Boosting Multi-View Indoor 3D Object Detection via Adaptive 3D Volume Construction
College of Information Science and Electronic Engineering, Zhejiang University（浙江大学信息科学与电子工程学院）；Ningbo Global Innovation Center, Zhejiang University（浙江大学宁波全球创新中心）；NingboTech University（宁波科技学院）；City University of Hong Kong（香港城市大学）
This work presents SGCDet, a novel multi-view indoor 3D object detection framework based on adaptive 3D volume construction. Unlike previous approaches that restrict the receptive field of voxels to fixed locations on images, we introduce a geometry and context aware aggregation module to integrate geometric and contextual information within adaptive regions in each image and dynamically adjust the contributions from different views, enhancing the representation capability of voxel features. Furthermore, we propose a sparse volume construction strategy that adaptively identifies and selects voxels with high occupancy probabilities for feature refinement, minimizing redundant computation in free space. Benefiting from the above designs, our framework achieves effective and efficient volume construction in an adaptive way. Better still, our network can be supervised using only 3D bounding boxes, eliminating the dependence on ground-truth scene geometry. Experimental results demonstrate that SGCDet achieves state-of-the-art performance on the ScanNet, ScanNet200 and ARKitScenes datasets. The source code is available at https://github.com/RM-Zhang/SGCDet.
Boosting Convolution with Efficient MLP-Permutation for Volumetric Medical Image Segmentation
Department of Computer Science and Engineering（计算机科学与工程系）；The Hong Kong University of Science and Technology（香港科学与技术大学）；HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute（HKUST深圳-香港协同创新研究院）
A Real-Time Online Learning Framework for Joint 3D Reconstruction and Semantic Segmentation of Indoor Scenes
ETH Zürich（苏黎世联邦理工学院）；CVL, ETH Zürich（苏黎世联邦理工学院计算机视觉实验室）；PSI, KU Leuven（鲁汶大学）；CVG Group at ETH Zürich（苏黎世联邦理工学院计算机视觉与几何组）；Google Research Zürich（谷歌苏黎世研究院）
Contextual Embedding Learning to Enhance 2D Networks for Volumetric Image Segmentation
Shenzhen University（深圳大学）；Shenzhen University Medical School（深圳大学医学院）；School of Biomedical Engineering（生物医学工程学院）；Huawei Cloud Computing Technologies Company Limited（华为云计算技术有限公司）；Shenzhen University General Hospital（深圳大学总医院）
NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo
Department of Automation, Tsinghua University（清华大学自动化系）；State Key Lab of Intelligent Technologies and Systems（智能技术与系统国家重点实验室）；ETH Zurich（苏黎世联邦理工学院）；Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）
Image-Plane Geometric Decoding for View-Invariant Indoor Scene Reconstruction
School of Microelectronics,Tianjin University（天津大学微电子学院）；College of Electronic Information and Optical Engineering,Nankai University（南开大学电子信息与光工程学院）；Technology Research Institute of MEM（MEM技术研究所）
Boosting Point Clouds Rendering via Radiance Mapping
Shanghai Jiao Tong University（上海交通大学）；Anhui University（安徽大学）；Shanghai AI Lab（上海人工智能实验室）
近几年来，基于NeRF的图像绘制技术由于其高质量的特性得到了迅速的发展。然而，点云渲染在某种程度上较少探索。与基于NeRF的渲染相比，其遭受密集空间采样，点云渲染的计算强度自然较低，这使得其能够部署在移动计算设备中。在这项工作中，我们专注于提高点云渲染的图像质量与紧凑的模型设计。首先分析了体渲染公式在点云上的适应性。基于分析，我们简化了NeRF表示的空间映射函数，它只需要单个评估每个像素。此外，受光线行进的启发，我们将噪声的原始点云校正为光线与表面之间的估计交点作为查询坐标，这可以避免\textit{spatial frequency collapse}和相邻点的干扰。由光栅化，空间映射和细化阶段组成，我们的方法实现了最先进的点云渲染性能，以显着的利润率优于以前的作品，具有较小的模型尺寸。我们在NeRF-Synthetic上获得了31.74的PSNR，在ScanNet上获得了25.88的PSNR，在DTU上获得了30.81的PSNR。代码和数据可在https://github.com/seanywang0408/RadianceMapping上公开获取。
VoxScene: Anchor-Conditioned Voxel Diffusion for Indoor Scene Arrangement
Shanghai Jiao Tong University（上海交通大学）；Hong Kong University of Science and Technology（香港科技大学）；Tsinghua University（清华大学）；University of Cambridge（剑桥大学）；Peking University（北京大学）
FLM-Occ: Feed-forward Likelihood Maximization for Efficient Indoor Occupancy Prediction
Southern University of Science and Technology（南方科技大学）；Guangdong Laboratory of Artificial Intelligence and Digital Economy (Shenzhen)（广东省人工智能与数字经济实验室（深圳））；Shenzhen Key Laboratory of Robotics and Computer Vision（深圳市机器人视觉与感知重点实验室）
Incremental Dense Reconstruction from Monocular Video with Guided Sparse Feature Volume Fusion
Technical University of Munich（慕尼黑工业大学）；Munich Center for Machine Learning（慕尼黑机器学习中心）；University of Delaware（特拉华大学）；Imperial College London（帝国理工学院）；University of Toronto（多伦多大学）；Munich Institute of Robotics and Machine Intelligence（慕尼黑机器人与机器学习研究所）
Fine-Tuned Vision Transformers Capture Complex Wheat Spike Morphology for Volume Estimation from RGB Images
ETH Zurich, Institute of Agricultural Science（苏黎世联邦理工学院农业科学研究所）；ETH Zurich, Department of Computer Science（苏黎世联邦理工学院计算机科学系）；ETH Zurich, Department of Mechanical and Process Engineering（苏黎世联邦理工学院机械与过程工程系）
2.75D: Boosting learning by representing 3D Medical imaging to 2D features for small data
Netherlands Cancer Institute（荷兰癌症研究所）；Erasmus Medical Center Rotterdam（鹿特丹伊拉斯姆斯医学中心）；Radboud University Medical Center（拉德堡德大学医学中心）；Southern University of Science and Technology（南方科技大学）；Aberystwyth University（阿伯里斯特威斯大学）
