通知：联邦节假日调休：哥伦布日 / 原住民日（Columbus Day / Indigenous Peoples' Day），今日（13日）无更新。通知：联邦节假日调休：哥伦布日 / 原住民日（Columbus Day / Indigenous Peoples' Day），今日（13日）无更新。
arXiv 2510.15072cs.CV
SaLon3R：基于未标定图像的结构感知长期可泛化三维重建
SaLon3R: Structure-aware Long-term Generalizable 3D Reconstruction from Unposed Images
The Chinese University of Hong Kong（香港中文大学）；Hong Kong Center for Logistics Robotics（香港物流机器人中心）；University of California, Berkeley（加州大学伯克利分校）；Zhejiang University（浙江大学）
Recent advances in 3D Gaussian Splatting (3DGS) have enabled generalizable, on-the-fly reconstruction of sequential input views. However, existing methods often predict per-pixel Gaussians and combine Gaussians from all views as the scene representation, leading to substantial redundancies and geometric inconsistencies in long-duration video sequences. To address this, we propose SaLon3R, a novel framework for Structure-aware, Long-term 3DGS Reconstruction. To our best knowledge, SaLon3R is the first online generalizable GS method capable of reconstructing over 50 views in over 10 FPS, with 50% to 90% redundancy removal. Our method introduces compact anchor primitives to eliminate redundancy through differentiable saliency-aware Gaussian quantization, coupled with a 3D Point Transformer that refines anchor attributes and saliency to resolve cross-frame geometric and photometric inconsistencies. Specifically, we first leverage a 3D reconstruction backbone to predict dense per-pixel Gaussians and a saliency map encoding regional geometric complexity. Redundant Gaussians are compressed into compact anchors by prioritizing high-complexity regions. The 3D Point Transformer then learns spatial structural priors in 3D space from training data to refine anchor attributes and saliency, enabling regionally adaptive Gaussian decoding for geometric fidelity. Without known camera parameters or test-time optimization, our approach effectively resolves artifacts and prunes the redundant 3DGS in a single feed-forward pass. Experiments on multiple datasets demonstrate our state-of-the-art performance on both novel view synthesis and depth estimation, demonstrating superior efficiency, robustness, and generalization ability for long-term generalizable 3D reconstruction. Project Page: https://wrld.github.io/SaLon3R/.
PanoSplatt3R: Leveraging Perspective Pretraining for Generalized Unposed Wide-Baseline Panorama Reconstruction
School of Electronics and Information, Northwestern Polytechnical University and Shaanxi Key Laboratory of Information Acquisition and Processing（电子工程学院、西北工业大学和陕西省信息获取与处理重点实验室）
EvTrajGS: Accurate and Efficient 3D Gaussian Splatting from Unposed Event Streams
School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机科学与工程学院）；Guangdong Province Key Laboratory of Information Security Technology（广东省信息安全技术重点实验室）；Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education（机器智能与先进计算教育部重点实验室）；College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）；School of Computing and Information Technology, Great Bay University（大湾区大学计算与信息技术学院）
NOVA3R: Non-pixel-aligned Visual Transformer for Amodal 3D Reconstruction
Technical University of Munich（慕尼黑技术大学）；Munich Center for Machine Learning（慕尼黑机器学习中心）；University of Oxford（牛津大学）；Nanyang Technological University（南洋理工大学）
We present StrobeNet, a method for category-level 3D reconstruction of articulating objects from one or more unposed RGB images. Reconstructing general articulating object categories % has important applications, but is challenging since objects can have wide variation in shape, articulation, appearance and topology. We address this by building on the idea of category-level articulation canonicalization -- mapping observations to a canonical articulation which enables correspondence-free multiview aggregation. Our end-to-end trainable neural network estimates feature-enriched canonical 3D poin…
Unposed Sparse Views Room Layout Reconstruction in the Age of Pretrain Model
Hong Kong Center for Construction Robotics, The Hong Kong University of Science and Technology（香港科技大学香港建造机器人中心）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Astribot；Intellifusion Inc.（云天励飞公司）；MMLab, The Chinese University of Hong Kong（香港中文大学MMLab实验室）
Unconstrained Large-scale 3D Reconstruction and Rendering across Altitudes
The Johns Hopkins University Applied Physics Laboratory（约翰·霍普金斯大学应用物理实验室）；Department of Computer Science, The Johns Hopkins University（约翰·霍普金斯大学计算机科学系）
ShanghaiTech University（上海科技大学）；University of California, San Diego（加利福尼亚大学圣迭戈分校）；Adobe Research（Adobe研究院）
We present MVSNeRF, a novel neural rendering approach that can efficiently reconstruct neural radiance fields for view synthesis. Unlike prior works on neural radiance fields that consider per-scene optimization on densely captured images, we propose a generic deep neural network that can reconstruct radiance fields from only three nearby input views via fast network inference. Our approach leverages plane-swept cost volumes (widely used in multi-view stereo) for geometry-aware scene reasoning, and combines this with physically based volume rendering for neural radiance field reconstruction. W…
REArtGS++: Generalizable Articulation Reconstruction with Temporal Geometry Constraint via Planar Gaussian Splatting
Hefei Institutes of Physical Science, Chinese Academy of Sciences（合肥物理科学研究院，中国科学院）；University of Science and Technology of China（中国科学技术大学）；Hefei University of Technology（合肥工业大学）；RoboticsX, Tencent（腾讯机器人院）；Shanghai Jiao Tong University（上海交通大学）
Stereo-GS: Multi-View Stereo Vision Model for Generalizable 3D Gaussian Splatting Reconstruction
Department of Computer Science, Hong Kong Baptist University（香港 Baptist 大学计算机科学系）；NVIDIA AI Technology Center, NVIDIA（NVIDIA 人工智能技术中心）；School of Control Science and Engineering, Shandong University（控制科学与工程学院，山东大学）
Dental3R: Geometry-Aware Pairing for Intraoral 3D Reconstruction from Sparse-View Photographs
School of AI and Advanced Computing, Xi'an Jiaotong-Liverpool University, China（人工智能与先进计算学院，西安交通大学利物浦大学，中国）；School of Electrical Engineering, Electronics and Computer Science, University of Liverpool, United Kingdom（电子工程与计算机科学学院，利物浦大学，英国）；School of Advanced Technology, Xi'an Jiaotong-Liverpool University, China（先进技术学院，西安交通大学利物浦大学，中国）；School of Physical Sciences, University of Liverpool, Liverpool, United Kingdom（物理科学学院，利物浦大学，英国）；School of Mathematics and Physics, Xi'an Jiaotong-Liverpool University, China（数学与物理学院，西安交通大学利物浦大学，中国）；Institute of Artificial Intelligence Innovation, Zhejiang University of Technology, China（人工智能创新研究院，浙江工业大学，中国）
MVSGaussian: Fast Generalizable Gaussian Splatting Reconstruction from Multi-View Stereo
Great Bay University（湾谷大学）；Huazhong University of Science and Technology（华中科技大学）；Nanyang Technological University（南洋理工大学）；Shanghai AI Laboratory（上海人工智能实验室）
Depth-Guided Bundle Sampling for Efficient Generalizable Neural Radiance Field Reconstruction
Key Laboratory of Media Audio and Video (Communication University of China), Ministry of Education（媒体音频与视频重点实验室（中国传媒大学），教育部）；School of Electronic Science and Engineering, Nanjing University（南京大学电子科学与工程学院）
针对可泛化神经辐射场渲染计算量大、采样冗余的问题，提出深度引导的束采样策略，通过分组采样和自适应分配采样点，在DTU数据集上实现1.27 dB PSNR提升和47% FPS增加，并达到2倍渲染加速。
H3R: Hybrid Multi-view Correspondence for Generalizable 3D Reconstruction
ReLER Lab, CCAI, Zhejiang University（浙江大学ReLER实验室，中国计算机协会，浙江大学）；The State Key Lab of Brain-Machine Intelligence, Zhejiang University（浙江大学脑机智能国家重点实验室）；Singapore University of Technology and Design（新加坡科技设计大学）
