Kejian Wu

Kejian Wu

Auto-generated profile, based on publicly available information

Kejian Wu

Nreal

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications

30 May 2024
Verified
Conference Paper
Open access
ZFZhaoxin Fan
Zhaoxin Fan
ZSZhenbo Song
Zhenbo Song
ZWZhicheng Wang
Zhicheng Wang
JXJian Xu
Jian Xu
KWKejian Wu
Kejian Wu
Jun HeJun He
Jun He
In the realm of category-level 6D object pose estimation, canonical 3D representation reconstruction is pivotal, yet current methods show limitations in reconstruction quality, a key step in current pose estimation pipeline. To address this, we introduce an innovative Adversarial Canonical Representation Reconstruction Network (ACR-Pose) in this paper. In particular, ACR-Pose comprises a Reconstructor, with novel sub-modules: a Pose-Irrelevant Module (PIM) for robustness to rotation and translation, and a Relational Reconstruction Module (RRM) for extracting relational information between input modalities. A Discriminator is incorporated to guide the generation of realistic canonical representations through adversarial optimization. Evaluated on the prevalent NOCS-CAMERA and NOCS-REAL datasets, our method significantly improves the performance of baseline models and achieves comparable performance with existing state-of-the-art methods, representing a promising advancement in the field of category-level 6D object pose estimation.

1 August 2023
Verified
Conference Paper
Open access
PDF file
ZFZhaoxin Fan
Zhaoxin Fan
YHYulin He
Yulin He
ZWZhicheng Wang
Zhicheng Wang
KWKejian Wu
Kejian Wu
HLHongyan Liu
Hongyan Liu
Jun HeJun He
Jun He
Real-world sensors often produce incomplete, irregular, and noisy point clouds, making point cloud completion increasingly important. However, most existing completion methods rely on large paired datasets for training, which is labor-intensive. This paper proposes RaPD, a novel semi-supervised point cloud completion method that reduces the need for paired datasets. RaPD utilizes a two-stage training scheme, where a deep semantic prior is learned in stage 1 from unpaired complete and incomplete point clouds, and a semi-supervised prior distillation process is introduced in stage 2 to train a completion network using only a small number of paired samples. Additionally, a self-supervised completion module is introduced to improve performance using unpaired incomplete point clouds. Experiments on multiple datasets show that RaPD outperforms previous methods in both homologous and heterologous scenarios.

28 August 2022 in arXiv
Verified
Preprint
Open access
PDF file
ZFZhaoxin Fan
Zhaoxin Fan
ZSZhenbo Song
Zhenbo Song
JXJian Xu
Jian Xu
ZWZhicheng Wang
Zhicheng Wang
KWKejian Wu
Kejian Wu
Jun HeJun He
Jun He
Recently, RGBD-based category-level 6D object pose estimation has achieved promising improvement in performance, however, the requirement of depth information prohibits broader applications. In order to relieve this problem, this paper proposes a novel approach named Object Level Depth reconstruction Network (OLD-Net) taking only RGB images as input for category-level 6D object pose estimation. We propose to directly predict object-level depth from a monocular RGB image by deforming the category-level shape prior into object-level depth and the canonical NOCS representation. Two novel modules named Normalized Global Position Hints (NGPH) and Shape-aware Decoupled Depth Reconstruction (SDDR) module are introduced to learn high fidelity object-level depth and delicate shape representations. At last, the 6D object pose is solved by aligning the predicted canonical representation with the back-projected object-level depth. Extensive experiments on the challenging CAMERA25 and REAL275 datasets indicate that our model, though simple, achieves state-of-the-art performance.

12 June 2024 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
HSHan Sun
Han Sun
ZFZhaoxin Fan
Zhaoxin Fan
ZSZhenbo Song
Zhenbo Song
ZWZhicheng Wang
Zhicheng Wang
KWKejian Wu
Kejian Wu
JLJianfeng Lu
Jianfeng Lu
Monocular 3D object detection is a fundamental but very important task to many applications including autonomous driving, robotic grasping, and augmented reality. Existing leading methods tend to estimate the depth of the input image as auxiliary information for monocular 3D detection. However, this routine suffers from the inherent gap between depth estimation and object detection, which would accumulate the prediction error. In this paper, a novel training paradigm named MonoSIM is proposed. The insight behind introducing MonoSIM is that we propose to simulate the feature learning behaviors of two heterogeneous object detectors. During the training period, monocular detectors simulate the learning behaviors of the target point cloud based detector. Hence, during the inference period, the steps of feature extraction and prediction process would be similar to the point cloud based detector as possible. To achieve it, we propose one scene-level simulation module, one RoI-level simulation module, and one response-level simulation module, which are progressively used for the detector’s full feature learning and prediction pipeline. In this paradigm, we adopt the famous M3D-RPN, CaDDN, and GUPNet detectors, and conduct extensive experiments on KITTI and Waymo Open datasets. Results show that our method has achieved a minimum 1% performance improvement for different baselines on various datasets. When compared with current state-of-the-art methods, our method only imposes the almost negligible cost for training and no extra computational cost for inference. Our codes are publicly available at https://github.com/sunh18/MonoSIM.

24 July 2023 in arXiv
Verified
Preprint
Open access
PDF file
ZFZhaoxin Fan
Zhaoxin Fan
YHYulin He
Yulin He
ZWZhicheng Wang
Zhicheng Wang
KWKejian Wu
Kejian Wu
HLHongyan Liu
Hongyan Liu
Jun HeJun He
Jun He
Real-world sensors often produce incomplete, irregular, and noisy point clouds, making point cloud completion increasingly important. However, most existing completion methods rely on large paired datasets for training, which is labor-intensive. This paper proposes RaPD, a novel semi-supervised point cloud completion method that reduces the need for paired datasets. RaPD utilizes a two-stage training scheme, where a deep semantic prior is learned in stage 1 from unpaired complete and incomplete point clouds, and a semi-supervised prior distillation process is introduced in stage 2 to train a completion network using only a small number of paired samples. Additionally, a self-supervised completion module is introduced to improve performance using unpaired incomplete point clouds. Experiments on multiple datasets show that RaPD outperforms previous methods in both homologous and heterologous scenarios.