skip to main content

Search for: All records

Creators/Authors contains: "Wu, Y"

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. Free, publicly-accessible full text available September 1, 2022
  2. M. Hadwiger, M. Larsen (Ed.)
    In this work, we present Unity Point-Cloud Interactive Core, a novel interactive point cloud rendering pipeline for the Unity Development Platform. The goal of the proposed pipeline is to expedite the development process for point cloud applications by encapsulating the rendering process as a standalone component, while maintaining flexibility through an implementable interface. The proposed pipeline allows for rendering arbitrarily large point clouds with improved performance and visual quality. First, a novel dynamic batching scheme is proposed to address the adaptive point sizing problem for level-of-detail (LOD) point cloud structures. Then, an approximate rendering algorithm is proposed to reduce overdrawmore »by minimizing the overall number of fragment operations through an intermediate occlusion culling pass. For the purpose of analysis, the visual quality of renderings is quantified and measured by comparing against a high-quality baseline. In the experiments, the proposed pipeline maintains above 90 FPS for a 20 million point budget while achieving greater than 90% visual quality during interaction when rendering a point-cloud with more than 20 billion points.« less
  3. We propose to learn energy-based model (EBM) in the latent space of a generator model, so that the EBM serves as a prior model that stands on the top-down networkofthegeneratormodel. BoththelatentspaceEBMandthetop-down network can be learned jointly by maximum likelihood, which involves short-run MCMC sampling from both the prior and posterior distributions of the latent vector. Due to the low dimensionality of the latent space and the expressiveness of the top-down network, a simple EBM in latent space can capture regularities in the data effectively, and MCMC sampling in latent space is efficient and mixes well. We show that the learnedmore »model exhibits strong performances in terms of image and text generation and anomaly detection. The one-page code can be found in supplementary materials.« less
    Free, publicly-accessible full text available July 1, 2022
  4. Alignments of multiple genomes are a cornerstone of comparative genomics, but generating these alignments remains technically challenging and often impractical. We developed the msa_pipeline workflow ( based on the LAST aligner to allow practical and sensitive multiple alignment of diverged plant genomes with minimal user inputs. Our workflow only requires a set of genomes in FASTA format as input. The workflow outputs multiple alignments in MAF format, and includes utilities to help calculate genome-wide conservation scores. As high repeat content and genomic divergence are substantial challenges in plant genome alignment, we also explored the impact of different masking approaches andmore »alignment parameters using genome assemblies of 33 grass species. Compared to conventional masking with RepeatMasker, a k-mer masking approach increased the alignment rate of CDS and non-coding functional regions by 25% and 14% respectively. We further found that default alignment parameters generally perform well, but parameter tuning can increase the alignment rate for non-coding functional regions by over 52% compared to default LAST settings. Finally, by increasing alignment sensitivity from the default baseline, parameter tuning can increase the number of non-coding sites that can be scored for conservation by over 76%.« less
  5. Human trajectory prediction is critical for autonomous platforms like self-driving cars or social robots. We present a latent belief energy-based model (LB-EBM) for diverse human trajectory forecast. LB-EBM is a probabilistic model with cost function defined in the latent space to account for the movement history and social context. The low dimensionality of the latent space and the high expressivity of the EBM make it easy for the model to capture the multimodality of pedestrian trajectory distributions. LB-EBM is learned from expert demonstrations (i.e., human trajectories) projected into the latent space. Sampling from or optimizing the learned LB-EBM yields amore »belief vector which is used to make a path plan, which then in turn helps to predict a long-range trajectory. The effectiveness of LB-EBM and the two-step approach are supported by strong empirical results. Our model is able to make accurate, multi-modal, and social compliant trajectory predictions and improves over prior state-of-the-arts performance on the Stanford Drone trajectory prediction benchmark by 10:9% and on the ETH-UCY benchmark by 27:6%.« less
  6. While energy-based models (EBMs) exhibit a number of desirable properties, training and sampling on high-dimensional datasets remains challenging. Inspired by recent progress on diffusion probabilistic models, we present a diffusion re- covery likelihood method to tractably learn and sample from a sequence of EBMs trained on increasingly noisy versions of a dataset. Each EBM is trained with recovery likelihood, which maximizes the conditional probability of the data at a certain noise level given their noisy versions at a higher noise level. Optimizing re- covery likelihood is more tractable than marginal likelihood, as sampling from the conditional distributions is much easiermore »than sampling from the marginal distribu- tions. After training, synthesized images can be generated by the sampling process that initializes from Gaussian white noise distribution and progressively samples the conditional distributions at decreasingly lower noise levels. Our method gener- ates high fidelity samples on various image datasets. On unconditional CIFAR-10 our method achieves FID 9.58 and inception score 8.30, superior to the majority of GANs. Moreover, we demonstrate that unlike previous work on EBMs, our long-run MCMC samples from the conditional distributions do not diverge and still represent realistic images, allowing us to accurately estimate the normalized density of data even for high-dimensional datasets. Our implementation is avail- able at« less
  7. Video sequences contain rich dynamic patterns, such as dynamic texture patterns that exhibit stationarity in the temporal domain, and action patterns that are non-stationary in either spatial or temporal domain. We show that an energy-based spatial-temporal generative ConvNet can be used to model and synthesize dynamic patterns. The model defines a probability distribution on the video sequence, and the log probability is defined by a spatial-temporal ConvNet that consists of multiple layers of spatial-temporal filters to capture spatial-temporal patterns of different scales. The model can be learned from the training video sequences by an “analysis by synthesis” learning algorithm thatmore »iterates the following two steps. Step 1 synthesizes video sequences from the currently learned model. Step 2 then updates the model parameters based on the difference between the synthesized video sequences and the observed training sequences. We show that the learning algorithm can synthesize realistic dynamic patterns. We also show that it is possible to learn the model from incomplete training sequences with either occluded pixels or missing frames, so that model learning and pattern completion can be accomplished simultaneously.« less