arXiv subjects

Yongliang Shi

Publications and source records attributed to Yongliang Shi.

23 records · Page 2Linked to original sources

arXiv2023

LODE: Locally Conditioned Eikonal Implicit Scene Completion from Sparse LiDAR

Scene completion refers to obtaining dense scene representation from an incomplete perception of complex 3D scenes. This helps robots detect multi-scale obstacles and analyse object occlusions in scenarios such as autonomous driving. Recent advances show that implicit representation learning can be leveraged for continuous scene completion and achieved through physical constraints like Eikonal equations. However, former Eikonal completion methods only demonstrate results on watertight meshes at a scale of tens of meshes. None of them are successfully done for non-watertight LiDAR point clouds of open large scenes at a scale of thousands of scenes. In this paper, we propose a novel Eikonal formulation that conditions the implicit representation on localized shape priors which function as dense boundary value constraints, and demonstrate it works on SemanticKITTI and SemanticPOSS. It can also be extended to semantic Eikonal scene completion with only small modifications to the network architecture. With extensive quantitative and qualitative results, we demonstrate the benefits and drawbacks of existing Eikonal methods, which naturally leads to the new locally conditioned formulation. Notably, we improve IoU from 31.7% to 51.2% on SemanticKITTI and from 40.5% to 48.7% on SemanticPOSS. We extensively ablate our methods and demonstrate that the proposed formulation is robust to a wide spectrum of implementation hyper-parameters. Codes and models are publicly available at https://github.com/AIR-DISCOVER/LODE.

cs.CV↗

arXiv2022

Ab initio Real-Time Quantum Dynamics of Charge Carriers in Momentum Space

Application of the nonadiabatic molecular dynamics (NAMD) approach is severely limited to studying carrier dynamics in the momentum space, since a supercell is required to sample the phonon excitation and electron-phonon (e-ph) interaction at different momenta in a molecular dynamics simulation. Here, we develop an ab initio approach for the real-time quantum dynamics for charge carriers in the momentum space (NAMD_k) by directly introducing the e-ph coupling into the Hamiltonian based on the harmonic approximation. The NAMD_k approach maintains the quantum zero-point energy and proper phonon dispersion, and includes memory effects of phonon excitation. The application of NAMD_k to the hot carrier dynamics in graphene reveals the phonon-specific relaxation mechanism. An energy threshold of 0.2eV, defined by two optical phonon modes strongly coupled to the electrons, separates the hot electron relaxation into fast and slow regions with the lifetimes of pico- and nano-seconds, respectively. The NAMD_k approach provides a powerful tool to understand real-time carrier dynamics in the momentum space for different materials.

physics.app-ph↗

arXiv2022

TOIST: Task Oriented Instance Segmentation Transformer with Noun-Pronoun Distillation

Current referring expression comprehension algorithms can effectively detect or segment objects indicated by nouns, but how to understand verb reference is still under-explored. As such, we study the challenging problem of task oriented detection, which aims to find objects that best afford an action indicated by verbs like sit comfortably on. Towards a finer localization that better serves downstream applications like robot interaction, we extend the problem into task oriented instance segmentation. A unique requirement of this task is to select preferred candidates among possible alternatives. Thus we resort to the transformer architecture which naturally models pair-wise query relationships with attention, leading to the TOIST method. In order to leverage pre-trained noun referring expression comprehension models and the fact that we can access privileged noun ground truth during training, a novel noun-pronoun distillation framework is proposed. Noun prototypes are generated in an unsupervised manner and contextual pronoun features are trained to select prototypes. As such, the network remains noun-agnostic during inference. We evaluate TOIST on the large-scale task oriented dataset COCO-Tasks and achieve +10.9% higher $\rm{mAP^{box}}$ than the best-reported results. The proposed noun-pronoun distillation can boost $\rm{mAP^{box}}$ and $\rm{mAP^{mask}}$ by +2.8% and +3.8%. Codes and models are publicly available at https://github.com/AIR-DISCOVER/TOIST.

cs.CV↗

arXiv2021

Semi-supervised Implicit Scene Completion from Sparse LiDAR

Recent advances show that semi-supervised implicit representation learning can be achieved through physical constraints like Eikonal equations. However, this scheme has not yet been successfully used for LiDAR point cloud data, due to its spatially varying sparsity. In this paper, we develop a novel formulation that conditions the semi-supervised implicit function on localized shape embeddings. It exploits the strong representation learning power of sparse convolutional networks to generate shape-aware dense feature volumes, while still allows semi-supervised signed distance function learning without knowing its exact values at free space. With extensive quantitative and qualitative results, we demonstrate intrinsic properties of this new learning system and its usefulness in real-world road scenes. Notably, we improve IoU from 26.3% to 51.0% on SemanticKITTI. Moreover, we explore two paradigms to integrate semantic label predictions, achieving implicit semantic completion. Code and models can be accessed at https://github.com/OPEN-AIR-SUN/SISC.

cs.CV↗

arXiv2021

Coherence Control of Directional Nonlinear Photocurrent in Spatially Symmetric Systems

The interplay between crystal symmetry and its optical responses is at the heart of tremendous recent advances in light-matter interactions and applications. Nonlinear optical processes that produce electric currents, for example bulk photovoltaic (BPV) effect, require inversion symmetry broken materials, such as ferroelectrics. In the current work, we demonstrate that such BPV current could be generated in centrosymmetric materials with excitation of out-of-equilibrium coherent phonons. This is much different from the generally studied static or thermally excited states. We show that depending on the oscillating phase factor of the coherent phonon, uni-directional static electric current can be observed, in addition to some terahertz alternating currents. We also generalize the conventional injection charge current into angular momentum (spin and orbital) degrees of freedom, and demonstrate spin and orbital BPV photocurrents under coherent phonons. Our findings open the pathway to exploring the exotic phonon-photon-electron coherent interactions in quantum materials.

cond-mat.mtrl-sci↗