Yu G

on the atlas — 31

• MMHal Bench1 savers
• DyniBar1 savers
• VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimation1 savers
• Fast Complementary Dynamics1 savers
• Simplicits: Mesh-Free, Geometry-Agnostic, Elastic Simulation1 savers
• [2403.14530] HAC: Hash-grid Assisted Context for 3D Gaussian Splatting Compression1 savers
• 3D Gaussian Splatting as Markov Chain Monte Carlo1 savers
• S4D1 savers
• Zero-Shot Knowledge Distillation in Deep Networks1 savers
• Box2Mask: Weakly Supervised 3D Semantic Instance Segmentation Using Bounding Boxes1 savers
• Amodal Detection of 3D Objects: Inferring 3D Bounding Boxes from 2D Ones in RGB-Depth Images1 savers
• 3D Object Detection via 2D Segmentation-Based Computational Integral Imaging Applied to a Real Video - PMC1 savers
• 3D object detection: Learning 3D bounding boxes from scaled down 2D bounding boxes in RGB-D images - ScienceDirect1 savers
• 2D Amodal Instance Segmentation Guided by 3D Shape Prior1 savers
• Generate a 3D BoundingBox from 2D Segmentation · Issue #4929 · isl-org/Open3D · GitHub1 savers
• Object recognition based on convex hull alignment - ScienceDirect1 savers
• Enhancing 3D Object Detection with 2D Detection-Guided Query Anchors1 savers
• 3D Object Localisation from Multi-view Image Detections1 savers
• Monocular 3D object detection using dual quadric for autonomous driving - ScienceDirect1 savers
• Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboids1 savers
• 3D-Aware Ellipse Prediction for Object-Based Camera Pose Estimation1 savers
• Abstract representations for interactive visualization of virtual 3D city models - ScienceDirect1 savers
• Unsupervised Object-Oriented 3D Scene Representation and Rendering1 savers
• Learning 3D object-centric representation through prediction1 savers
• Convex hull, Image processing, Image Classification, Image retrieval, Shape detection1 savers
• IEEE Xplore Full-Text PDF:36 savers
• [2310.08586] PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm2 savers
• 3D-LFM: Lifting Foundation Model1 savers
• Habitat-Matterport 3D Semantics Dataset1 savers
• Curius / Onboarding2621 savers
• Curius / Bookmarks for the extremely curious182 savers

highlights — 2

• press. He went over to his grandfather who was a grocer and he read the progressi

  Curius / Onboarding

• Learning accurate and efficient 3D shape representations is crucial for many cutting-edge applica- tions in the fields of machine vision and robotics. Recent advances in 3D coordinate-based neural representations including occupancy fields (OF) [ 46 ; 11 ], un/signed distance fields (U/SDF) [ 54 ; 14 ], and radiance fields (NeRF) [ 47 ], have shown great potential to recover complex shapes from RGB/D images and/or point clouds. Although these methods and their variants have achieved excellent performance in a wide range of downstream tasks such as shape reconstruction [ 55 ; 58 ; 60 ], novel v…

  RayDF: Neural Ray-surface Distance Fields with Multi-view Consistency