Liang Yang

Ziyue Feng, Liang Yang, Longlong Jing et al.

Conventional self-supervised monocular depth prediction methods are based on a static environment assumption, which leads to accuracy degradation in dynamic scenes due to the mismatch and occlusion problems introduced by object motions. Existing dynamic-object-focused methods only partially solved the mismatch problem at the training loss level. In this paper, we accordingly propose a novel multi-frame monocular depth prediction method to solve these problems at both the prediction and supervision loss levels. Our method, called DynamicDepth, is a new framework trained via a self-supervised cycle consistent learning scheme. A Dynamic Object Motion Disentanglement (DOMD) module is proposed to disentangle object motions to solve the mismatch problem. Moreover, novel occlusion-aware Cost Volume and Re-projection Loss are designed to alleviate the occlusion effects of object motions. Extensive analyses and experiments on the Cityscapes and KITTI datasets show that our method significantly outperforms the state-of-the-art monocular depth prediction methods, especially in the areas of dynamic objects. Code is available at https://github.com/AutoAILab/DynamicDepth

Noah Stier, Anurag Ranjan, Alex Colburn et al. · apple-ml, uw

Recent works on 3D reconstruction from posed images have demonstrated that direct inference of scene-level 3D geometry without test-time optimization is feasible using deep neural networks, showing remarkable promise and high efficiency. However, the reconstructed geometry, typically represented as a 3D truncated signed distance function (TSDF), is often coarse without fine geometric details. To address this problem, we propose three effective solutions for improving the fidelity of inference-based 3D reconstructions. We first present a resolution-agnostic TSDF supervision strategy to provide the network with a more accurate learning signal during training, avoiding the pitfalls of TSDF interpolation seen in previous work. We then introduce a depth guidance strategy using multi-view depth estimates to enhance the scene representation and recover more accurate surfaces. Finally, we develop a novel architecture for the final layers of the network, conditioning the output TSDF prediction on high-resolution image features in addition to coarse voxel features, enabling sharper reconstruction of fine details. Our method, FineRecon, produces smooth and highly accurate reconstructions, showing significant improvements across multiple depth and 3D reconstruction metrics.

Noah Stier, Baptiste Angles, Liang Yang et al. · apple-ml, uw

Dense 3D reconstruction from RGB images traditionally assumes static camera pose estimates. This assumption has endured, even as recent works have increasingly focused on real-time methods for mobile devices. However, the assumption of a fixed pose for each image does not hold for online execution: poses from real-time SLAM are dynamic and may be updated following events such as bundle adjustment and loop closure. This has been addressed in the RGB-D setting, by de-integrating past views and re-integrating them with updated poses, but it remains largely untreated in the RGB-only setting. We formalize this problem to define the new task of dense online reconstruction from dynamically-posed images. To support further research, we introduce a dataset called LivePose containing the dynamic poses from a SLAM system running on ScanNet. We select three recent reconstruction systems and apply a framework based on de-integration to adapt each one to the dynamic-pose setting. In addition, we propose a novel, non-linear de-integration module that learns to remove stale scene content. We show that responding to pose updates is critical for high-quality reconstruction, and that our de-integration framework is an effective solution.

Jinglun Feng, Hua Xiao, Ejup Hoxha et al.

Impact sounding signal has been shown to contain information about structural integrity flaws and subsurface objects from previous research. As non-destructive testing (NDT) method, one of the biggest challenges in impact sounding based inspection is the subsurface targets detection and reconstruction. This paper presents the importance and practicability of using solenoids to trigger impact sounding signal and using acoustic data to reconstruct subsurface objects to address this issue. First, by taking advantage of Visual Simultaneous Localization and Mapping (V-SLAM), we could obtain the 3D position of the robot during the inspection. Second, our NDE method is based on Frequency Density (FD) analysis for the Fast Fourier Transform (FFT) of the impact sounding signal. At last, by combining the 3D position data and acoustic data, this paper creates a 3D map to highlight the possible subsurface objects. The experimental results demonstrate the feasibility of the method.

Liang Yang, Hao Jiang, Jizhong Xiao et al.

Using an ego-centric camera to do localization and tracking is highly needed for urban navigation and indoor assistive system when GPS is not available or not accurate enough. The traditional hand-designed feature tracking and estimation approach would fail without visible features. Recently, there are several works exploring to use context features to do localization. However, all of these suffer severe accuracy loss if given no visual context information. To provide a possible solution to this problem, this paper proposes a camera system with both ego-downward and third-static view to perform localization and tracking in a learning approach. Besides, we also proposed a novel action and motion verification model for cross-view verification and localization. We performed comparative experiments based on our collected dataset which considers the same dressing, gender, and background diversity. Results indicate that the proposed model can achieve $18.32 \%$ improvement in accuracy performance. Eventually, we tested the model on multi-people scenarios and obtained an average $67.767 \%$ accuracy.