Search Results for author: Changjian Li

Found 14 papers, 6 papers with code

CADTalk: An Algorithm and Benchmark for Semantic Commenting of CAD Programs

no code implementations28 Nov 2023 Haocheng Yuan, Jing Xu, Hao Pan, Adrien Bousseau, Niloy J. Mitra, Changjian Li

CAD programs are a popular way to compactly encode shapes as a sequence of operations that are easy to parametrically modify.

ContextSeg: Sketch Semantic Segmentation by Querying the Context with Attention

no code implementations28 Nov 2023 Jiawei Wang, Changjian Li

Sketch semantic segmentation is a well-explored and pivotal problem in computer vision involving the assignment of pre-defined part labels to individual strokes.

Semantic Segmentation

iPUNet:Iterative Cross Field Guided Point Cloud Upsampling

1 code implementation13 Oct 2023 Guangshun Wei, Hao Pan, Shaojie Zhuang, Yuanfeng Zhou, Changjian Li

To solve the non-uniformity of input points, on top of the cross field guided upsampling, we further introduce an iterative strategy that refines the point distribution by moving sparse points onto the desired continuous 3D surface in each iteration.

Geometry-Aware Attenuation Field Learning for Sparse-View CBCT Reconstruction

no code implementations26 Mar 2023 Zhentao Liu, Yu Fang, Changjian Li, Han Wu, YuAn Liu, Zhiming Cui, Dinggang Shen

This paper proposes a novel attenuation field encoder-decoder framework by first encoding the volumetric feature from multi-view X-ray projections, then decoding it into the desired attenuation field.

SNAF: Sparse-view CBCT Reconstruction with Neural Attenuation Fields

no code implementations30 Nov 2022 Yu Fang, Lanzhuju Mei, Changjian Li, YuAn Liu, Wenping Wang, Zhiming Cui, Dinggang Shen

Cone beam computed tomography (CBCT) has been widely used in clinical practice, especially in dental clinics, while the radiation dose of X-rays when capturing has been a long concern in CBCT imaging.

ToothInpaintor: Tooth Inpainting from Partial 3D Dental Model and 2D Panoramic Image

no code implementations25 Nov 2022 Yuezhi Yang, Zhiming Cui, Changjian Li, Wenping Wang

In this paper, we propose a neural network, called ToothInpaintor, that takes as input a partial 3D dental model and a 2D panoramic image and reconstructs the full tooth model with high-quality root(s).

CDT: Cascading Decision Trees for Explainable Reinforcement Learning

1 code implementation15 Nov 2020 Zihan Ding, Pablo Hernandez-Leal, Gavin Weiguang Ding, Changjian Li, Ruitong Huang

As a second contribution our study reveals limitations of explaining black-box policies via imitation learning with tree-based explainable models, due to its inherent instability.

Explainable Models Imitation Learning +3

SEG-MAT: 3D Shape Segmentation Using Medial Axis Transform

1 code implementation22 Oct 2020 Cheng Lin, Lingjie Liu, Changjian Li, Leif Kobbelt, Bin Wang, Shiqing Xin, Wenping Wang

Segmenting arbitrary 3D objects into constituent parts that are structurally meaningful is a fundamental problem encountered in a wide range of computer graphics applications.

Segmentation

Topological Hall Effect and Skyrmion-like Bubbles at a Charge-transfer Interface

no code implementations3 Jun 2020 Zhi Shiuh Lim, Changjian Li, Zhen Huang, Xiao Chi, Jun Zhou, Shengwei Zeng, Ganesh Ji Omar, Yuan Ping Feng, Andrivo Rusydi, Stephen John Pennycook, Thirumalai Venkatesan, Ariando Ariando

Here, the emergence, tuning and interpretation of hump-shape Hall Effect from a CaMnO3/CaIrO3/CaMnO3 trilayer structure are studied in detail.

Mesoscale and Nanoscale Physics

Some Insights into Lifelong Reinforcement Learning Systems

1 code implementation27 Jan 2020 Changjian Li

A lifelong reinforcement learning system is a learning system that has the ability to learn through trail-and-error interaction with the environment over its lifetime.

reinforcement-learning Reinforcement Learning (RL)

A Micro-Objective Perspective of Reinforcement Learning

no code implementations24 May 2019 Changjian Li, Krzysztof Czarnecki

The standard reinforcement learning (RL) formulation considers the expectation of the (discounted) cumulative reward.

reinforcement-learning Reinforcement Learning (RL)

Floorplan-Jigsaw: Jointly Estimating Scene Layout and Aligning Partial Scans

no code implementations ICCV 2019 Cheng Lin, Changjian Li, Wenping Wang

We present a novel approach to align partial 3D reconstructions which may not have substantial overlap.

Urban Driving with Multi-Objective Deep Reinforcement Learning

1 code implementation21 Nov 2018 Changjian Li, Krzysztof Czarnecki

Autonomous driving is a challenging domain that entails multiple aspects: a vehicle should be able to drive to its destination as fast as possible while avoiding collision, obeying traffic rules and ensuring the comfort of passengers.

Autonomous Driving Q-Learning +2

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