Search Results for author: Marcelo H. Ang Jr

Found 20 papers, 14 papers with code

DriveSceneGen: Generating Diverse and Realistic Driving Scenarios from Scratch

no code implementations26 Sep 2023 Shuo Sun, Zekai Gu, Tianchen Sun, Jiawei Sun, Chengran Yuan, Yuhang Han, Dongen Li, Marcelo H. Ang Jr

Realistic and diverse traffic scenarios in large quantities are crucial for the development and validation of autonomous driving systems.

Autonomous Driving Diversity

DR-Pose: A Two-stage Deformation-and-Registration Pipeline for Category-level 6D Object Pose Estimation

1 code implementation5 Sep 2023 Lei Zhou, Zhiyang Liu, Runze Gan, Haozhe Wang, Marcelo H. Ang Jr

In the second stage, a novel registration network is designed to extract pose-sensitive features and predict the representation of object partial point cloud in canonical space based on the deformation results from the first stage.

6D Pose Estimation using RGB Object +1

SynTable: A Synthetic Data Generation Pipeline for Unseen Object Amodal Instance Segmentation of Cluttered Tabletop Scenes

1 code implementation14 Jul 2023 Zhili Ng, Haozhe Wang, Zhengshen Zhang, Francis Tay Eng Hock, Marcelo H. Ang Jr

In this work, we present SynTable, a unified and flexible Python-based dataset generator built using NVIDIA's Isaac Sim Replicator Composer for generating high-quality synthetic datasets for unseen object amodal instance segmentation of cluttered tabletop scenes.

Amodal Instance Segmentation Semantic Segmentation +1

Multi-Frequency-Aware Patch Adversarial Learning for Neural Point Cloud Rendering

no code implementations7 Oct 2022 Jay Karhade, Haiyue Zhu, Ka-Shing Chung, Rajesh Tripathy, Wei Lin, Marcelo H. Ang Jr

The proposed approach aims to improve the rendering realness by minimizing the spectrum discrepancy between real and synthesized images, especially on the high-frequency localized sharpness information which causes image blur visually.

BIMS-PU: Bi-Directional and Multi-Scale Point Cloud Upsampling

no code implementations25 Jun 2022 Yechao Bai, Xiaogang Wang, Marcelo H. Ang Jr, Daniela Rus

The learning and aggregation of multi-scale features are essential in empowering neural networks to capture the fine-grained geometric details in the point cloud upsampling task.

point cloud upsampling

A Benchmark for Modeling Violation-of-Expectation in Physical Reasoning Across Event Categories

no code implementations16 Nov 2021 Arijit Dasgupta, Jiafei Duan, Marcelo H. Ang Jr, Yi Lin, Su-hua Wang, Renée Baillargeon, Cheston Tan

Recent work in computer vision and cognitive reasoning has given rise to an increasing adoption of the Violation-of-Expectation (VoE) paradigm in synthetic datasets.

TAda! Temporally-Adaptive Convolutions for Video Understanding

2 code implementations ICLR 2022 Ziyuan Huang, Shiwei Zhang, Liang Pan, Zhiwu Qing, Mingqian Tang, Ziwei Liu, Marcelo H. Ang Jr

This work presents Temporally-Adaptive Convolutions (TAdaConv) for video understanding, which shows that adaptive weight calibration along the temporal dimension is an efficient way to facilitate modelling complex temporal dynamics in videos.

Ranked #67 on Action Recognition on Something-Something V2 (using extra training data)

Action Classification Action Recognition +2

AVoE: A Synthetic 3D Dataset on Understanding Violation of Expectation for Artificial Cognition

1 code implementation12 Oct 2021 Arijit Dasgupta, Jiafei Duan, Marcelo H. Ang Jr, Cheston Tan

Recent work in cognitive reasoning and computer vision has engendered an increasing popularity for the Violation-of-Expectation (VoE) paradigm in synthetic datasets.

ParamCrop: Parametric Cubic Cropping for Video Contrastive Learning

1 code implementation24 Aug 2021 Zhiwu Qing, Ziyuan Huang, Shiwei Zhang, Mingqian Tang, Changxin Gao, Marcelo H. Ang Jr, Rong Jin, Nong Sang

The visualizations show that ParamCrop adaptively controls the center distance and the IoU between two augmented views, and the learned change in the disparity along the training process is beneficial to learning a strong representation.

Contrastive Learning

A Stronger Baseline for Ego-Centric Action Detection

1 code implementation13 Jun 2021 Zhiwu Qing, Ziyuan Huang, Xiang Wang, Yutong Feng, Shiwei Zhang, Jianwen Jiang, Mingqian Tang, Changxin Gao, Marcelo H. Ang Jr, Nong Sang

This technical report analyzes an egocentric video action detection method we used in the 2021 EPIC-KITCHENS-100 competition hosted in CVPR2021 Workshop.

Action Detection

Multi-Scale Feature Aggregation by Cross-Scale Pixel-to-Region Relation Operation for Semantic Segmentation

no code implementations3 Jun 2021 Yechao Bai, Ziyuan Huang, Lyuyu Shen, Hongliang Guo, Marcelo H. Ang Jr, Daniela Rus

Experiment results on two challenging datasets Cityscapes and COCO demonstrate that the RSP head performs competitively on both semantic segmentation and panoptic segmentation with high efficiency.

Panoptic Segmentation Relation +1

Point Cloud Completion by Learning Shape Priors

1 code implementation2 Aug 2020 Xiaogang Wang, Marcelo H. Ang Jr, Gim Hee Lee

Then we learn a mapping to transfer the point features from partial points to that of the complete points by optimizing feature alignment losses.

Generative Adversarial Network Point Cloud Completion

Shape Prior Deformation for Categorical 6D Object Pose and Size Estimation

2 code implementations ECCV 2020 Meng Tian, Marcelo H. Ang Jr, Gim Hee Lee

We present a novel learning approach to recover the 6D poses and sizes of unseen object instances from an RGB-D image.

Object

Toward Hierarchical Self-Supervised Monocular Absolute Depth Estimation for Autonomous Driving Applications

1 code implementation12 Apr 2020 Feng Xue, Guirong Zhuo, Ziyuan Huang, Wufei Fu, Zhuoyue Wu, Marcelo H. Ang Jr

Our contributions are twofold: a) a novel dense connected prediction (DCP) layer is proposed to provide better object-level depth estimation and b) specifically for autonomous driving scenarios, dense geometrical constrains (DGC) is introduced so that precise scale factor can be recovered without additional cost for autonomous vehicles.

Autonomous Driving Monocular Depth Estimation +1

Cannot find the paper you are looking for? You can Submit a new open access paper.