Search Results for author: Xuejian Rong

Found 7 papers, 1 papers with code

Incremental Scene Synthesis

no code implementations NeurIPS 2019 Benjamin Planche, Xuejian Rong, Ziyan Wu, Srikrishna Karanam, Harald Kosch, YingLi Tian, Jan Ernst, Andreas Hutter

We present a method to incrementally generate complete 2D or 3D scenes with the following properties: (a) it is globally consistent at each step according to a learned scene prior, (b) real observations of a scene can be incorporated while observing global consistency, (c) unobserved regions can be hallucinated locally in consistence with previous observations, hallucinations and global priors, and (d) hallucinations are statistical in nature, i. e., different scenes can be generated from the same observations.

Autonomous Navigation Hallucination

Unambiguous Text Localization and Retrieval for Cluttered Scenes

no code implementations CVPR 2017 Xuejian Rong, Chucai Yi, YingLi Tian

Text instance as one category of self-described objects provides valuable information for understanding and describing cluttered scenes.

Retrieval Text Retrieval

Weakly Supervised Semantic Segmentation in 3D Graph-Structured Point Clouds of Wild Scenes

no code implementations26 Apr 2020 Hai-Yan Wang, Xuejian Rong, Liang Yang, Jinglun Feng, Jizhong Xiao, YingLi Tian

The deficiency of 3D segmentation labels is one of the main obstacles to effective point cloud segmentation, especially for scenes in the wild with varieties of different objects.

3D Semantic Segmentation Point Cloud Segmentation +4

Burst Denoising via Temporally Shifted Wavelet Transforms

no code implementations ECCV 2020 Xuejian Rong, Denis Demandolx, Kevin Matzen, Priyam Chatterjee, YingLi Tian

As a result, imaging pipelines often rely on computational photography to improve SNR by fusing multiple short exposures.

Denoising

Robust Consistent Video Depth Estimation

1 code implementation CVPR 2021 Johannes Kopf, Xuejian Rong, Jia-Bin Huang

We present an algorithm for estimating consistent dense depth maps and camera poses from a monocular video.

Depth Estimation

Boosting View Synthesis With Residual Transfer

no code implementations CVPR 2022 Xuejian Rong, Jia-Bin Huang, Ayush Saraf, Changil Kim, Johannes Kopf

We present a simple but effective technique to boost the rendering quality, which can be easily integrated with most view synthesis methods.

Novel View Synthesis

AMICO: Amodal Instance Composition

no code implementations11 Oct 2022 Peiye Zhuang, Jia-Bin Huang, Ayush Saraf, Xuejian Rong, Changil Kim, Denis Demandolx

Image composition aims to blend multiple objects to form a harmonized image.

Object

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