeled semantics. Additionally, we propose two data augmentation strategies: the Prompt Mixture Strategy (PMS) and the Alternate Mask Strategy (AMS), aimed at mitigating the overfitting of the NFNet to a few prompt images. We conduct extensive experiments on four night-time datasets: NightCity, NightCity+, Dark Zurich, and ACDC. The results indicate that utilizing PIG can enhance the parsing accuracy of UDA.
The third Pixel-level Video Understanding in the Wild (PVUW CVPR 2024) challenge aims to advance the state of art in video understanding through benchmarking Video Panoptic Segmentation (VPS) and Video Semantic Segmentation (VSS) on challenging videos and scenes introduced in the large-scale Video Panoptic Segmentation in the Wild (VIPSeg) test set and the large-scale Video Scene Parsing in the Wild (VSPW) test set, respectively. This paper details our research work that achieved the 1st place winner in the PVUW'24 VPS challenge, establishing state of art results in all metrics, including the Video Panoptic Quality (VPQ) and Segmentation and Tracking Quality (STQ). With minor fine-tuning our approach also achieved the 3rd place in the PVUW'24 VSS challenge ranked by the mIoU (mean intersection over union) metric and the first place ranked by the VC16 (16-frame video consistency) metric. Our winning solution stands on the shoulders of giant foundational vision transformer model (DINOv2 ViT-g) and proven multi-stage Decoupled Video Instance Segmentation (DVIS) frameworks for video understanding.
Pixel-level Scene Understanding is one of the fundamental problems in computer vision, which aims at recognizing object classes, masks and semantics of each pixel in the given image. Compared with image scene parsing, video scene parsing introduces temporal information, which can effectively improve the consistency and accuracy of prediction,because the real-world is actually video-based rather than a static state. In this paper, we adopt semi-supervised video semantic segmentation method based on unreliable pseudo labels. Then, We ensemble the teacher network model with the student network model to generate pseudo labels and retrain the student network. Our method achieves the mIoU scores of 63.71% and 67.83% on development test and final test respectively. Finally, we obtain the 1st place in the Video Scene Parsing in the Wild Challenge at CVPR 2024.
Radar sensors are low cost, long-range, and weather-resilient. Therefore, they are widely used for driver assistance functions, and are expected to be crucial for the success of autonomous driving in the future. In many perception tasks only pre-processed radar point clouds are considered. In contrast, radar spectra are a raw form of radar measurements and contain more information than radar point clouds. However, radar spectra are rather difficult to interpret. In this work, we aim to explore the semantic information contained in spectra in the context of automated driving, thereby moving towards better interpretability of radar spectra. To this end, we create a radar spectra-language model, allowing us to query radar spectra measurements for the presence of scene elements using free text. We overcome the scarcity of radar spectra data by matching the embedding space of an existing vision-language model. Finally, we explore the benefit of the learned representation for scene retrieval using radar spectra only, and obtain improvements in free space segmentation and object detection merely by injecting the spectra embedding into a baseline model.
Advancements in machine learning, computer vision, and robotics have paved the way for transformative solutions in various domains, particularly in agriculture. For example, accurate identification and segmentation of fruits from field images plays a crucial role in automating jobs such as harvesting, disease detection, and yield estimation. However, achieving robust and precise infield fruit segmentation remains a challenging task since large amounts of labeled data are required to handle variations in fruit size, shape, color, and occlusion. In this paper, we develop a few-shot semantic segmentation framework for infield fruits using transfer learning. Concretely, our work is aimed at addressing agricultural domains that lack publicly available labeled data. Motivated by similar success in urban scene parsing, we propose specialized pre-training using a public benchmark dataset for fruit transfer learning. By leveraging pre-trained neural networks, accurate semantic segmentation of fruit in the field is achieved with only a few labeled images. Furthermore, we show that models with pre-training learn to distinguish between fruit still on the trees and fruit that have fallen on the ground, and they can effectively transfer the knowledge to the target fruit dataset.
We propose a system for visual scene analysis and recognition based on encoding the sparse, latent feature-representation of an image into a high-dimensional vector that is subsequently factorized to parse scene content. The sparse feature representation is learned from image statistics via convolutional sparse coding, while scene parsing is performed by a resonator network. The integration of sparse coding with the resonator network increases the capacity of distributed representations and reduces collisions in the combinatorial search space during factorization. We find that for this problem the resonator network is capable of fast and accurate vector factorization, and we develop a confidence-based metric that assists in tracking the convergence of the resonator network.
Data-fusion networks have shown significant promise for RGB-thermal scene parsing. However, the majority of existing studies have relied on symmetric duplex encoders for heterogeneous feature extraction and fusion, paying inadequate attention to the inherent differences between RGB and thermal modalities. Recent progress in vision foundation models (VFMs) trained through self-supervision on vast amounts of unlabeled data has proven their ability to extract informative, general-purpose features. However, this potential has yet to be fully leveraged in the domain. In this study, we take one step toward this new research area by exploring a feasible strategy to fully exploit VFM features for RGB-thermal scene parsing. Specifically, we delve deeper into the unique characteristics of RGB and thermal modalities, thereby designing a hybrid, asymmetric encoder that incorporates both a VFM and a convolutional neural network. This design allows for more effective extraction of complementary heterogeneous features, which are subsequently fused in a dual-path, progressive manner. Moreover, we introduce an auxiliary task to further enrich the local semantics of the fused features, thereby improving the overall performance of RGB-thermal scene parsing. Our proposed HAPNet, equipped with all these components, demonstrates superior performance compared to all other state-of-the-art RGB-thermal scene parsing networks, achieving top ranks across three widely used public RGB-thermal scene parsing datasets. We believe this new paradigm has opened up new opportunities for future developments in data-fusion scene parsing approaches.
Humans perceive and construct the world as an arrangement of simple parametric models. In particular, we can often describe man-made environments using volumetric primitives such as cuboids or cylinders. Inferring these primitives is important for attaining high-level, abstract scene descriptions. Previous approaches for primitive-based abstraction estimate shape parameters directly and are only able to reproduce simple objects. In contrast, we propose a robust estimator for primitive fitting, which meaningfully abstracts complex real-world environments using cuboids. A RANSAC estimator guided by a neural network fits these primitives to a depth map. We condition the network on previously detected parts of the scene, parsing it one-by-one. To obtain cuboids from single RGB images, we additionally optimise a depth estimation CNN end-to-end. Naively minimising point-to-primitive distances leads to large or spurious cuboids occluding parts of the scene. We thus propose an improved occlusion-aware distance metric correctly handling opaque scenes. Furthermore, we present a neural network based cuboid solver which provides more parsimonious scene abstractions while also reducing inference time. The proposed algorithm does not require labour-intensive labels, such as cuboid annotations, for training. Results on the NYU Depth v2 dataset demonstrate that the proposed algorithm successfully abstracts cluttered real-world 3D scene layouts.
The complexity of scene parsing grows with the number of object and scene classes, which is higher in unrestricted open scenes. The biggest challenge is to model the spatial relation between scene elements while succeeding in identifying objects at smaller scales. This paper presents a novel feature-boosting network that gathers spatial context from multiple levels of feature extraction and computes the attention weights for each level of representation to generate the final class labels. A novel `channel attention module' is designed to compute the attention weights, ensuring that features from the relevant extraction stages are boosted while the others are attenuated. The model also learns spatial context information at low resolution to preserve the abstract spatial relationships among scene elements and reduce computation cost. Spatial attention is subsequently concatenated into a final feature set before applying feature boosting. Low-resolution spatial attention features are trained using an auxiliary task that helps learning a coarse global scene structure. The proposed model outperforms all state-of-the-art models on both the ADE20K and the Cityscapes datasets.
UAV-based automatic railway inspection is expected to have the potential to reform the inspection of railways. In this area, real-time railway scene parsing is quite essential. However, the limited computation resources of the UAV onboard computer pose a huge challenge for the algorithm to juggle a precise prediction with strong timeliness. Concerning this issue, this paper proposes a novel algorithm named deep fully decoupled residual convolutional network, which consists of fully decoupled residual blocks (Non-bottleneck-FDs) to deal with the dilemma between the high demand of real-time and limited resources. The residual block is constructed based on a new convolution which divides the standard convolution into three sequential convolutions to decouple the conventional operational correlations fully. Furthermore, a customized auxiliary line loss (LL) function is proposed to constrain the segmentation of railway and non-railway simultaneously without increasing the computation complexity. The proposed LL can force the predicted railway areas to concentrate in long strip areas precisely and inhibit their appearances in other impossible local areas. Subsequently, an integrated loss backpropagation strategy of the LL and cross-entropy function is presented. A comprehensive set of experiments are conducted for verification. Experiments demonstrate the superior performance of our approach with a more than 2× reduction in parameters and computation cost. Moreover, our approach also has a faster inference speed than the most existing lightweight architectures while providing comparable or higher accuracy. It is proven that our approach can reconcile the precise prediction with strong timeliness for railway scene parsing within the limitation of onboard computers. Besides, the results also imply its highest performance in terms of local details and edges of railway areas.
There are two challenges presented in parsing road scenes from UAV images: the complexity of processing high-resolution images and the dependency on extensive manual annotations required by traditional supervised deep learning methods to train robust and accurate models. In this paper, a novel unsupervised road parsing framework that leverages advancements in vision language models with fundamental computer vision techniques is introduced to address these critical challenges. Our approach initiates with a vision language model that efficiently processes ultra-high resolution images to rapidly identify road regions of interest. Subsequent application of the vision foundation model, SAM, generates masks for these regions without requiring category information. A self-supervised learning network then processes these masked regions to extract feature representations, which are clustered using an unsupervised algorithm that assigns unique IDs to each feature cluster. The masked regions are combined with the corresponding IDs to generate initial pseudo-labels, which initiate an iterative self-training process for regular semantic segmentation. Remarkably, the proposed method achieves a mean Intersection over Union (mIoU) of 89.96% on the development dataset without any manual annotation, demonstrating extraordinary flexibility by surpassing the limitations of human-defined categories, and autonomously acquiring knowledge of new categories from the dataset itself.
Leveraging rich information is crucial for dense prediction tasks. Light field (LF) cameras are instrumental in this regard, as they allow data to be sampled from various perspectives. This capability provides valuable spatial, depth, and angular information, enhancing scene-parsing tasks. However, we have identified two overlooked issues for the LF salient object detection (SOD) task. (1): Previous approaches predominantly employ a customized two-stream design to discover the spatial and depth features within light field images. The network struggles to learn the implicit angular information between different images due to a lack of intra-network data connectivity. (2): Little research has been directed towards the data augmentation strategy for LF SOD. Research on inter-network data connectivity is scant. In this study, we propose an efficient paradigm (LF Tracy) to address those issues. This comprises a single-pipeline encoder paired with a highly efficient information aggregation (IA) module (around 8M parameters) to establish an intra-network connection. Then, a simple yet effective data augmentation strategy called MixLD is designed to bridge the inter-network connections. Owing to this innovative paradigm, our model surpasses the existing state-of-the-art method through extensive experiments. Especially, LF Tracy demonstrates a 23% improvement over previous results on the latest large-scale PKU dataset. The source code is publicly available at: https://github.com/FeiBryantkit/LF-Tracy.