Machine Learning for 3D Data Processing
As three-dimensional (3D) vision data can provide abundant spatial information, it is being widely used in many areas, including autonomous driving and mobile robots. We aim to develop efficient and accurate 3D data processing techniques for classification, segmentation, pose estimation, etc.
![[C106] ACA-GS: Adaptive-Capacity Anchored Gaussian Splatting for Compact Dynamic Radiance Fields](/publication/c106_acm_mm_2026/featured_hu3f9edee44762da83cc5dfb783fac784f_164969_150x0_resize_q75_h2_lanczos_3.webp)
![[J35] RUSH: Recursive and Scalable 3D Coarse To Fine Path Planning](/publication/j35_ieee-ra-l_2026/featured_huc1ea2439b331c74724339a42511d6847_221349_150x0_resize_q75_h2_lanczos_3.webp){kind=small}
![[C85] Optimized Minimal 3D Gaussian Splatting](/publication/c85_neurips_2025/featured_hu73c7476fefbc8540ace24a63d65f02e0_2817743_150x0_resize_q75_h2_lanczos_3.webp)
![[C67] F-3DGS: Factorized Coordinates and Representations for 3D Gaussian Splatting](/publication/c67_acm_2024/featured_hu5a2a7205ae7f4448336179c250301291_140424_150x0_resize_q75_h2_lanczos.webp)
![[C66] HandDAGT: A Denoising Adaptive Graph Transformer for 3D Hand Pose Estimation](/publication/c66_eccv_2024_hand/featured_hu517eb54f6d0ca4f24b50120b9dde9d8e_108644_150x0_resize_q75_h2_lanczos.webp){kind=small}
![[C63] A Hybrid Precision Network with Efficient Processing Elements for 3D Hand Pose Estimation](/publication/c63_isocc_2024_hand/featured_huc5182e23574aefa0b9d566b5cf77994c_59133_150x0_resize_q75_h2_lanczos_3.webp)
![[C61] HandDiff: 3D Hand Pose Estimation with Diffusion on Image-Point Cloud](/publication/c61_cvpr_2024_hand/featured_hu6f0f7d1e39cc9571e441f280fc5b81b7_92954_150x0_resize_q75_h2_lanczos_3.webp)
![[C60] Compact 3D Gaussian Representation for Radiance Field](/publication/c60_cvpr_2024/featured_hu07f1dacca0e701ff33150a4fba1491a7_720675_150x0_resize_q75_h2_lanczos.webp){kind=small}
![[C54]Coordinate-Aware Modulation for Neural Fields](/publication/c54_iclr_2024/featured_huf973761d8efb8b2cd62d9bc2734c9a2d_272436_150x0_resize_q75_h2_lanczos_3.webp){kind=small}
![[C52] Mip-Grid: Anti-aliased Grid Representations for Neural Radiance Fields](/publication/c52_nips_2023/featured_hud88947c53ae862c46bcfe1a5042b256b_505844_150x0_resize_q75_h2_lanczos_3.webp)
![[C49] Multi-Scale Bidirectional Recurrent Network with Hybrid Correlation for Point Cloud Based Scene Flow Estimation](/publication/c49_iccv_2023/featured_hu154ba78a02c57d2179791e271d6b0716_2931168_150x0_resize_q75_h2_lanczos_3.webp)
![[C48] HandR2N2: Iterative 3D Hand Pose Estimation Using a Residual Recurrent Neural Network](/publication/c48_iccv_2023/featured_hu475d33d5dd777ca67f63823c2a1a6be9_999485_150x0_resize_q75_h2_lanczos_3.webp)
![[C43] Dynamic Inference Acceleration of 3D Point Cloud Deep Neural Networks Using Point Density and Entropy](/publication/c43_cvprw_2023/featured_hu1c9933325cfefdc0eec3bf2647fbc08d_389324_150x0_resize_q75_h2_lanczos_3.webp)
![[C41] Masked Wavelet Representation for Compact Neural Radiance Fields](/publication/c41_cvpr_2023/featured_hua6678f696dd195d9e2934608c163c38c_106243_150x0_resize_q75_h2_lanczos_3.webp)
![[C36] Bi-PointFlowNet: Bidirectional Learning for Point Cloud Based Scene Flow Estimation](/publication/c36_eccv_2022/Featured_hua6724a628a2e70fd2206b7e039d540e0_267845_150x0_resize_q75_h2_lanczos.webp)
![[C31] HandFoldingNet: A 3D Hand Pose Estimation Network Using Multiscale-Feature Guided Folding of a 2D Hand Skeleton](/publication/c31_iccv_2021/Featured_hu6aef2193e6bece41bd2a0e680fa624e7_108849_150x0_resize_q75_h2_lanczos.webp)
![[C28] A Sub-Milliwatt and Sub-Millisecond 3-D GazeEstimator for Ultra Low-Power AR Applications](/publication/c28_eyeware_2021/Featured_hu6aef2193e6bece41bd2a0e680fa624e7_234065_150x0_resize_q75_h2_lanczos.webp)
![[J10] Segmentation of Points in the Future: Joint Segmentation and Prediction of a Point Cloud](/publication/j10_access_2021/featured_hu2dd439b07f37e1b018942b5db1ee4b9f_88120_150x0_resize_q75_h2_lanczos.webp)