Neural surfaces learning has shown impressive performance in multi-view surface reconstruction. However, most existing methods use large multilayer perceptrons (MLPs) to train their models from scratch, resulting in hours of training for a single scene. Recently, how to accelerate the neural surfaces learning has received a lot of attention and remains an open problem. In this work, we propose a prior-based residual learning paradigm for fast multi-view neural surface reconstruction. This paradigm consists of two optimization stages. In the first stage, we propose to leverage generalization models to generate a basis signed distance function (SDF) field. This initial field can be quickly obtained by fusing multiple local SDF fields produced by generalization models. This provides a coarse global geometry prior. Based on this prior, in the second stage, a fast residual learning strategy based on hash-encoding networks is proposed to encode an offset SDF field for the basis SDF field. Moreover, we introduce a prior-guided sampling scheme to help the residual learning stage converge better, and thus recover finer structures. With our designed paradigm, experimental results show that our method only takes about 3 minutes to reconstruct the surface of a single scene, while achieving competitive surface quality. Our code will be released upon publication.
RNb-NeuS: Reflectance and Normal-based Multi-View 3D Reconstruction
IRIT, UMR CNRS 5505(法国国家科学研究中心IRIT联合研究单位);Normandie Univ, UNICAEN, ENSICAEN, CNRS, GREYC(诺曼底大学、卡昂大学、卡昂高等工程师学院、法国国家科学研究中心GREYC联合研究单位);Balgrist Hospital, University of Zurich(苏黎世大学巴尔格里斯医院);OR-X
IT-TextFusion: Iterative Text-Image Interaction with Text-Guided Residual Refinement for Degradation-Aware Image Fusion
School of Automation, Southeast University(东南大学自动化学院);Chair of Robotics, Artificial Intelligence and Real-time Systems, Technical University of Munich(慕尼黑工业大学机器人、人工智能与实时系统研究所)
SynA-ResNet: Spike-driven ResNet Achieved through OR Residual Connection
School of Software, Liaoning Technical University(辽宁工程技术大学软件学院);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);University of California, Santa Cruz(加州大学圣克鲁兹分校);University of Electronic Science and Technology of China(电子科技大学)
Low-Light Video Enhancement with An Effective Spatial-Temporal Decomposition Paradigm
Department of Computer Science and Engineering, The Chinese University of Hong Kong(计算机科学与工程系,香港中文大学);Shenzhen University(深圳大学);The University of Hong Kong(香港大学);camera group of DJI(大疆创新相机组);Zhejiang Normal University(浙江师范大学)
Volume Rendering with Metric--Phase Fields for Thin Structures and Sign-Ambiguous Geometry
College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算与数据科学学院);Institute of Software, Chinese Academy of Sciences(中国科学院软件研究所);University of Chinese Academy of Sciences(中国科学院大学);City University of Hong Kong(香港城市大学);Texas A&M University(德克萨斯农工大学)
Neural Diffeomorphic-Neural Operator for Residual Stress-Induced Deformation Prediction
College of Mechanical and Electrical Engineering, Nanjing University of Aeronautics and Astronautics(南京航空航天大学机电学院);School of Mechanical and Aerospace Engineering, Queen's University Belfast(贝尔法斯特女王大学机械与航空航天工程学院)
Self-Auditing Residual Drifting for Pathology-Preserving Accelerated Knee MRI
Department of Radiology & Biomedical Imaging, Yale School of Medicine(放射学与生物医学成像系,耶鲁医学院);Department of Biomedical Engineering, Rensselaer Polytechnic Institute(生物医学工程系,伦塞拉尔理工学院)