arXiv subjects

Weiliang Chen

Publications and source records attributed to Weiliang Chen.

23 records · Page 2Linked to original sources

arXiv2024

Make-Your-3D: Fast and Consistent Subject-Driven 3D Content Generation

Recent years have witnessed the strong power of 3D generation models, which offer a new level of creative flexibility by allowing users to guide the 3D content generation process through a single image or natural language. However, it remains challenging for existing 3D generation methods to create subject-driven 3D content across diverse prompts. In this paper, we introduce a novel 3D customization method, dubbed Make-Your-3D that can personalize high-fidelity and consistent 3D content from only a single image of a subject with text description within 5 minutes. Our key insight is to harmonize the distributions of a multi-view diffusion model and an identity-specific 2D generative model, aligning them with the distribution of the desired 3D subject. Specifically, we design a co-evolution framework to reduce the variance of distributions, where each model undergoes a process of learning from the other through identity-aware optimization and subject-prior optimization, respectively. Extensive experiments demonstrate that our method can produce high-quality, consistent, and subject-specific 3D content with text-driven modifications that are unseen in subject image.

cs.CV↗

arXiv2023

OccWorld: Learning a 3D Occupancy World Model for Autonomous Driving

Understanding how the 3D scene evolves is vital for making decisions in autonomous driving. Most existing methods achieve this by predicting the movements of object boxes, which cannot capture more fine-grained scene information. In this paper, we explore a new framework of learning a world model, OccWorld, in the 3D Occupancy space to simultaneously predict the movement of the ego car and the evolution of the surrounding scenes. We propose to learn a world model based on 3D occupancy rather than 3D bounding boxes and segmentation maps for three reasons: 1) expressiveness. 3D occupancy can describe the more fine-grained 3D structure of the scene; 2) efficiency. 3D occupancy is more economical to obtain (e.g., from sparse LiDAR points). 3) versatility. 3D occupancy can adapt to both vision and LiDAR. To facilitate the modeling of the world evolution, we learn a reconstruction-based scene tokenizer on the 3D occupancy to obtain discrete scene tokens to describe the surrounding scenes. We then adopt a GPT-like spatial-temporal generative transformer to generate subsequent scene and ego tokens to decode the future occupancy and ego trajectory. Extensive experiments on the widely used nuScenes benchmark demonstrate the ability of OccWorld to effectively model the evolution of the driving scenes. OccWorld also produces competitive planning results without using instance and map supervision. Code: https://github.com/wzzheng/OccWorld.

cs.CV↗

arXiv2023

Development and Evaluation of a Narrow Linewidth Laser System for 171Yb+ E2 Transition

We report the construction and characterization of a narrow-linewidth laser system to interrogate the E2 clock transitions at 436 nm of ytterbium ions trapped in end-cap traps. The 871 nm seed laser at the fundamental frequency is referenced to a 10 cm long notched ULE cavity. The output of the laser system is delivered to a narrow-linewidth femtosecond fiber comb, which has been referenced to an ultrastable 698 nm laser, with a phase noise-canceled fiber link. The beat between the laser and the comb shows a sub-Hz linewidth, and with a stability better than 2E-15@1~100 s. The performance of the self-developed wavelength extension ports at 871 nm of the narrow linewidth erbium-doped fiber comb with single-point frequency-doubling technique is also verified.

physics.atom-ph↗

arXiv2022

The Brain-Inspired Decoder for Natural Visual Image Reconstruction

Decoding images from brain activity has been a challenge. Owing to the development of deep learning, there are available tools to solve this problem. The decoded image, which aims to map neural spike trains to low-level visual features and high-level semantic information space. Recently, there are a few studies of decoding from spike trains, however, these studies pay less attention to the foundations of neuroscience and there are few studies that merged receptive field into visual image reconstruction. In this paper, we propose a deep learning neural network architecture with biological properties to reconstruct visual image from spike trains. As far as we know, we implemented a method that integrated receptive field property matrix into loss function at the first time. Our model is an end-to-end decoder from neural spike trains to images. We not only merged Gabor filter into auto-encoder which used to generate images but also proposed a loss function with receptive field properties. We evaluated our decoder on two datasets which contain macaque primary visual cortex neural spikes and salamander retina ganglion cells (RGCs) spikes. Our results show that our method can effectively combine receptive field features to reconstruct images, providing a new approach to visual reconstruction based on neural information.

cs.CV↗

arXiv2016

Parallel STEPS: Large Scale Stochastic Spatial Reaction-Diffusion Simulation with High Performance Computers

Stochastic, spatial reaction-diffusion simulations have been widely used in systems biology and computational neuroscience. However, the increasing scale and complexity of simulated models and morphologies have exceeded the capacity of any serial implementation. This led to development of parallel solutions that benefit from the boost in performance of modern large-scale supercomputers. In this paper, we describe an MPI-based, parallel Operator-Splitting implementation for stochastic spatial reaction-diffusion simulations with irregular tetrahedral meshes. The performance of our implementation is first examined and analyzed with simulations of a simple model. We then demonstrate its usage in real-world research by simulating the reaction-diffusion components of a published calcium burst model in both Purkinje neuron sub-branch and full dendrite morphologies. Simulation results indicate that our implementation is capable of achieving super-linear speedup for balanced loading simulations with reasonable molecule density and mesh quality. In the best scenario a parallel simulation with 2000 processes achieves more than 3600 times of speedup relative to its serial SSA counterpart and more than 20 times of speedup relative to parallel simulation with 100 processes. While simulation performance is affected by unbalanced loading, a substantial speedup can still be observed without any special treatment.

q-bio.QM↗