Basis Decomposition

Follow this topic Ask about this topic

Momentum

1 paper in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 18

All topics

NIDAR: NIR-Guided Intrinsic Decomposition for Scalable Scene-Agnostic LiDAR Intensity Reconstruction
Sep 29, 2026Junjie Zhang, Jie Yin, Kefei Qian +5Scene Reconstruction Infrared
Chongqing University · Shanghai Jiao Tong University · Ministry of Industry and Information Technology +1
Quality-Constrained Routing over a Fixed Pool of Quantized Mixture-of-Experts Instances
Sep 14, 2026Zhenghong Huang, Hongfan Wu, Jiheng ZhangLarge Language Model Routing Basis Decomposition
The Hong Kong University of Science and Technology Clear Water Bay, Kowloon, Hong Kong
Algebraic Decomposition Theory for Transformer Length Generalization
Aug 13, 2026Andy Yang, Blerta Veseli, Corentin Barloy +5Transformer Architectures Language Modeling
University of Notre Dame · 2Saarland University · 3Ruhr University Bochum +4
Low-Rank Dependence Decomposition via Accelerated Symmetric Non-negative Matrix Factorization
Jul 27, 2026Lavinia Ghita, Dhruv Desai, Jake Goldberg +1Nonnegative Matrix Factorization Matrix
NVIDIA
The Zero Pattern of a Design Matrix Drives Multiple Descent in Over-parameterized Regression
Jul 27, 2026Kevin Han Huang, Haoyu Ye, Somak Laha +1Overparameterization Covariance
University of Warwick · Harvard University
Program-Synthesis-Driven Autodesign of Universal Unitary Operators
Jul 11, 2026Yifei Zhang, Dong Chen, Fan Wang +6Basis Decomposition Llm-Driven Code Synthesis
Key Laboratory of Nuclear Physics and Ion-beam Application (MOE), Institute of Modern Physics, Fudan University, Shanghai 200433, China · Huawei Technologies Co., Ltd, Beijing 100095, China · Department of Industrial Engineering and Decision Analytics, Hong Kong University of Science and Technology, HongKong, China +6
Intrinsic decomposition and editing of 3D Gaussian splats
Jun 30, 2026Alexandre Lanvin, Jeffrey Hu, Simon Lucas +2Image Editing Basis Decomposition
Inria, Université Côte d’Azur, France · Cambridge University, United Kingdom
Beyond Additive Decompositions: Interpretability Through Separability
May 29, 2026Jinyang Liu, Munir Eberhardt HiabuShapley Additive Explanations Interpretability
Department of Mathematical Sciences, University of Copenhagen, Denmark.
MuellerPT: Decomposition Driven Pretraining for Dense Learning in Mueller Polarimetry
May 22, 2026Adam Tlemsani, Yingdian Li, Maxime Giot +4Multiple Instance Learning Hyperspectral Image
Department of Computing, Imperial College London · Hamlyn Centre for Robotic Surgery, Imperial College London · Department of Surgery and Cancer, Imperial College London +2
Generalized Functional ANOVA in Closed-Form: A Unified View of Additive Explanations
May 18, 2026Baptiste Ferrere, Nicolas Bousquet, Fabrice Gamboa +1Shapley Additive Explanations Explainability
EDF R&D, SINCLAIR Lab · Université de Toulouse · Sorbonne Université +2
ODRPO: Ordinal Decompositions of Discrete Rewards for Robust Policy Optimization
May 12, 2026Nirmal Patel, Fei Wang, Inderjit S. DhillonMulti-Dimensional Evaluation Basis Decomposition
University of Texas at Austin · Google
Relations Are Channels: Knowledge Graph Embedding via Kraus Decompositions
May 11, 2026Sayan Kumar ChakiKnowledge Graph Embeddings Knowledge Graphs
Inria, Laboratoire Hubert Curien, Université Jean Monnet
Core-Halo Decomposition: Decentralizing Large-Scale Fixed-Point Problems
May 9, 2026Haixiang, Yang Xu, Jiefu Zhang +4Decentralized Autonomous Organization Fixed-Point Iteration
Purdue University · The University of Hong Kong · Johns Hopkins University
CARD: Coarse-to-fine Autoregressive Modeling with Radix-based Decomposition for Transferable Free Energy Estimation
May 4, 2026Ziyang Yu, Yi He, Wenbing Huang +2Free Energy Principle Molecular Dynamics
ByteDance Seed · Department of Computer Science and Technology, Tsinghua University · Institute for AI Industry Research (AIR), Tsinghua University +2
PEPS: Positional Encoding Projected Sampling -- Extended
Apr 27, 2026Guillaume Perez, Janarbek Matai, Takahiro HaradaPositional Encoding Neural Representations
Advanded Micro Devices
Analytical Extraction of Conditional Sobol' Indices via Basis Decomposition of Polynomial Chaos Expansions
Apr 21, 2026Shijie Zhong, Jiangfeng FuUncertainty Quantification Basis Decomposition
School of Power and Energy Northwestern Polytechnical University Xi’an, Shanxi 710129
KANFIS: A Neuro-Symbolic Framework for Interpretable and Uncertainty-Aware Learning
Feb 3, 2026Binbin Yong, Haoran Pei, Jun Shen +3Fuzzy Kolmogorov-Arnold Networks
School of Information Science and Engineering, Lanzhou University, China · School of Computing and Information Technology, University of Wollongong, Australia · Department of Data Science and Artificial Intelligence, Monash University, Australia
Accelerating Attention with Basis Decomposition
Oct 2, 2025Jialin ZhaoDynamic Attention Deepseek
Department of Computer Science Tsinghua University

Sep 29, 2026, cs.ROJ/K move · Enter open · S save

NIDAR: NIR-Guided Intrinsic Decomposition for Scalable Scene-Agnostic LiDAR Intensity Reconstruction

Junjie Zhang, Jie Yin, Kefei Qian, Jie Li+4

Chongqing University · Shanghai Jiao Tong University · Ministry of Industry and Information Technology+1

Scene Reconstruction Infrared Rgb-Depth Cameras Intensity Simultaneous Localization And Mapping Basis Decomposition

Open paper AskPDF arXiv

LiDAR return intensity provides complementary surface-response cues for robotic perception and state estimation, yet many simulation pipelines omit it or reproduce it using reconstruction methods that require real intensity supervision and per-scene optimization. These requirements increase data-collection and fitting costs and limit reuse across simulated scenes. We present NIDAR, a feed-forward framework that synthesizes dense intensity-like observations from RGB appearance and simulator geometry. NIDAR combines pretrained pseudo-NIR translation, hierarchical intrinsic decomposition, geometry-aware modulation, and source-domain distribution calibration to transfer reflectance-related image cues to simulated point clouds. Its learned components are trained offline using Waymo data; their weights and calibration remain fixed during evaluation on Waymo and nuScenes. Deployment therefore requires neither target-scene intensity labels nor target-scene gradient-based fitting. The reported comparisons show competitive pixel-wise accuracy and favorable structural and perceptual fidelity against the evaluated reconstruction baselines. A controlled pseudo-NIR-versus-RGB diagnostic further shows that the pseudo-NIR prior is most beneficial when used through the paper-aligned reflectance-and-remapping route, rather than as a simple direct intensity regressor. We further integrate NIDAR with Unreal Engine 5, Isaac Sim, and a generative LiDAR pipeline. Two intensity-aware SLAM systems evaluated in two simulated indoor scenes suggest potential downstream utility, but do not constitute real-robot validation. NIDAR therefore offers a scalable intensity-synthesis interface for the evaluated settings; cross-wavelength, camera-configuration, embedded, and real-sensor validation remain future work.

Momentum

Related topics

Latest papers 18