Human-centered dynamic scene understanding plays a pivotal role in enhancing the capability of robotic and autonomous systems, in which Video-based Human-Object Interaction (V-HOI) detection is a crucial task in semantic scene understanding, aimed at comprehensively understanding HOI relationships within a video to benefit the behavioral decisions of mobile robots and autonomous driving systems. Although previous V-HOI detection models have made significant strides in accurate detection on specific datasets, they still lack the general reasoning ability like human beings to effectively induce HOI relationships. In this study, we propose V-HOI Multi-LLMs Collaborated Reasoning (V-HOI MLCR), a novel framework consisting of a series of plug-and-play modules that could facilitate the performance of current V-HOI detection models by leveraging the strong reasoning ability of different off-the-shelf pre-trained large language models (LLMs). We design a two-stage collaboration system of different LLMs for the V-HOI task. Specifically, in the first stage, we design a Cross-Agents Reasoning scheme to leverage the LLM conduct reasoning from different aspects. In the second stage, we perform Multi-LLMs Debate to get the final reasoning answer based on the different knowledge in different LLMs. Additionally, we devise an auxiliary training strategy that utilizes CLIP, a large vision-language model to enhance the base V-HOI models' discriminative ability to better cooperate with LLMs. We validate the superiority of our design by demonstrating its effectiveness in improving the prediction accuracy of the base V-HOI model via reasoning from multiple perspectives.
We propose SparseDC, a model for Depth Completion of Sparse and non-uniform depth inputs. Unlike previous methods focusing on completing fixed distributions on benchmark datasets (e.g., NYU with 500 points, KITTI with 64 lines), SparseDC is specifically designed to handle depth maps with poor quality in real usage. The key contributions of SparseDC are two-fold. First, we design a simple strategy, called SFFM, to improve the robustness under sparse input by explicitly filling the unstable depth features with stable image features. Second, we propose a two-branch feature embedder to predict both the precise local geometry of regions with available depth values and accurate structures in regions with no depth. The key of the embedder is an uncertainty-based fusion module called UFFM to balance the local and long-term information extracted by CNNs and ViTs. Extensive indoor and outdoor experiments demonstrate the robustness of our framework when facing sparse and non-uniform input depths. The pre-trained model and code are available at https://github.com/WHU-USI3DV/SparseDC.
Monocular 6D pose estimation is a fundamental task in computer vision. Existing works often adopt a two-stage pipeline by establishing correspondences and utilizing a RANSAC algorithm to calculate 6 degrees-of-freedom (6DoF) pose. Recent works try to integrate differentiable RANSAC algorithms to achieve an end-to-end 6D pose estimation. However, most of them hardly consider the geometric features in 3D space, and ignore the topology cues when performing differentiable RANSAC algorithms. To this end, we proposed a Depth-Guided Edge Convolutional Network (DGECN) for 6D pose estimation task. We have made efforts from the following three aspects: 1) We take advantages ofestimated depth information to guide both the correspondences-extraction process and the cascaded differentiable RANSAC algorithm with geometric information. 2)We leverage the uncertainty ofthe estimated depth map to improve accuracy and robustness ofthe output 6D pose. 3) We propose a differentiable Perspective-n-Point(PnP) algorithm via edge convolution to explore the topology relations between 2D-3D correspondences. Experiments demonstrate that our proposed network outperforms current works on both effectiveness and efficiency.
Unpaired 3D object completion aims to predict a complete 3D shape from an incomplete input without knowing the correspondence between the complete and incomplete shapes during training. To build the correspondence between two data modalities, previous methods usually apply adversarial training to match the global shape features extracted by the encoder. However, this ignores the correspondence between multi-scaled geometric information embedded in the pyramidal hierarchy of the decoder, which makes previous methods struggle to generate high-quality complete shapes. To address this problem, we propose a novel unpaired shape completion network, named MFM-Net, using multi-stage feature matching, which decomposes the learning of geometric correspondence into multi-stages throughout the hierarchical generation process in the point cloud decoder. Specifically, MFM-Net adopts a dual path architecture to establish multiple feature matching channels in different layers of the decoder, which is then combined with the adversarial learning to merge the distribution of features from complete and incomplete modalities. In addition, a refinement is applied to enhance the details. As a result, MFM-Net makes use of a more comprehensive understanding to establish the geometric correspondence between complete and incomplete shapes in a local-to-global perspective, which enables more detailed geometric inference for generating high-quality complete shapes. We conduct comprehensive experiments on several datasets, and the results show that our method outperforms previous methods of unpaired point cloud completion with a large margin.
Point cloud upsampling is to densify a sparse point set acquired from 3D sensors, providing a denser representation for underlying surface. However, existing methods perform upsampling on a single patch, ignoring the coherence and relation of the entire surface, thus limiting the upsampled capability. Also, they mainly focus on a clean input, thus the performance is severely compromised when handling scenarios with extra noises. In this paper, we present a novel method for more effective point cloud upsampling, achieving a more robust and improved performance. To this end, we incorporate two thorough considerations. i) Instead of upsampling each small patch independently as previous works, we take adjacent patches as input and introduce a Patch Correlation Unit to explore the shape correspondence between them for effective upsampling. ii)We propose a Position Correction Unit to mitigate the effects of outliers and noisy points. It contains a distance-aware encoder to dynamically adjust the generated points to be close to the underlying surface. Extensive experiments demonstrate that our proposed method surpasses previous upsampling methods on both clean and noisy inputs.
Point cloud shape completion is a challenging problem in 3D vision and robotics. Existing learning-based frameworks leverage encoder-decoder architectures to recover the complete shape from a highly encoded global feature vector. Though the global feature can approximately represent the overall shape of 3D objects, it would lead to the loss of shape details during the completion process. In this work, instead of using a global feature to recover the whole complete surface, we explore the functionality of multi-level features and aggregate different features to represent the known part and the missing part separately. We propose two different feature aggregation strategies, named global \& local feature aggregation(GLFA) and residual feature aggregation(RFA), to express the two kinds of features and reconstruct coordinates from their combination. In addition, we also design a refinement component to prevent the generated point cloud from non-uniform distribution and outliers. Extensive experiments have been conducted on the ShapeNet dataset. Qualitative and quantitative evaluations demonstrate that our proposed network outperforms current state-of-the art methods especially on detail preservation.
Point cloud based retrieval for place recognition is an emerging problem in vision field. The main challenge is how to find an efficient way to encode the local features into a discriminative global descriptor. In this paper, we propose a Point Contextual Attention Network (PCAN), which can predict the significance of each local point feature based on point context. Our network makes it possible to pay more attention to the task-relevent features when aggregating local features. Experiments on various benchmark datasets show that the proposed network can provide outperformance than current state-of-the-art approaches.