Deep learning approaches have achieved great success in addressing the problem of optical flow estimation. The keys to success lie in the use of cost volume and coarse-to-fine flow inference. However, the matching problem becomes ill-posed when partially occluded or homogeneous regions exist in images. This causes a cost volume to contain outliers and affects the flow decoding from it. Besides, the coarse-to-fine flow inference demands an accurate flow initialization. Ambiguous correspondence yields erroneous flow fields and affects the flow inferences in subsequent levels. In this paper, we introduce LiteFlowNet3, a deep network consisting of two specialized modules, to address the above challenges. (1) We ameliorate the issue of outliers in the cost volume by amending each cost vector through an adaptive modulation prior to the flow decoding. (2) We further improve the flow accuracy by exploring local flow consistency. To this end, each inaccurate optical flow is replaced with an accurate one from a nearby position through a novel warping of the flow field. LiteFlowNet3 not only achieves promising results on public benchmarks but also has a small model size and a fast runtime.
Speeded Up Robust Features (SURF) has emerged as one of the more popular feature descriptors and detectors in recent years. Performance and algorithmic details vary widely between implementations due to SURF's complexity and ambiguities found in its description. To resolve these ambiguities, a set of general techniques for feature stability is defined based on the smoothness rule. Additional improvements to SURF are proposed for speed and stability. To illustrate the importance of these implementation details, a performance study of popular SURF implementations is done. By utilizing all the su…
Resolving Symmetry Ambiguity in Correspondence-based Methods for Instance-level Object Pose Estimation
College of Control Science and Engineering, Zhejiang University（浙江大学控制科学与工程学院）；RPTU Kaiserslautern（凯泽斯劳滕工业大学）；German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心）；Technische Universität München（慕尼黑工业大学）
University of Delaware（特拉华大学）；Microsoft Research（微软研究院）
In perspective cameras, images of a frontal-parallel 3D object preserve its aspect ratio invariant to its depth. Such an invariance is useful in photography but is unique to perspective projection. In this paper, we show that alternative non-perspective cameras such as the crossed-slit or XSlit cameras exhibit a different depth-dependent aspect ratio (DDAR) property that can be used to 3D recovery. We first conduct a comprehensive analysis to characterize DDAR, infer object depth from its AR, and model recoverable depth range, sensitivity, and error. We show that repeated shape patterns in rea…
Teaching Vision-Language Models to Ask: Resolving Ambiguity in Visual Questions
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Wuhan AI Research（武汉人工智能研究院）
Resolving the Ambiguity of Complete-to-Partial Point Cloud Registration for Image-Guided Liver Surgery with Patches-to-Partial Matching
Center for Imaging Science and Department of Biomedical Engineering, Rochester Institute of Technology（成像科学中心和生物医学工程系，罗切斯特理工学院）；Department of Biomedical Engineering, Vanderbilt University（生物医学工程系，范德比尔特大学）；School of Science and Engineering, University of Missouri – Kansas City（科学与工程学院，密苏里大学-堪萨斯城分校）
Resolving Long-Tail Ambiguity in Unsupervised 3D Point Cloud Segmentation with Language Priors
South China University of Technology（华南理工大学）；Bytedance（字节跳动）；Tsinghua University（清华大学）；Shenzhen MSU-BIT University（深圳MSU-BIT大学）；Guangming Laboratory（光明实验室）
Resolving Ambiguity in Gaze-Facilitated Visual Assistant Interaction Paradigm
Key Laboratory of Pervasive Computing, Tsinghua University（清华大学普适计算重点实验室）；The University of New South Wales（新南威尔士大学）；SKLSDE Lab, Beihang University（北航SKLSDE实验室）
Don't Guess, Just Ask: Resolving Ambiguity in Referring Segmentation via Multi-turn Clarification
School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机科学与工程学院）；Guangdong Province Key Laboratory of Information Security Technology（广东省信息安全技术重点实验室）；Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education（教育部机器智能与先进计算重点实验室）
Resolving Representation Ambiguity in Feedforward Novel View Synthesis Transformer via Semantic-Spatial Decoupling
Institute of Trustworthy Embodied Artificial Intelligence (TEAI)（可信具身人工智能研究所）；Shanghai Key Laboratory of Multimodal Embodied AI（上海多模态具身人工智能重点实验室）；Sch. of Artificial Intelligence & Sch. of Computer Science, Shanghai Jiao Tong University（上海交通大学人工智能学院与计算机科学学院）；University of Science and Technology of China（中国科学技术大学）
The University of Adelaide（阿德莱德大学）；University of Tsukuba（筑波大学）
Planar markers are useful in robotics and computer vision for mapping and localisation. Given a detected marker in an image, a frequent task is to estimate the 6DOF pose of the marker relative to the camera, which is an instance of planar pose estimation (PPE). Although there are mature techniques, PPE suffers from a fundamental ambiguity problem, in that there can be more than one plausible pose solutions for a PPE instance. Especially when localisation of the marker corners is noisy, it is often difficult to disambiguate the pose solutions based on reprojection error alone. Previous methods …
Ask-to-Clarify: Resolving Instruction Ambiguity through Multi-turn Dialogue
College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China（复旦大学计算机科学与人工智能学院）；Shanghai Innovation Institute, Shanghai, China（上海创新研究院）；Mechanical Systems Control Lab, UC Berkeley, California, USA（伯克利机械系统控制实验室）
City University of Hong Kong（香港城市大学）；Hong Kong University of Science and Technology（香港科技大学）；Zhejiang University（浙江大学）；University of Surrey（萨里大学）
In this paper, we study the problem of multi-view sketch correspondence, where we take as input multiple freehand sketches with different views of the same object and predict as output the semantic correspondence among the sketches. This problem is challenging since the visual features of corresponding points at different views can be very different. To this end, we take a deep learning approach and learn a novel local sketch descriptor from data. We contribute a training dataset by generating the pixel-level correspondence for the multi-view line drawings synthesized from 3D shapes. To handle…
PolarGS: Polarimetric Cues for Ambiguity-Free Gaussian Splatting with Accurate Geometry Recovery
Institute of Artificial Intelligence, Beihang University（北航人工智能研究院）；Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing（北京未来区块链与隐私计算先进创新中心）；State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University（虚拟现实技术与系统国家重点实验室，北航计算机科学与工程学院）
Prior-based Objective Inference Mining Potential Uncertainty for Facial Expression Recognition
College of Electronics and Information Engineering, Tongji University（同济大学电子与信息工程学院）；Frontiers Science Center for Intelligent Autonomous Systems, Tongji University（同济大学智能自主系统前沿科学中心）
Correspondence-based shape models are key to various medical imaging applications that rely on a statistical analysis of anatomies. Such shape models are expected to represent consistent anatomical features across the population for population-specific shape statistics. Early approaches for correspondence placement rely on nearest neighbor search for simpler anatomies. Coordinate transformations for shape correspondence hold promise to address the increasing anatomical complexities. Nonetheless, due to the inherent shape-level geometric complexity and population-level shape variation, the coor…
University of Southern Denmark（南丹麦大学）；Maersk Mc-Kinney Moller Institute（马士基·麦金尼·穆勒研究所）
In many automation tasks involving manipulation of rigid objects, the poses of the objects must be acquired. Vision-based pose estimation using a single RGB or RGB-D sensor is especially popular due to its broad applicability. However, single-view pose estimation is inherently limited by depth ambiguity and ambiguities imposed by various phenomena like occlusion, self-occlusion, reflections, etc. Aggregation of information from multiple views can potentially resolve these ambiguities, but the current state-of-the-art multi-view pose estimation method only uses multiple views to aggregate singl…
