BM
Baorui Ma
cs.CVcs.AIcs.CLcs.GRcs.RO
On Valency
published · living versionsW_qxrrjvxk·v1 · currentpublished
HRoPE: Homography Relative Positional Encoding
with Huachen Gao, Yang Yang, Xiaoqian Liang, Xingyu Chen +4
1 version
Preprints & journals
26 papers in the corpus · 2020–2026HRoPE: Homography Relative Positional Encoding2610.28284v1 · Huachen Gao, Yang Yang, Xiaoqian Liang et al.2026 · 0 citationsarXivon Valency
MOJITO: Modal Joint Learning for Unified End-to-End Autonomous Driving2607.23511v1 · Zhijing Cheng, Xuancheng Zhang, Donglin Di et al.2026 · 0 citationsarXiv
UDFStudio: A Unified Framework of Datasets, Benchmarks and Generative Models for Unsigned Distance Functions.41758845 · Zhou, Junsheng, Zhang, Weiqi, Ma, Baorui et al.2026 · 1 citationIEEE transactions on pattern analysis and machine intelligence. 2026;48(7):7902-7919
Chain of World: World Model Thinking in Latent Motion2603.03195v1 · Fuxiang Yang, Donglin Di, Lulu Tang et al.2026 · 0 citationsarXiv
MetricAnything: Scaling Metric Depth Pretraining with Noisy Heterogeneous Sources2601.22054v2 · Baorui Ma, Jiahui Yang, Donglin Di et al.2026 · 0 citationsarXiv
TIGaussian: Disentangle Gaussians for Spatial-Awared Text-Image-3D Alignment2601.19247v1 · Jiarun Liu, Qifeng Chen, Yiru Zhao et al.2026 · 0 citationsarXiv
See4D: Pose-Free 4D Generation via Auto-Regressive Video Inpainting2510.26796v2 · Dongyue Lu, Ao Liang, Tianxin Huang et al.2025 · 0 citationsComputer Graphics Forum (Eurographics 2026), e70345, 2026
TV-3DG: Mastering Text-to-3D Customized Generation with Visual Prompt.40663668 · Yang, Jiahui, Di, Donglin, Ma, Baorui et al.2025 · 2 citationsIEEE transactions on pattern analysis and machine intelligence. 2025;PP
NeRFPrior: Learning Neural Radiance Field as a Prior for Indoor Scene Reconstruction2503.18361v2 · Wenyuan Zhang, Emily Yue-ting Jia, Junsheng Zhou et al.2025 · 6 citationsarXiv
You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale2412.06699v3 · Baorui Ma, Huachen Gao, Haoge Deng et al.2024 · 23 citationsarXiv
CAP-UDF: Learning Unsigned Distance Functions Progressively From Raw Point Clouds With Consistency-Aware Field Optimization.38648138 · Zhou, Junsheng, Ma, Baorui, Li, Shujuan et al.2024 · 72 citationsIEEE transactions on pattern analysis and machine intelligence. 2024;46(12):7475-7492
Fast Learning of Signed Distance Functions From Noisy Point Clouds via Noise to Noise Mapping.38889034 · Zhou, Junsheng, Ma, Baorui, Liu, Yu-Shen et al.2024 · 13 citationsIEEE transactions on pattern analysis and machine intelligence. 2024;46(12):8936-8953
UDiFF: Generating Conditional Unsigned Distance Fields with Optimal Wavelet Diffusion2404.06851v1 · Junsheng Zhou, Weiqi Zhang, Baorui Ma et al.2024 · 17 citationsarXiv
Learning Continuous Implicit Field with Local Distance Indicator for Arbitrary-Scale Point Cloud Upsampling2312.15133v1 · Shujuan Li, Junsheng Zhou, Baorui Ma et al.2023 · 28 citationsarXiv
Differentiable Registration of Images and LiDAR Point Clouds with VoxelPoint-to-Pixel Matching2312.04060v1 · Junsheng Zhou, Baorui Ma, Wenyuan Zhang et al.2023 · 21 citationsarXiv
GeoDream: Disentangling 2D and Geometric Priors for High-Fidelity and Consistent 3D Generation2311.17971v2 · Baorui Ma, Haoge Deng, Junsheng Zhou et al.2023 · 6 citationsarXiv
Uni3D: Exploring Unified 3D Representation at Scale2310.06773v1 · Junsheng Zhou, Jinsheng Wang, Baorui Ma et al.2023 · 9 citationsarXiv
Learning a More Continuous Zero Level Set in Unsigned Distance Fields through Level Set Projection2308.11441v1 · Junsheng Zhou, Baorui Ma, Shujuan Li et al.2023 · 43 citationsarXiv
Learning Signed Distance Functions from Noisy 3D Point Clouds via Noise to Noise Mapping2306.01405v1 · Baorui Ma, Yu-Shen Liu, Zhizhong Han2023 · 3 citationsarXiv
Towards Better Gradient Consistency for Neural Signed Distance Functions via Level Set Alignment2305.11601v1 · Baorui Ma, Junsheng Zhou, Yu-Shen Liu et al.2023 · 42 citationsarXiv
NeAF: Learning Neural Angle Fields for Point Normal Estimation2211.16869v1 · Shujuan Li, Junsheng Zhou, Baorui Ma et al.2022 · 41 citationsarXiv
Surface Reconstruction from Point Clouds by Learning Predictive Context Priors2204.11015v1 · Baorui Ma, Yu-Shen Liu, Matthias Zwicker et al.2022 · 78 citationsarXiv
Reconstructing Surfaces for Sparse Point Clouds with On-Surface Priors2204.10603v1 · Baorui Ma, Yu-Shen Liu, Zhizhong Han2022 · 78 citationsarXiv
3D-OAE: Occlusion Auto-Encoders for Self-Supervised Learning on Point Clouds2203.14084v3 · Junsheng Zhou, Xin Wen, Baorui Ma et al.2022 · 15 citationsarXiv
Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfaces2011.13495v2 · Baorui Ma, Zhizhong Han, Yu-Shen Liu et al.2020 · 61 citationsarXiv
Reconstructing 3D Shapes from Multiple Sketches using Direct Shape Optimization.32870791 · Han, Zhizhong, Ma, Baorui, Liu, Yu-Shen et al.2024 · 50 citationsIEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 2020;PP
Career total: 35 works. 26 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.