Michael Ying Yang

Hao Cheng, Mengmeng Liu, Lin Chen et al.

Trajectory prediction has been a long-standing problem in intelligent systems like autonomous driving and robot navigation. Models trained on large-scale benchmarks have made significant progress in improving prediction accuracy. However, the importance on efficiency for real-time applications has been less emphasized. This paper proposes an attention-based graph model, named GATraj, which achieves a good balance of prediction accuracy and inference speed. We use attention mechanisms to model the spatial-temporal dynamics of agents, such as pedestrians or vehicles, and a graph convolutional network to model their interactions. Additionally, a Laplacian mixture decoder is implemented to mitigate mode collapse and generate diverse multimodal predictions for each agent. GATraj achieves state-of-the-art prediction performance at a much higher speed when tested on the ETH/UCY datasets for pedestrian trajectories, and good performance at about 100 Hz inference speed when tested on the nuScenes dataset for autonomous driving. We conduct extensive experiments to analyze the probability estimation of the Laplacian mixture decoder and compare it with a Gaussian mixture decoder for predicting different multimodalities. Furthermore, comprehensive ablation studies demonstrate the effectiveness of each proposed module in GATraj. The code is released at https://github.com/mengmengliu1998/GATraj.

Yunshuang Yuan, Hao Cheng, Michael Ying Yang et al.

Safety is critical for autonomous driving, and one aspect of improving safety is to accurately capture the uncertainties of the perception system, especially knowing the unknown. Different from only providing deterministic or probabilistic results, e.g., probabilistic object detection, that only provide partial information for the perception scenario, we propose a complete probabilistic model named GevBEV. It interprets the 2D driving space as a probabilistic Bird's Eye View (BEV) map with point-based spatial Gaussian distributions, from which one can draw evidence as the parameters for the categorical Dirichlet distribution of any new sample point in the continuous driving space. The experimental results show that GevBEV not only provides more reliable uncertainty quantification but also outperforms the previous works on the benchmarks OPV2V and V2V4Real of BEV map interpretation for cooperative perception in simulated and real-world driving scenarios, respectively. A critical factor in cooperative perception is the data transmission size through the communication channels. GevBEV helps reduce communication overhead by selecting only the most important information to share from the learned uncertainty, reducing the average information communicated by 87% with only a slight performance drop. Our code is published at https://github.com/YuanYunshuang/GevBEV.

Kun Li, George Vosselman, Michael Ying Yang

Interactive image segmentation aims to segment the target from the background with the manual guidance, which takes as input multimodal data such as images, clicks, scribbles, and bounding boxes. Recently, vision transformers have achieved a great success in several downstream visual tasks, and a few efforts have been made to bring this powerful architecture to interactive segmentation task. However, the previous works neglect the relations between two modalities and directly mock the way of processing purely visual information with self-attentions. In this paper, we propose a simple yet effective network for click-based interactive segmentation with cross-modality vision transformers. Cross-modality transformers exploits mutual information to better guide the learning process. The experiments on several benchmarks show that the proposed method achieves superior performance in comparison to the previous state-of-the-art models. The stability of our method in term of avoiding failure cases shows its potential to be a practical annotation tool. The code and pretrained models will be released under https://github.com/lik1996/iCMFormer.

Mengmeng Liu, Hao Cheng, Lin Chen et al.

Trajectory prediction for autonomous driving must continuously reason the motion stochasticity of road agents and comply with scene constraints. Existing methods typically rely on one-stage trajectory prediction models, which condition future trajectories on observed trajectories combined with fused scene information. However, they often struggle with complex scene constraints, such as those encountered at intersections. To this end, we present a novel method, called LAformer. It uses a temporally dense lane-aware estimation module to select only the top highly potential lane segments in an HD map, which effectively and continuously aligns motion dynamics with scene information, reducing the representation requirements for the subsequent attention-based decoder by filtering out irrelevant lane segments. Additionally, unlike one-stage prediction models, LAformer utilizes predictions from the first stage as anchor trajectories and adds a second-stage motion refinement module to further explore temporal consistency across the complete time horizon. Extensive experiments on Argoverse 1 and nuScenes demonstrate that LAformer achieves excellent performance for multimodal trajectory prediction.

Kun Li, George Vosselman, Michael Ying Yang

Visual question answering (VQA) is an important and challenging multimodal task in computer vision. Recently, a few efforts have been made to bring VQA task to aerial images, due to its potential real-world applications in disaster monitoring, urban planning, and digital earth product generation. However, not only the huge variation in the appearance, scale and orientation of the concepts in aerial images, but also the scarcity of the well-annotated datasets restricts the development of VQA in this domain. In this paper, we introduce a new dataset, HRVQA, which provides collected 53512 aerial images of 1024*1024 pixels and semi-automatically generated 1070240 QA pairs. To benchmark the understanding capability of VQA models for aerial images, we evaluate the relevant methods on HRVQA. Moreover, we propose a novel model, GFTransformer, with gated attention modules and a mutual fusion module. The experiments show that the proposed dataset is quite challenging, especially the specific attribute related questions. Our method achieves superior performance in comparison to the previous state-of-the-art approaches. The dataset and the source code will be released at https://hrvqa.nl/.

Yuren Cong, Martin Renqiang Min, Li Erran Li et al.

Despite the recent impressive breakthroughs in text-to-image generation, generative models have difficulty in capturing the data distribution of underrepresented attribute compositions while over-memorizing overrepresented attribute compositions, which raises public concerns about their robustness and fairness. To tackle this challenge, we propose ACTIG, an attribute-centric compositional text-to-image generation framework. We present an attribute-centric feature augmentation and a novel image-free training scheme, which greatly improves model's ability to generate images with underrepresented attributes. We further propose an attribute-centric contrastive loss to avoid overfitting to overrepresented attribute compositions. We validate our framework on the CelebA-HQ and CUB datasets. Extensive experiments show that the compositional generalization of ACTIG is outstanding, and our framework outperforms previous works in terms of image quality and text-image consistency.

Yao Wei, George Vosselman, Michael Ying Yang

3D building generation with low data acquisition costs, such as single image-to-3D, becomes increasingly important. However, most of the existing single image-to-3D building creation works are restricted to those images with specific viewing angles, hence they are difficult to scale to general-view images that commonly appear in practical cases. To fill this gap, we propose a novel 3D building shape generation method exploiting point cloud diffusion models with image conditioning schemes, which demonstrates flexibility to the input images. By cooperating two conditional diffusion models and introducing a regularization strategy during denoising process, our method is able to synthesize building roofs while maintaining the overall structures. We validate our framework on two newly built datasets and extensive experiments show that our method outperforms previous works in terms of building generation quality.

Yao Wei, George Vosselman, Michael Ying Yang

Generating a 3D point cloud from a single 2D image is of great importance for 3D scene understanding applications. To reconstruct the whole 3D shape of the object shown in the image, the existing deep learning based approaches use either explicit or implicit generative modeling of point clouds, which, however, suffer from limited quality. In this work, we aim to alleviate this issue by introducing a hybrid explicit-implicit generative modeling scheme, which inherits the flow-based explicit generative models for sampling point clouds with arbitrary resolutions while improving the detailed 3D structures of point clouds by leveraging the implicit generative adversarial networks (GANs). We evaluate on the large-scale synthetic dataset ShapeNet, with the experimental results demonstrating the superior performance of the proposed method. In addition, the generalization ability of our method is demonstrated by performing on cross-category synthetic images as well as by testing on real images from PASCAL3D+ dataset.

Yuren Cong, Jinhui Yi, Bodo Rosenhahn et al.

As a natural extension of the image synthesis task, video synthesis has attracted a lot of interest recently. Many image synthesis works utilize class labels or text as guidance. However, neither labels nor text can provide explicit temporal guidance, such as when an action starts or ends. To overcome this limitation, we introduce semantic video scene graphs as input for video synthesis, as they represent the spatial and temporal relationships between objects in the scene. Since video scene graphs are usually temporally discrete annotations, we propose a video scene graph (VSG) encoder that not only encodes the existing video scene graphs but also predicts the graph representations for unlabeled frames. The VSG encoder is pre-trained with different contrastive multi-modal losses. A semantic scene graph-to-video synthesis framework (SSGVS), based on the pre-trained VSG encoder, VQ-VAE, and auto-regressive Transformer, is proposed to synthesize a video given an initial scene image and a non-fixed number of semantic scene graphs. We evaluate SSGVS and other state-of-the-art video synthesis models on the Action Genome dataset and demonstrate the positive significance of video scene graphs in video synthesis. The source code will be released.

Yuren Cong, Wentong Liao, Bodo Rosenhahn et al.

Learning similarity between scene graphs and images aims to estimate a similarity score given a scene graph and an image. There is currently no research dedicated to this task, although it is critical for scene graph generation and downstream applications. Scene graph generation is conventionally evaluated by Recall$@K$ and mean Recall$@K$, which measure the ratio of predicted triplets that appear in the human-labeled triplet set. However, such triplet-oriented metrics fail to demonstrate the overall semantic difference between a scene graph and an image and are sensitive to annotation bias and noise. Using generated scene graphs in the downstream applications is therefore limited. To address this issue, for the first time, we propose a Scene graPh-imAge coNtrastive learning framework, SPAN, that can measure the similarity between scene graphs and images. Our novel framework consists of a graph Transformer and an image Transformer to align scene graphs and their corresponding images in the shared latent space. We introduce a novel graph serialization technique that transforms a scene graph into a sequence with structural encodings. Based on our framework, we propose R-Precision measuring image retrieval accuracy as a new evaluation metric for scene graph generation. We establish new benchmarks on the Visual Genome and Open Images datasets. Extensive experiments are conducted to verify the effectiveness of SPAN, which shows great potential as a scene graph encoder.

Jiuming Liu, Guangming Wang, Zhe Liu et al.

Although point cloud registration has achieved remarkable advances in object-level and indoor scenes, large-scale LiDAR registration methods has been rarely explored before. Challenges mainly arise from the huge point scale, complex point distribution, and numerous outliers within outdoor LiDAR scans. In addition, most existing registration works generally adopt a two-stage paradigm: They first find correspondences by extracting discriminative local descriptors and then leverage robust estimators (e.g. RANSAC) to filter outliers, which are highly dependent on well-designed descriptors and post-processing choices. To address these problems, we propose a novel end-to-end differential transformer network, termed RegFormer++, for large-scale point cloud alignment without requiring any further post-processing. Specifically, a hierarchical projection-aware 2D transformer with linear complexity is proposed to project raw LiDAR points onto a cylindrical surface and extract global point features, which can improve resilience to outliers due to long-range dependencies. Because we fill original 3D coordinates into 2D projected positions, our designed transformer can benefit from both high efficiency in 2D processing and accuracy from 3D geometric information. Furthermore, to effectively reduce wrong point matching, a Bijective Association Transformer (BAT) is designed, combining both cross attention and all-to-all point gathering. To improve training stability and robustness, a feature-transformed optimal transport module is also designed for regressing the final pose transformation. Extensive experiments on KITTI, NuScenes, and Argoverse datasets demonstrate that our model achieves state-of-the-art performance in terms of both accuracy and efficiency.

Biyuan Liu, Huaixin Chen, Kun Li et al.

Change detection plays a fundamental role in Earth observation for analyzing temporal iterations over time. However, recent studies have largely neglected the utilization of multimodal data that presents significant practical and technical advantages compared to single-modal approaches. This research focuses on leveraging {pre-event} digital surface model (DSM) data and {post-event} digital aerial images captured at different times for detecting change beyond 2D. We observe that the current change detection methods struggle with the multitask conflicts between semantic and height change detection tasks. To address this challenge, we propose an efficient Transformer-based network that learns shared representation between cross-dimensional inputs through cross-attention. {It adopts a consistency constraint to establish the multimodal relationship. Initially, pseudo-changes are derived by employing height change thresholding. Subsequently, the $L2$ distance between semantic and pseudo-changes within their overlapping regions is minimized. This explicitly endows the height change detection (regression task) and semantic change detection (classification task) with representation consistency.} A DSM-to-image multimodal dataset encompassing three cities in the Netherlands was constructed. It lays a new foundation for beyond-2D change detection from cross-dimensional inputs. Compared to five state-of-the-art change detection methods, our model demonstrates consistent multitask superiority in terms of semantic and height change detection. Furthermore, the consistency strategy can be seamlessly adapted to the other methods, yielding promising improvements.

Kun Li, George Vosselman, Michael Ying Yang

Visual Question Answering (VQA) is a challenging task of predicting the answer to a question about the content of an image. Prior works directly evaluate the answering models by simply calculating the accuracy of predicted answers. However, the inner reasoning behind the predictions is disregarded in such a "black box" system, and we cannot ascertain the trustworthiness of the predictions. Even more concerning, in some cases, these models predict correct answers despite focusing on irrelevant visual regions or textual tokens. To develop an explainable and trustworthy answering system, we propose a novel model termed MRVQA (Multimodal Rationales for VQA), which provides visual and textual rationales to support its predicted answers. To measure the quality of generated rationales, a new metric vtS (visual-textual Similarity) score is introduced from both visual and textual perspectives. Considering the extra annotations distinct from standard VQA, MRVQA is trained and evaluated using samples synthesized from some existing datasets. Extensive experiments across three EVQA datasets demonstrate that MRVQA achieves new state-of-the-art results through additional rationale generation, enhancing the trustworthiness of the explainable VQA model. The code and the synthesized dataset are released under https://github.com/lik1996/MRVQA2025.

Yuren Cong, Wentong Liao, Hanno Ackermann et al.

Dynamic scene graph generation aims at generating a scene graph of the given video. Compared to the task of scene graph generation from images, it is more challenging because of the dynamic relationships between objects and the temporal dependencies between frames allowing for a richer semantic interpretation. In this paper, we propose Spatial-temporal Transformer (STTran), a neural network that consists of two core modules: (1) a spatial encoder that takes an input frame to extract spatial context and reason about the visual relationships within a frame, and (2) a temporal decoder which takes the output of the spatial encoder as input in order to capture the temporal dependencies between frames and infer the dynamic relationships. Furthermore, STTran is flexible to take varying lengths of videos as input without clipping, which is especially important for long videos. Our method is validated on the benchmark dataset Action Genome (AG). The experimental results demonstrate the superior performance of our method in terms of dynamic scene graphs. Moreover, a set of ablative studies is conducted and the effect of each proposed module is justified. Code available at: https://github.com/yrcong/STTran.

Hao Cheng, Wentong Liao, Xuejiao Tang et al.

To accurately predict future positions of different agents in traffic scenarios is crucial for safely deploying intelligent autonomous systems in the real-world environment. However, it remains a challenge due to the behavior of a target agent being affected by other agents dynamically and there being more than one socially possible paths the agent could take. In this paper, we propose a novel framework, named Dynamic Context Encoder Network (DCENet). In our framework, first, the spatial context between agents is explored by using self-attention architectures. Then, the two-stream encoders are trained to learn temporal context between steps by taking the respective observed trajectories and the extracted dynamic spatial context as input. The spatial-temporal context is encoded into a latent space using a Conditional Variational Auto-Encoder (CVAE) module. Finally, a set of future trajectories for each agent is predicted conditioned on the learned spatial-temporal context by sampling from the latent space, repeatedly. DCENet is evaluated on one of the most popular challenging benchmarks for trajectory forecasting Trajnet and reports a new state-of-the-art performance. It also demonstrates superior performance evaluated on the benchmark inD for mixed traffic at intersections. A series of ablation studies is conducted to validate the effectiveness of each proposed module. Our code is available at https://github.com/wtliao/DCENet.

Mengmeng Liu, Jiuming Liu, Yunpeng Zhang et al.

Remarkable advances in recent 2D image and 3D shape generation have induced a significant focus on dynamic 4D content generation. However, previous 4D generation methods commonly struggle to maintain spatial-temporal consistency and adapt poorly to rapid temporal variations, due to the lack of effective spatial-temporal modeling. To address these problems, we propose a novel 4D generation network called 4DSTR, which modulates generative 4D Gaussian Splatting with spatial-temporal rectification. Specifically, temporal correlation across generated 4D sequences is designed to rectify deformable scales and rotations and guarantee temporal consistency. Furthermore, an adaptive spatial densification and pruning strategy is proposed to address significant temporal variations by dynamically adding or deleting Gaussian points with the awareness of their pre-frame movements. Extensive experiments demonstrate that our 4DSTR achieves state-of-the-art performance in video-to-4D generation, excelling in reconstruction quality, spatial-temporal consistency, and adaptation to rapid temporal movements.

Kun Li, Michael Ying Yang, Sami Sebastian Brandt

Audio--Visual Question Answering (AVQA) is a challenging multimodal task that requires jointly reasoning over audio, visual, and textual information in a given video to answer natural language questions. Inspired by recent advances in Video QA, many existing AVQA approaches primarily focus on visual information processing, leveraging pre-trained models to extract object-level and motion-level representations. However, in those methods, the audio input is primarily treated as complementary to video analysis, and the textual question information contributes minimally to audio--visual understanding, as it is typically integrated only in the final stages of reasoning. To address these limitations, we propose a novel Query-guided Spatial--Temporal--Frequency (QSTar) interaction method, which effectively incorporates question-guided clues and exploits the distinctive frequency-domain characteristics of audio signals, alongside spatial and temporal perception, to enhance audio--visual understanding. Furthermore, we introduce a Query Context Reasoning (QCR) block inspired by prompting, which guides the model to focus more precisely on semantically relevant audio and visual features. Extensive experiments conducted on several AVQA benchmarks demonstrate the effectiveness of our proposed method, achieving significant performance improvements over existing Audio QA, Visual QA, Video QA, and AVQA approaches. The code and pretrained models will be released after publication.

Yi Yang, Yiming Xu, Timo Kaiser et al.

In this report, we present our solution to the MOT25-Spatiotemporal Action Grounding (MOT25-StAG) Challenge. The aim of this challenge is to accurately localize and track multiple objects that match specific and free-form language queries, using video data of complex real-world scenes as input. We model the underlying task as a video retrieval problem and present a two-stage, zero-shot approach, combining the advantages of the SOTA tracking model FastTracker and Multi-modal Large Language Model LLaVA-Video. On the MOT25-StAG test set, our method achieves m-HIoU and HOTA scores of 20.68 and 10.73 respectively, which won second place in the challenge.

Sophie Crommelinck, Mila Koeva, Michael Ying Yang et al. · mila

The extraction of object outlines has been a research topic during the last decades. In spite of advances in photogrammetry, remote sensing and computer vision, this task remains challenging due to object and data complexity. The development of object extraction approaches is promoted through publically available benchmark datasets and evaluation frameworks. Many aspects of performance evaluation have already been studied. This study collects the best practices from literature, puts the various aspects in one evaluation framework, and demonstrates its usefulness to a case study on mapping object outlines. The evaluation framework includes five dimensions: the robustness to changes in resolution, input, location, parameters, and application. Examples for investigating these dimensions are provided, as well as accuracy measures for their qualitative analysis. The measures consist of time efficiency and a procedure for line-based accuracy assessment regarding quantitative completeness and spatial correctness. The delineation approach to which the evaluation framework is applied, was previously introduced and is substantially improved in this study.

Sophie Crommelinck, Michael Ying Yang, Mila Koeva et al. · mila

Unmanned aerial vehicles (UAV) are evolving as an alternative tool to acquire land tenure data. UAVs can capture geospatial data at high quality and resolution in a cost-effective, transparent and flexible manner, from which visible land parcel boundaries, i.e., cadastral boundaries are delineable. This delineation is to no extent automated, even though physical objects automatically retrievable through image analysis methods mark a large portion of cadastral boundaries. This study proposes (i) a workflow that automatically extracts candidate cadastral boundaries from UAV orthoimages and (ii) a tool for their semi-automatic processing to delineate final cadastral boundaries. The workflow consists of two state-of-the-art computer vision methods, namely gPb contour detection and SLIC superpixels that are transferred to remote sensing in this study. The tool combines the two methods, allows a semi-automatic final delineation and is implemented as a publicly available QGIS plugin. The approach does not yet aim to provide a comparable alternative to manual cadastral mapping procedures. However, the methodological development of the tool towards this goal is developed in this paper. A study with 13 volunteers investigates the design and implementation of the approach and gathers initial qualitative as well as quantitate results. The study revealed points for improvement, which are prioritized based on the study results and which will be addressed in future work.

Florian Kluger, Eric Brachmann, Michael Ying Yang et al.

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.

Kun Li, George Vosselman, Michael Ying Yang

The goal of referring remote sensing image segmentation (RRSIS) is to extract specific pixel-level regions within an aerial image via a natural language expression. Recent advancements, particularly Transformer-based fusion designs, have demonstrated remarkable progress in this domain. However, existing methods primarily focus on refining visual features using language-aware guidance during the cross-modal fusion stage, neglecting the complementary vision-to-language flow. This limitation often leads to irrelevant or suboptimal representations. In addition, the diverse spatial scales of ground objects in aerial images pose significant challenges to the visual perception capabilities of existing models when conditioned on textual inputs. In this paper, we propose an innovative framework called Scale-wise Bidirectional Alignment Network (SBANet) to address these challenges for RRSIS. Specifically, we design a Bidirectional Alignment Module (BAM) with learnable query tokens to selectively and effectively represent visual and linguistic features, emphasizing regions associated with key tokens. BAM is further enhanced with a dynamic feature selection block, designed to provide both macro- and micro-level visual features, preserving global context and local details to facilitate more effective cross-modal interaction. Furthermore, SBANet incorporates a text-conditioned channel and spatial aggregator to bridge the gap between the encoder and decoder, enhancing cross-scale information exchange in complex aerial scenarios. Extensive experiments demonstrate that our proposed method achieves superior performance in comparison to previous state-of-the-art methods on the RRSIS-D and RefSegRS datasets, both quantitatively and qualitatively. The code will be released after publication.

Mengmeng Liu, Diankun Zhang, Jiuming Liu et al.

Generalization is a central challenge in autonomous driving, as real-world deployment requires robust performance under unseen scenarios, sensor domains, and environmental conditions. Recent world-model-based planning methods have shown strong capabilities in scene understanding and multi-modal future prediction, yet their generalization across datasets and sensor configurations remains limited. In addition, their loosely coupled planning paradigm often leads to poor video-trajectory consistency during visual imagination. To overcome these limitations, we propose DriveVA, a novel autonomous driving world model that jointly decodes future visual forecasts and action sequences in a shared latent generative process. DriveVA inherits rich priors on motion dynamics and physical plausibility from well-pretrained large-scale video generation models to capture continuous spatiotemporal evolution and causal interaction patterns. To this end, DriveVA employs a DiT-based decoder to jointly predict future action sequences (trajectories) and videos, enabling tighter alignment between planning and scene evolution. We also introduce a video continuation strategy to strengthen long-duration rollout consistency. DriveVA achieves an impressive closed-loop performance of 90.9 PDM score on the challenge NAVSIM. Extensive experiments also demonstrate the zero-shot capability and cross-domain generalization of DriveVA, which reduces average L2 error and collision rate by 78.9% and 83.3% on nuScenes and 52.5% and 52.4% on the Bench2drive built on CARLA v2 compared with the state-of-the-art world-model-based planner.

Mengmeng Liu, Michael Ying Yang, Jiuming Liu et al.

Visual-LiDAR odometry is a critical component for autonomous system localization, yet achieving high accuracy and strong robustness remains a challenge. Traditional approaches commonly struggle with sensor misalignment, fail to fully leverage temporal information, and require extensive manual tuning to handle diverse sensor configurations. To address these problems, we introduce DVLO4D, a novel visual-LiDAR odometry framework that leverages sparse spatial-temporal fusion to enhance accuracy and robustness. Our approach proposes three key innovations: (1) Sparse Query Fusion, which utilizes sparse LiDAR queries for effective multi-modal data fusion; (2) a Temporal Interaction and Update module that integrates temporally-predicted positions with current frame data, providing better initialization values for pose estimation and enhancing model's robustness against accumulative errors; and (3) a Temporal Clip Training strategy combined with a Collective Average Loss mechanism that aggregates losses across multiple frames, enabling global optimization and reducing the scale drift over long sequences. Extensive experiments on the KITTI and Argoverse Odometry dataset demonstrate the superiority of our proposed DVLO4D, which achieves state-of-the-art performance in terms of both pose accuracy and robustness. Additionally, our method has high efficiency, with an inference time of 82 ms, possessing the potential for the real-time deployment.

Yao Wei, Matteo Toso, Pietro Morerio et al.

This paper presents a novel generative approach that outputs 3D indoor environments solely from a textual description of the scene. Current methods often treat scene synthesis as a mere layout prediction task, leading to rooms with overlapping objects or overly structured scenes, with limited consideration of the practical usability of the generated environment. Instead, our approach is based on a simple, but effective principle: we condition scene synthesis to generate rooms that are usable by humans. This principle is implemented by synthesizing 3D humans that interact with the objects composing the scene. If this human-centric scene generation is viable, the room layout is functional and it leads to a more coherent 3D structure. To this end, we propose a novel method for functional 3D scene synthesis, which consists of reasoning, 3D assembling and optimization. We regard text guided 3D synthesis as a reasoning process by generating a scene graph via a graph diffusion network. Considering object functional co-occurrence, a new strategy is designed to better accommodate human-object interaction and avoidance, achieving human-aware 3D scene optimization. We conduct both qualitative and quantitative experiments to validate the effectiveness of our method in generating coherent 3D scene synthesis results.

Yi Yang, Yuren Cong, Hao Cheng et al.

Dynamic scene graph generation extends scene graph generation from images to videos by modeling entity relationships and their temporal evolution. However, existing methods either generate scene graphs from observed frames without explicitly modeling temporal dynamics, or predict only relationships while assuming static entity labels and locations. These limitations hinder effective extrapolation of both entity and relationship dynamics, restricting video scene understanding. We propose Forecasting Dynamic Scene Graphs (FDSG), a novel framework that predicts future entity labels, bounding boxes, and relationships, for unobserved frames, while also generating scene graphs for observed frames. Our scene graph forecast module leverages query decomposition and neural stochastic differential equations to model entity and relationship dynamics. A temporal aggregation module further refines predictions by integrating forecasted and observed information via cross-attention. To benchmark FDSG, we introduce Scene Graph Forecasting, a new task for full future scene graph prediction. Experiments on Action Genome show that FDSG outperforms state-of-the-art methods on dynamic scene graph generation, scene graph anticipation, and scene graph forecasting. Codes will be released upon publication.

Kun Li, Hao Cheng, George Vosselman et al.

Interactive image segmentation enables users to interact minimally with a machine, facilitating the gradual refinement of the segmentation mask for a target of interest. Previous studies have demonstrated impressive performance in extracting a single target mask through interactive segmentation. However, the information cues of previously interacted objects have been overlooked in the existing methods, which can be further explored to speed up interactive segmentation for multiple targets in the same category. To this end, we introduce novel interactive segmentation frameworks for both a single object and multiple objects in the same category. Specifically, our model leverages transformer backbones to extract interaction-focused visual features from the image and the interactions to obtain a satisfactory mask of a target as an exemplar. For multiple objects, we propose an exemplar-informed module to enhance the learning of similarities among the objects of the target category. To combine attended features from different modules, we incorporate cross-attention blocks followed by a feature fusion module. Experiments conducted on mainstream benchmarks demonstrate that our models achieve superior performance compared to previous methods. Particularly, our model reduces users' labor by around 15\%, requiring two fewer clicks to achieve target IoUs 85\% and 90\%. The results highlight our models' potential as a flexible and practical annotation tool. The source code will be released after publication.

Yao Wei, Martin Renqiang Min, George Vosselman et al.

Compositional 3D scene synthesis has diverse applications across a spectrum of industries such as robotics, films, and video games, as it closely mirrors the complexity of real-world multi-object environments. Conventional works typically employ shape retrieval based frameworks which naturally suffer from limited shape diversity. Recent progresses have been made in object shape generation with generative models such as diffusion models, which increases the shape fidelity. However, these approaches separately treat 3D shape generation and layout generation. The synthesized scenes are usually hampered by layout collision, which suggests that the scene-level fidelity is still under-explored. In this paper, we aim at generating realistic and reasonable 3D indoor scenes from scene graph. To enrich the priors of the given scene graph inputs, large language model is utilized to aggregate the global-wise features with local node-wise and edge-wise features. With a unified graph encoder, graph features are extracted to guide joint layout-shape generation. Additional regularization is introduced to explicitly constrain the produced 3D layouts. Benchmarked on the SG-FRONT dataset, our method achieves better 3D scene synthesis, especially in terms of scene-level fidelity. The source code will be released after publication.

Yuren Cong, Michael Ying Yang, Bodo Rosenhahn

Different objects in the same scene are more or less related to each other, but only a limited number of these relationships are noteworthy. Inspired by DETR, which excels in object detection, we view scene graph generation as a set prediction problem and propose an end-to-end scene graph generation model RelTR which has an encoder-decoder architecture. The encoder reasons about the visual feature context while the decoder infers a fixed-size set of triplets subject-predicate-object using different types of attention mechanisms with coupled subject and object queries. We design a set prediction loss performing the matching between the ground truth and predicted triplets for the end-to-end training. In contrast to most existing scene graph generation methods, RelTR is a one-stage method that predicts a set of relationships directly only using visual appearance without combining entities and labeling all possible predicates. Extensive experiments on the Visual Genome and Open Images V6 datasets demonstrate the superior performance and fast inference of our model.

Gui-Song Xia, Jian Ding, Ming Qian et al.

This report summarizes the results of Learning to Understand Aerial Images (LUAI) 2021 challenge held on ICCV 2021, which focuses on object detection and semantic segmentation in aerial images. Using DOTA-v2.0 and GID-15 datasets, this challenge proposes three tasks for oriented object detection, horizontal object detection, and semantic segmentation of common categories in aerial images. This challenge received a total of 146 registrations on the three tasks. Through the challenge, we hope to draw attention from a wide range of communities and call for more efforts on the problems of learning to understand aerial images.

Sen He, Wentong Liao, Michael Ying Yang et al.

A lifespan face synthesis (LFS) model aims to generate a set of photo-realistic face images of a person's whole life, given only one snapshot as reference. The generated face image given a target age code is expected to be age-sensitive reflected by bio-plausible transformations of shape and texture, while being identity preserving. This is extremely challenging because the shape and texture characteristics of a face undergo separate and highly nonlinear transformations w.r.t. age. Most recent LFS models are based on generative adversarial networks (GANs) whereby age code conditional transformations are applied to a latent face representation. They benefit greatly from the recent advancements of GANs. However, without explicitly disentangling their latent representations into the texture, shape and identity factors, they are fundamentally limited in modeling the nonlinear age-related transformation on texture and shape whilst preserving identity. In this work, a novel LFS model is proposed to disentangle the key face characteristics including shape, texture and identity so that the unique shape and texture age transformations can be modeled effectively. This is achieved by extracting shape, texture and identity features separately from an encoder. Critically, two transformation modules, one conditional convolution based and the other channel attention based, are designed for modeling the nonlinear shape and texture feature transformations respectively. This is to accommodate their rather distinct aging processes and ensure that our synthesized images are both age-sensitive and identity preserving. Extensive experiments show that our LFS model is clearly superior to the state-of-the-art alternatives. Codes and demo are available on our project website: \url{https://senhe.github.io/projects/iccv_2021_lifespan_face}.

Florian Kluger, Hanno Ackermann, Eric Brachmann et al.

Humans perceive and construct the surrounding world as an arrangement of simple parametric models. In particular, man-made environments commonly consist of volumetric primitives such as cuboids or cylinders. Inferring these primitives is an important step to attain high-level, abstract scene descriptions. Previous approaches directly estimate shape parameters from a 2D or 3D input, and are only able to reproduce simple objects, yet unable to accurately parse more complex 3D scenes. In contrast, we propose a robust estimator for primitive fitting, which can meaningfully abstract real-world environments using cuboids. A RANSAC estimator guided by a neural network fits these primitives to 3D features, such as a depth map. We condition the network on previously detected parts of the scene, thus parsing it one-by-one. To obtain 3D features from a single RGB image, we additionally optimise a feature extraction CNN in an end-to-end manner. However, naively minimising point-to-primitive distances leads to large or spurious cuboids occluding parts of the scene behind. We thus propose an occlusion-aware distance metric correctly handling opaque scenes. The proposed algorithm does not require labour-intensive labels, such as cuboid annotations, for training. Results on the challenging NYU Depth v2 dataset demonstrate that the proposed algorithm successfully abstracts cluttered real-world 3D scene layouts.

Kai Hu, Wentong Liao, Michael Ying Yang et al.

Text-to-image synthesis (T2I) aims to generate photo-realistic images which are semantically consistent with the text descriptions. Existing methods are usually built upon conditional generative adversarial networks (GANs) and initialize an image from noise with sentence embedding, and then refine the features with fine-grained word embedding iteratively. A close inspection of their generated images reveals a major limitation: even though the generated image holistically matches the description, individual image regions or parts of somethings are often not recognizable or consistent with words in the sentence, e.g. "a white crown". To address this problem, we propose a novel framework Semantic-Spatial Aware GAN for synthesizing images from input text. Concretely, we introduce a simple and effective Semantic-Spatial Aware block, which (1) learns semantic-adaptive transformation conditioned on text to effectively fuse text features and image features, and (2) learns a semantic mask in a weakly-supervised way that depends on the current text-image fusion process in order to guide the transformation spatially. Experiments on the challenging COCO and CUB bird datasets demonstrate the advantage of our method over the recent state-of-the-art approaches, regarding both visual fidelity and alignment with input text description.

Sen He, Wentong Liao, Michael Ying Yang et al.

A layout to image (L2I) generation model aims to generate a complicated image containing multiple objects (things) against natural background (stuff), conditioned on a given layout. Built upon the recent advances in generative adversarial networks (GANs), existing L2I models have made great progress. However, a close inspection of their generated images reveals two major limitations: (1) the object-to-object as well as object-to-stuff relations are often broken and (2) each object's appearance is typically distorted lacking the key defining characteristics associated with the object class. We argue that these are caused by the lack of context-aware object and stuff feature encoding in their generators, and location-sensitive appearance representation in their discriminators. To address these limitations, two new modules are proposed in this work. First, a context-aware feature transformation module is introduced in the generator to ensure that the generated feature encoding of either object or stuff is aware of other co-existing objects/stuff in the scene. Second, instead of feeding location-insensitive image features to the discriminator, we use the Gram matrix computed from the feature maps of the generated object images to preserve location-sensitive information, resulting in much enhanced object appearance. Extensive experiments show that the proposed method achieves state-of-the-art performance on the COCO-Thing-Stuff and Visual Genome benchmarks.

Ye Lyu, George Vosselman, Gui-Song Xia et al.

Semantic segmentation for aerial platforms has been one of the fundamental scene understanding task for the earth observation. Most of the semantic segmentation research focused on scenes captured in nadir view, in which objects have relatively smaller scale variation compared with scenes captured in oblique view. The huge scale variation of objects in oblique images limits the performance of deep neural networks (DNN) that process images in a single scale fashion. In order to tackle the scale variation issue, in this paper, we propose the novel bidirectional multi-scale attention networks, which fuse features from multiple scales bidirectionally for more adaptive and effective feature extraction. The experiments are conducted on the UAVid2020 dataset and have shown the effectiveness of our method. Our model achieved the state-of-the-art (SOTA) result with a mean intersection over union (mIoU) score of 70.80%.

Logambal Madhuanand, Francesco Nex, Michael Ying Yang

UAVs have become an essential photogrammetric measurement as they are affordable, easily accessible and versatile. Aerial images captured from UAVs have applications in small and large scale texture mapping, 3D modelling, object detection tasks, DTM and DSM generation etc. Photogrammetric techniques are routinely used for 3D reconstruction from UAV images where multiple images of the same scene are acquired. Developments in computer vision and deep learning techniques have made Single Image Depth Estimation (SIDE) a field of intense research. Using SIDE techniques on UAV images can overcome the need for multiple images for 3D reconstruction. This paper aims to estimate depth from a single UAV aerial image using deep learning. We follow a self-supervised learning approach, Self-Supervised Monocular Depth Estimation (SMDE), which does not need ground truth depth or any extra information other than images for learning to estimate depth. Monocular video frames are used for training the deep learning model which learns depth and pose information jointly through two different networks, one each for depth and pose. The predicted depth and pose are used to reconstruct one image from the viewpoint of another image utilising the temporal information from videos. We propose a novel architecture with two 2D CNN encoders and a 3D CNN decoder for extracting information from consecutive temporal frames. A contrastive loss term is introduced for improving the quality of image generation. Our experiments are carried out on the public UAVid video dataset. The experimental results demonstrate that our model outperforms the state-of-the-art methods in estimating the depths.

Yaping Lin, George Vosselman, Yanpeng Cao et al.

Interpretation of Airborne Laser Scanning (ALS) point clouds is a critical procedure for producing various geo-information products like 3D city models, digital terrain models and land use maps. In this paper, we present a local and global encoder network (LGENet) for semantic segmentation of ALS point clouds. Adapting the KPConv network, we first extract features by both 2D and 3D point convolutions to allow the network to learn more representative local geometry. Then global encoders are used in the network to exploit contextual information at the object and point level. We design a segment-based Edge Conditioned Convolution to encode the global context between segments. We apply a spatial-channel attention module at the end of the network, which not only captures the global interdependencies between points but also models interactions between channels. We evaluate our method on two ALS datasets namely, the ISPRS benchmark dataset and DCF2019 dataset. For the ISPRS benchmark dataset, our model achieves state-of-the-art results with an overall accuracy of 0.845 and an average F1 score of 0.737. With regards to the DFC2019 dataset, our proposed network achieves an overall accuracy of 0.984 and an average F1 score of 0.834.

Fan Wang, Jiangxin Yang, Yanlong Cao et al.

Image Super-Resolution (SR) provides a promising technique to enhance the image quality of low-resolution optical sensors, facilitating better-performing target detection and autonomous navigation in a wide range of robotics applications. It is noted that the state-of-the-art SR methods are typically trained and tested using single-channel inputs, neglecting the fact that the cost of capturing high-resolution images in different spectral domains varies significantly. In this paper, we attempt to leverage complementary information from a low-cost channel (visible/depth) to boost image quality of an expensive channel (thermal) using fewer parameters. To this end, we first present an effective method to virtually generate pixel-wise aligned visible and thermal images based on real-time 3D reconstruction of multi-modal data captured at various viewpoints. Then, we design a feature-level multispectral fusion residual network model to perform high-accuracy SR of thermal images by adaptively integrating co-occurrence features presented in multispectral images. Experimental results demonstrate that this new approach can effectively alleviate the ill-posed inverse problem of image SR by taking into account complementary information from an additional low-cost channel, significantly outperforming state-of-the-art SR approaches in terms of both accuracy and efficiency.

Michael Ying Yang, Saumya Kumaar, Ye Lyu et al.

With the increasing demand of autonomous systems, pixelwise semantic segmentation for visual scene understanding needs to be not only accurate but also efficient for potential real-time applications. In this paper, we propose Context Aggregation Network, a dual branch convolutional neural network, with significantly lower computational costs as compared to the state-of-the-art, while maintaining a competitive prediction accuracy. Building upon the existing dual branch architectures for high-speed semantic segmentation, we design a cheap high resolution branch for effective spatial detailing and a context branch with light-weight versions of global aggregation and local distribution blocks, potent to capture both long-range and local contextual dependencies required for accurate semantic segmentation, with low computational overheads. We evaluate our method on two semantic segmentation datasets, namely Cityscapes dataset and UAVid dataset. For Cityscapes test set, our model achieves state-of-the-art results with mIOU of 75.9%, at 76 FPS on an NVIDIA RTX 2080Ti and 8 FPS on a Jetson Xavier NX. With regards to UAVid dataset, our proposed network achieves mIOU score of 63.5% with high execution speed (15 FPS).

Yang Long, Gui-Song Xia, Shengyang Li et al.

The past years have witnessed great progress on remote sensing (RS) image interpretation and its wide applications. With RS images becoming more accessible than ever before, there is an increasing demand for the automatic interpretation of these images. In this context, the benchmark datasets serve as essential prerequisites for developing and testing intelligent interpretation algorithms. After reviewing existing benchmark datasets in the research community of RS image interpretation, this article discusses the problem of how to efficiently prepare a suitable benchmark dataset for RS image interpretation. Specifically, we first analyze the current challenges of developing intelligent algorithms for RS image interpretation with bibliometric investigations. We then present the general guidances on creating benchmark datasets in efficient manners. Following the presented guidances, we also provide an example on building RS image dataset, i.e., Million-AID, a new large-scale benchmark dataset containing a million instances for RS image scene classification. Several challenges and perspectives in RS image annotation are finally discussed to facilitate the research in benchmark dataset construction. We do hope this paper will provide the RS community an overall perspective on constructing large-scale and practical image datasets for further research, especially data-driven ones.

Hao Cheng, Wentong Liao, Michael Ying Yang et al.

Trajectory prediction is critical for applications of planning safe future movements and remains challenging even for the next few seconds in urban mixed traffic. How an agent moves is affected by the various behaviors of its neighboring agents in different environments. To predict movements, we propose an end-to-end generative model named Attentive Maps Encoder Network (AMENet) that encodes the agent's motion and interaction information for accurate and realistic multi-path trajectory prediction. A conditional variational auto-encoder module is trained to learn the latent space of possible future paths based on attentive dynamic maps for interaction modeling and then is used to predict multiple plausible future trajectories conditioned on the observed past trajectories. The efficacy of AMENet is validated using two public trajectory prediction benchmarks Trajnet and InD.

Wentong Liao, Xiang Chen, Jingfeng Yang et al.

State-of-the-art object detection approaches such as Fast/Faster R-CNN, SSD, or YOLO have difficulties detecting dense, small targets with arbitrary orientation in large aerial images. The main reason is that using interpolation to align RoI features can result in a lack of accuracy or even loss of location information. We present the Local-aware Region Convolutional Neural Network (LR-CNN), a novel two-stage approach for vehicle detection in aerial imagery. We enhance translation invariance to detect dense vehicles and address the boundary quantization issue amongst dense vehicles by aggregating the high-precision RoIs' features. Moreover, we resample high-level semantic pooled features, making them regain location information from the features of a shallower convolutional block. This strengthens the local feature invariance for the resampled features and enables detecting vehicles in an arbitrary orientation. The local feature invariance enhances the learning ability of the focal loss function, and the focal loss further helps to focus on the hard examples. Taken together, our method better addresses the challenges of aerial imagery. We evaluate our approach on several challenging datasets (VEDAI, DOTA), demonstrating a significant improvement over state-of-the-art methods. We demonstrate the good generalization ability of our approach on the DLR 3K dataset.

Ye Lyu, Michael Ying Yang, George Vosselman et al.

Video object detection targets to simultaneously localize the bounding boxes of the objects and identify their classes in a given video. One challenge for video object detection is to consistently detect all objects across the whole video. As the appearance of objects may deteriorate in some frames, features or detections from the other frames are commonly used to enhance the prediction. In this paper, we propose a Plug & Play scale-adaptive convolutional regression tracker for the video object detection task, which could be easily and compatibly implanted into the current state-of-the-art detection networks. As the tracker reuses the features from the detector, it is a very light-weighted increment to the detection network. The whole network performs at the speed close to a standard object detector. With our new video object detection pipeline design, image object detectors can be easily turned into efficient video object detectors without modifying any parameters. The performance is evaluated on the large-scale ImageNet VID dataset. Our Plug & Play design improves mAP score for the image detector by around 5% with only little speed drop.

Hao Cheng, Wentong Liao, Michael Ying Yang et al.

Trajectory prediction in urban mixed-traffic zones (a.k.a. shared spaces) is critical for many intelligent transportation systems, such as intent detection for autonomous driving. However, there are many challenges to predict the trajectories of heterogeneous road agents (pedestrians, cyclists and vehicles) at a microscopical level. For example, an agent might be able to choose multiple plausible paths in complex interactions with other agents in varying environments. To this end, we propose an approach named Multi-Context Encoder Network (MCENET) that is trained by encoding both past and future scene context, interaction context and motion information to capture the patterns and variations of the future trajectories using a set of stochastic latent variables. In inference time, we combine the past context and motion information of the target agent with samplings of the latent variables to predict multiple realistic trajectories in the future. Through experiments on several datasets of varying scenes, our method outperforms some of the recent state-of-the-art methods for mixed traffic trajectory prediction by a large margin and more robust in a very challenging environment. The impact of each context is justified via ablation studies.

Cong Yuren, Hanno Ackermann, Wentong Liao et al.

Semantic image understanding is a challenging topic in computer vision. It requires to detect all objects in an image, but also to identify all the relations between them. Detected objects, their labels and the discovered relations can be used to construct a scene graph which provides an abstract semantic interpretation of an image. In previous works, relations were identified by solving an assignment problem formulated as Mixed-Integer Linear Programs. In this work, we interpret that formulation as Ordinary Differential Equation (ODE). The proposed architecture performs scene graph inference by solving a neural variant of an ODE by end-to-end learning. It achieves state-of-the-art results on all three benchmark tasks: scene graph generation (SGGen), classification (SGCls) and visual relationship detection (PredCls) on Visual Genome benchmark.

Florian Kluger, Eric Brachmann, Hanno Ackermann et al.

We present a robust estimator for fitting multiple parametric models of the same form to noisy measurements. Applications include finding multiple vanishing points in man-made scenes, fitting planes to architectural imagery, or estimating multiple rigid motions within the same sequence. In contrast to previous works, which resorted to hand-crafted search strategies for multiple model detection, we learn the search strategy from data. A neural network conditioned on previously detected models guides a RANSAC estimator to different subsets of all measurements, thereby finding model instances one after another. We train our method supervised as well as self-supervised. For supervised training of the search strategy, we contribute a new dataset for vanishing point estimation. Leveraging this dataset, the proposed algorithm is superior with respect to other robust estimators as well as to designated vanishing point estimation algorithms. For self-supervised learning of the search, we evaluate the proposed algorithm on multi-homography estimation and demonstrate an accuracy that is superior to state-of-the-art methods.

Du Chen, Zewei He, Yanpeng Cao et al.

Recently, Convolutional Neural Networks (CNNs) have been successfully adopted to solve the ill-posed single image super-resolution (SISR) problem. A commonly used strategy to boost the performance of CNN-based SISR models is deploying very deep networks, which inevitably incurs many obvious drawbacks (e.g., a large number of network parameters, heavy computational loads, and difficult model training). In this paper, we aim to build more accurate and faster SISR models via developing better-performing feature extraction and fusion techniques. Firstly, we proposed a novel Orientation-Aware feature extraction and fusion Module (OAM), which contains a mixture of 1D and 2D convolutional kernels (i.e., 5 x 1, 1 x 5, and 3 x 3) for extracting orientation-aware features. Secondly, we adopt the channel attention mechanism as an effective technique to adaptively fuse features extracted in different directions and in hierarchically stacked convolutional stages. Based on these two important improvements, we present a compact but powerful CNN-based model for high-quality SISR via Channel Attention-based fusion of Orientation-Aware features (SISR-CA-OA). Extensive experimental results verify the superiority of the proposed SISR-CA-OA model, performing favorably against the state-of-the-art SISR models in terms of both restoration accuracy and computational efficiency. The source codes will be made publicly available.

Ye Lyu, George Vosselman, Gui-Song Xia et al.

In recent years, the task of segmenting foreground objects from background in a video, i.e. video object segmentation (VOS), has received considerable attention. In this paper, we propose a single end-to-end trainable deep neural network, convolutional gated recurrent Mask-RCNN, for tackling the semi-supervised VOS task. We take advantage of both the instance segmentation network (Mask-RCNN) and the visual memory module (Conv-GRU) to tackle the VOS task. The instance segmentation network predicts masks for instances, while the visual memory module learns to selectively propagate information for multiple instances simultaneously, which handles the appearance change, the variation of scale and pose and the occlusions between objects. After offline and online training under purely instance segmentation losses, our approach is able to achieve satisfactory results without any post-processing or synthetic video data augmentation. Experimental results on DAVIS 2016 dataset and DAVIS 2017 dataset have demonstrated the effectiveness of our method for video object segmentation task.

Florian Kluger, Hanno Ackermann, Michael Ying Yang et al.

The horizon line is an important geometric feature for many image processing and scene understanding tasks in computer vision. For instance, in navigation of autonomous vehicles or driver assistance, it can be used to improve 3D reconstruction as well as for semantic interpretation of dynamic environments. While both algorithms and datasets exist for single images, the problem of horizon line estimation from video sequences has not gained attention. In this paper, we show how convolutional neural networks are able to utilise the temporal consistency imposed by video sequences in order to increase the accuracy and reduce the variance of horizon line estimates. A novel CNN architecture with an improved residual convolutional LSTM is presented for temporally consistent horizon line estimation. We propose an adaptive loss function that ensures stable training as well as accurate results. Furthermore, we introduce an extension of the KITTI dataset which contains precise horizon line labels for 43699 images across 72 video sequences. A comprehensive evaluation shows that the proposed approach consistently achieves superior performance compared with existing methods.

Dayan Guan, Xing Luo, Yanpeng Cao et al.

Multimodal information (e.g., visible and thermal) can generate robust pedestrian detections to facilitate around-the-clock computer vision applications, such as autonomous driving and video surveillance. However, it still remains a crucial challenge to train a reliable detector working well in different multispectral pedestrian datasets without manual annotations. In this paper, we propose a novel unsupervised domain adaptation framework for multispectral pedestrian detection, by iteratively generating pseudo annotations and updating the parameters of our designed multispectral pedestrian detector on target domain. Pseudo annotations are generated using the detector trained on source domain, and then updated by fixing the parameters of detector and minimizing the cross entropy loss without back-propagation. Training labels are generated using the pseudo annotations by considering the characteristics of similarity and complementarity between well-aligned visible and infrared image pairs. The parameters of detector are updated using the generated labels by minimizing our defined multi-detection loss function with back-propagation. The optimal parameters of detector can be obtained after iteratively updating the pseudo annotations and parameters. Experimental results show that our proposed unsupervised multimodal domain adaptation method achieves significantly higher detection performance than the approach without domain adaptation, and is competitive with the supervised multispectral pedestrian detectors.