{"total":106,"rows":[{"id":"2311.04400","title":"LRM: Large Reconstruction Model for Single Image to 3D","created":"2023-11-08","cited_by_count":849,"area":null},{"id":"2203.03570","title":"Kubric: A scalable dataset generator","created":"2022-03-07","cited_by_count":381,"area":null},{"id":"2110.06199","title":"ABO: Dataset and Benchmarks for Real-World 3D Object Understanding","created":"2021-10-12","cited_by_count":366,"area":null},{"id":"2302.12251","title":"VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion","created":"2023-02-23","cited_by_count":313,"area":null},{"id":"2104.03110","title":"Neural Articulated Radiance Field","created":"2021-04-07","cited_by_count":196,"area":null},{"id":"2302.10109","title":"NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusion","created":"2023-02-20","cited_by_count":180,"area":null},{"id":"2110.07604","title":"NeRS: Neural Reflectance Surfaces for Sparse-view 3D Reconstruction in the Wild","created":"2021-10-14","cited_by_count":136,"area":null},{"id":"2212.03293","title":"Diffusion-SDF: Text-to-Shape via Voxelized Diffusion","created":"2022-12-06","cited_by_count":128,"area":null},{"id":"2306.07881","title":"Viewset Diffusion: (0-)Image-Conditioned 3D Generative Models from 2D Data","created":"2023-06-13","cited_by_count":113,"area":"diffusion"},{"id":"2112.02789","title":"HumanNeRF: Efficiently Generated Human Radiance Field from Sparse Inputs","created":"2021-12-06","cited_by_count":112,"area":null},{"id":"2402.12712","title":"MVDiffusion++: A Dense High-resolution Multi-view Diffusion Model for Single or Sparse-view 3D Object Reconstruction","created":"2024-02-20","cited_by_count":95,"area":"diffusion"},{"id":"2107.12512","title":"H3D-Net: Few-Shot High-Fidelity 3D Head Reconstruction","created":"2021-07-26","cited_by_count":81,"area":null},{"id":"2207.12298","title":"Deforming Radiance Fields with Cages","created":"2022-07-25","cited_by_count":78,"area":null},{"id":"2505.00702","title":"RayZer: A Self-supervised Large View Synthesis Model","created":"2025-05-01","cited_by_count":77,"area":null},{"id":"2301.08247","title":"Multiview Compressive Coding for 3D Reconstruction","created":"2023-01-19","cited_by_count":71,"area":null},{"id":"2103.16552","title":"Unsupervised Learning of 3D Object Categories from Videos in the Wild","created":"2021-03-30","cited_by_count":67,"area":null},{"id":"2102.06195","title":"Shelf-Supervised Mesh Prediction in the Wild","created":"2021-02-11","cited_by_count":65,"area":null},{"id":"2112.05143","title":"GAN-Supervised Dense Visual Alignment","created":"2021-12-09","cited_by_count":62,"area":null},{"id":"2210.08061","title":"Motion Inspired Unsupervised Perception and Prediction in Autonomous Driving","created":"2022-10-14","cited_by_count":59,"area":null},{"id":"2105.06663","title":"Sketch2Model: View-Aware 3D Modeling from Single Free-Hand Sketches","created":"2021-05-14","cited_by_count":54,"area":null},{"id":"2212.04492","title":"Few-View Object Reconstruction with Unknown Categories and Camera Poses","created":"2022-12-08","cited_by_count":53,"area":null},{"id":"2103.15627","title":"Learning Generative Models of Textured 3D Meshes from Real-World Images","created":"2021-03-29","cited_by_count":44,"area":null},{"id":"2405.10255","title":"When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Models","created":"2024-05-16","cited_by_count":43,"area":"mllm"},{"id":"2203.10339","title":"Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimation","created":"2022-03-19","cited_by_count":34,"area":null},{"id":"2206.04942","title":"Neural Template: Topology-aware Reconstruction and Disentangled Generation of 3D Meshes","created":"2022-06-10","cited_by_count":34,"area":null},{"id":"2107.05775","title":"Fast and Explicit Neural View Synthesis","created":"2021-07-12","cited_by_count":28,"area":null},{"id":"2208.11905","title":"Neural Novel Actor: Learning a Generalized Animatable Neural Representation for Human Actors","created":"2022-08-25","cited_by_count":28,"area":null},{"id":"2310.07522","title":"S4C: Self-Supervised Semantic Scene Completion with Neural Fields","created":"2023-10-11","cited_by_count":28,"area":null},{"id":"1806.00047","title":"Following High-level Navigation Instructions on a Simulated Quadcopter with Imitation Learning","created":"2018-05-31","cited_by_count":27,"area":"offlinerl"},{"id":"2108.03746","title":"Unsupervised Learning of Fine Structure Generation for 3D Point Clouds by 2D Projection Matching","created":"2021-08-08","cited_by_count":26,"area":null},{"id":"2201.00112","title":"SurfGen: Adversarial 3D Shape Synthesis with Explicit Surface Discriminators","created":"2022-01-01","cited_by_count":26,"area":null},{"id":"2204.10310","title":"Share With Thy Neighbors: Single-View Reconstruction by Cross-Instance Consistency","created":"2022-04-21","cited_by_count":26,"area":null},{"id":"2111.01067","title":"OctField: Hierarchical Implicit Functions for 3D Modeling","created":"2021-11-01","cited_by_count":25,"area":null},{"id":"2308.14177","title":"AI-Generated Content (AIGC) for Various Data Modalities: A Survey","created":"2023-08-27","cited_by_count":25,"area":null},{"id":"2110.05651","title":"Learning with Algorithmic Supervision via Continuous Relaxations","created":"2021-10-11","cited_by_count":21,"area":null},{"id":"2112.05300","title":"Representing 3D Shapes with Probabilistic Directed Distance Fields","created":"2021-12-10","cited_by_count":21,"area":null},{"id":"2410.13851","title":"Differentiable Robot Rendering","created":"2024-10-17","cited_by_count":21,"area":null},{"id":"2104.03851","title":"CoCoNets: Continuous Contrastive 3D Scene Representations","created":"2021-04-08","cited_by_count":19,"area":null},{"id":"2304.01716","title":"Decoupling Dynamic Monocular Videos for Dynamic View Synthesis","created":"2023-04-04","cited_by_count":17,"area":null},{"id":"2111.10701","title":"Self-Supervised Point Cloud Completion via Inpainting","created":"2021-11-21","cited_by_count":16,"area":null},{"id":"2304.06247","title":"ShapeClipper: Scalable 3D Shape Learning from Single-View Images via Geometric and CLIP-based Consistency","created":"2023-04-13","cited_by_count":16,"area":null},{"id":"2305.03043","title":"Single-Shot Implicit Morphable Faces with Consistent Texture Parameterization","created":"2023-05-04","cited_by_count":16,"area":null},{"id":"2405.02508","title":"Rasterized Edge Gradients: Handling Discontinuities Differentiably","created":"2024-05-03","cited_by_count":14,"area":null},{"id":"2206.11895","title":"Learning Viewpoint-Agnostic Visual Representations by Recovering Tokens in 3D Space","created":"2022-06-23","cited_by_count":13,"area":null},{"id":"2204.13845","title":"GenDR: A Generalized Differentiable Renderer","created":"2022-04-29","cited_by_count":12,"area":null},{"id":"2207.10156","title":"Structural Causal 3D Reconstruction","created":"2022-07-20","cited_by_count":12,"area":null},{"id":"2311.03784","title":"UP-NeRF: Unconstrained Pose-Prior-Free Neural Radiance Fields","created":"2023-11-07","cited_by_count":12,"area":null},{"id":"2105.11692","title":"A Geometry-Informed Deep Learning Framework for Ultra-Sparse 3D Tomographic Image Reconstruction","created":"2021-05-25","cited_by_count":11,"area":null},{"id":"2110.03448","title":"Multi-Head ReLU Implicit Neural Representation Networks","created":"2021-10-07","cited_by_count":10,"area":null},{"id":"2103.16693","title":"Mask-ToF: Learning Microlens Masks for Flying Pixel Correction in Time-of-Flight Imaging","created":"2021-03-30","cited_by_count":9,"area":null},{"id":"2204.10235","title":"Planes vs. Chairs: Category-guided 3D shape learning without any 3D cues","created":"2022-04-21","cited_by_count":9,"area":null},{"id":"2306.17651","title":"Implicit 3D Human Mesh Recovery using Consistency with Pose and Shape from Unseen-view","created":"2023-06-30","cited_by_count":8,"area":null},{"id":"2108.03743","title":"Hierarchical View Predictor: Unsupervised 3D Global Feature Learning through Hierarchical Prediction among Unordered Views","created":"2021-08-08","cited_by_count":7,"area":null},{"id":"2110.09107","title":"Differentiable Rendering with Perturbed Optimizers","created":"2021-10-18","cited_by_count":7,"area":null},{"id":"2210.04127","title":"Towards Efficient Neural Scene Graphs by Learning Consistency Fields","created":"2022-10-09","cited_by_count":7,"area":null},{"id":"2411.17945","title":"MARVEL-40M+: Multi-Level Visual Elaboration for High-Fidelity Text-to-3D Content Creation","created":"2024-11-26","cited_by_count":7,"area":null},{"id":"2508.08199","title":"Generalizable Operating Room Expert with Multimodal Enhancement","created":"2025-08-11","cited_by_count":7,"area":null},{"id":"2209.05013","title":"Learning A Locally Unified 3D Point Cloud for View Synthesis","created":"2022-09-12","cited_by_count":6,"area":null},{"id":"2209.08459","title":"StereoVoxelNet: Real-Time Obstacle Detection Based on Occupancy Voxels from a Stereo Camera Using Deep Neural Networks","created":"2022-09-18","cited_by_count":6,"area":null},{"id":"2104.01103","title":"Semi-supervised Viewpoint Estimation with Geometry-aware Conditional Generation","created":"2021-04-02","cited_by_count":5,"area":null},{"id":"2110.11256","title":"Multi-Category Mesh Reconstruction From Image Collections","created":"2021-10-21","cited_by_count":5,"area":null},{"id":"2504.21847","title":"Differentiable Room Acoustic Rendering with Multi-View Vision Priors","created":"2025-04-30","cited_by_count":5,"area":null},{"id":"2103.04493","title":"Localization and Mapping using Instance-specific Mesh Models","created":"2021-03-08","cited_by_count":4,"area":null},{"id":"2205.15595","title":"Novel View Synthesis for High-fidelity Headshot Scenes","created":"2022-05-31","cited_by_count":4,"area":null},{"id":"2604.08532","title":"Self-Improving 4D Perception via Self-Distillation","created":"2026-04-09","cited_by_count":4,"area":"distill"},{"id":"2110.10784","title":"Style Agnostic 3D Reconstruction via Adversarial Style Transfer","created":"2021-10-20","cited_by_count":3,"area":null},{"id":"2212.00435","title":"ViewNet: Unsupervised Viewpoint Estimation from Conditional Generation","created":"2022-12-01","cited_by_count":3,"area":null},{"id":"2408.14279","title":"Learning Local Pattern Modularization for Point Cloud Reconstruction from Unseen Classes","created":"2024-08-26","cited_by_count":3,"area":null},{"id":"2409.06923","title":"Rethinking Directional Parameterization in Neural Implicit Surface Reconstruction","created":"2024-09-11","cited_by_count":3,"area":null},{"id":"2106.06440","title":"Learning Compositional Shape Priors for Few-Shot 3D Reconstruction","created":"2021-06-11","cited_by_count":2,"area":null},{"id":"2108.02121","title":"Deep Portrait Lighting Enhancement with 3D Guidance","created":"2021-08-04","cited_by_count":2,"area":null},{"id":"2108.03072","title":"STR-GQN: Scene Representation and Rendering for Unknown Cameras Based on Spatial Transformation Routing","created":"2021-08-06","cited_by_count":2,"area":null},{"id":"2108.09593","title":"SSR: Semi-supervised Soft Rasterizer for single-view 2D to 3D Reconstruction","created":"2021-08-21","cited_by_count":2,"area":null},{"id":"2207.09735","title":"CrossHuman: Learning Cross-Guidance from Multi-Frame Images for Human Reconstruction","created":"2022-07-20","cited_by_count":2,"area":null},{"id":"2212.00436","title":"ViewNeRF: Unsupervised Viewpoint Estimation Using Category-Level Neural Radiance Fields","created":"2022-12-01","cited_by_count":2,"area":null},{"id":"2301.04612","title":"Self-Supervised Generative-Contrastive Learning of Multi-Modal Euclidean Input for 3D Shape Latent Representations: A Dynamic Switching Approach","created":"2023-01-11","cited_by_count":2,"area":null},{"id":"2302.12883","title":"3D Surface Reconstruction in the Wild by Deforming Shape Priors from Synthetic Data","created":"2023-02-24","cited_by_count":2,"area":null},{"id":"2503.11269","title":"Prof. Robot: Differentiable Robot Rendering Without Static and Self-Collisions","created":"2025-03-14","cited_by_count":2,"area":null},{"id":"2104.13854","title":"D-OccNet: Detailed 3D Reconstruction Using Cross-Domain Learning","created":"2021-04-28","cited_by_count":1,"area":null},{"id":"2110.15569","title":"Novel View Synthesis from a Single Image via Unsupervised learning","created":"2021-10-29","cited_by_count":1,"area":null},{"id":"2201.05706","title":"Perspective Transformation Layer","created":"2022-01-14","cited_by_count":1,"area":null},{"id":"2212.01639","title":"Visual Question Answering From Another Perspective: CLEVR Mental Rotation Tests","created":"2022-12-03","cited_by_count":1,"area":"lr"},{"id":"2302.07360","title":"Self-supervised learning of object pose estimation using keypoint prediction","created":"2023-02-14","cited_by_count":1,"area":null},{"id":"2309.13281","title":"Automatic Reverse Engineering: Creating computer-aided design (CAD) models from multi-view images","created":"2023-09-23","cited_by_count":1,"area":null},{"id":"2311.03414","title":"A Generative Neural Network Approach for 3D Multi-Criteria Design Generation and Optimization of an Engine Mount for an Unmanned Air Vehicle","created":"2023-11-06","cited_by_count":1,"area":null},{"id":"2404.00269","title":"IPoD: Implicit Field Learning with Point Diffusion for Generalizable 3D Object Reconstruction from Single RGB-D Images","created":"2024-03-30","cited_by_count":1,"area":null},{"id":"2505.09073","title":"2D-3D Attention and Entropy for Pose Robust 2D Facial Recognition","created":"2025-05-14","cited_by_count":1,"area":null},{"id":"2506.12727","title":"Efficient multi-view training for 3D Gaussian Splatting","created":"2025-06-15","cited_by_count":1,"area":null},{"id":"2510.06145","title":"Bimanual 3D Hand Motion and Articulation Forecasting in Everyday Images","created":"2025-10-07","cited_by_count":1,"area":null},{"id":"2106.03087","title":"Neural Implicit 3D Shapes from Single Images with Spatial Patterns","created":"2021-06-06","cited_by_count":0,"area":null},{"id":"2106.15325","title":"SE-MD: A Single-encoder multiple-decoder deep network for point cloud generation from 2D images","created":"2021-06-17","cited_by_count":0,"area":null},{"id":"2111.10520","title":"StylePart: Image-based Shape Part Manipulation","created":"2021-11-20","cited_by_count":0,"area":null},{"id":"2111.15158","title":"A Dataset-Dispersion Perspective on Reconstruction Versus Recognition in Single-View 3D Reconstruction Networks","created":"2021-11-30","cited_by_count":0,"area":null},{"id":"2210.09148","title":"Pruning-based Topology Refinement of 3D Mesh using a 2D Alpha Mask","created":"2022-10-17","cited_by_count":0,"area":null},{"id":"2303.01736","title":"Multi-Plane Neural Radiance Fields for Novel View Synthesis","created":"2023-03-03","cited_by_count":0,"area":null},{"id":"2309.11627","title":"GenLayNeRF: Generalizable Layered Representations with 3D Model Alignment for Multi-Human View Synthesis","created":"2023-09-20","cited_by_count":0,"area":null},{"id":"2310.19188","title":"3DMiner: Discovering Shapes from Large-Scale Unannotated Image Datasets","created":"2023-10-29","cited_by_count":0,"area":null},{"id":"2311.00425","title":"Neural Implicit Field Editing Considering Object-environment Interaction","created":"2023-11-01","cited_by_count":0,"area":null},{"id":"2311.13199","title":"Two-stage Synthetic Supervising and Multi-view Consistency Self-supervising based Animal 3D Reconstruction by Single Image","created":"2023-11-22","cited_by_count":0,"area":null},{"id":"2312.06706","title":"UNeR3D: Versatile and Scalable 3D RGB Point Cloud Generation from 2D Images in Unsupervised Reconstruction","created":"2023-12-10","cited_by_count":0,"area":null}],"next_cursor":"100"}