{"total":227,"rows":[{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071,"area":"mllm"},{"id":"2311.04400","title":"LRM: Large Reconstruction Model for Single Image to 3D","created":"2023-11-08","cited_by_count":849,"area":null},{"id":"2312.12337","title":"pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction","created":"2023-12-19","cited_by_count":684,"area":null},{"id":"2403.14627","title":"MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images","created":"2024-03-21","cited_by_count":566,"area":null},{"id":"2301.11445","title":"3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models","created":"2023-01-26","cited_by_count":458,"area":"diffusion"},{"id":"2405.10314","title":"CAT3D: Create Anything in 3D with Multi-View Diffusion Models","created":"2024-05-16","cited_by_count":432,"area":"diffusion"},{"id":"2203.03570","title":"Kubric: A scalable dataset generator","created":"2022-03-07","cited_by_count":381,"area":null},{"id":"2312.02981","title":"ReconFusion: 3D Reconstruction with Diffusion Priors","created":"2023-12-05","cited_by_count":318,"area":"diffusion"},{"id":"2210.04628","title":"Novel View Synthesis with Diffusion Models","created":"2022-10-06","cited_by_count":300,"area":"diffusion"},{"id":"2304.02602","title":"Generative Novel View Synthesis with 3D-Aware Diffusion Models","created":"2023-04-05","cited_by_count":274,"area":"diffusion"},{"id":"2212.00792","title":"SparseFusion: Distilling View-conditioned Diffusion for 3D Reconstruction","created":"2022-12-01","cited_by_count":216,"area":null},{"id":"2410.17242","title":"LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias","created":"2024-10-22","cited_by_count":189,"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":"2502.12138","title":"FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Views","created":"2025-02-17","cited_by_count":180,"area":null},{"id":"2504.12369","title":"WorldMem: Long-term Consistent World Simulation with Memory","created":"2025-04-16","cited_by_count":168,"area":"wm"},{"id":"2311.12024","title":"PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Prediction","created":"2023-11-20","cited_by_count":165,"area":null},{"id":"2210.00379","title":"NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)","created":"2022-10-01","cited_by_count":158,"area":null},{"id":"2207.13751","title":"GAUDI: A Neural Architect for Immersive 3D Scene Generation","created":"2022-07-27","cited_by_count":136,"area":null},{"id":"2207.10662","title":"Generalizable Patch-Based Neural Rendering","created":"2022-07-21","cited_by_count":122,"area":null},{"id":"2406.04343","title":"Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Image","created":"2024-06-06","cited_by_count":116,"area":null},{"id":"2411.04924","title":"MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Views","created":"2024-11-07","cited_by_count":116,"area":null},{"id":"2207.13298","title":"Is Attention All That NeRF Needs?","created":"2022-07-27","cited_by_count":113,"area":null},{"id":"2306.11719","title":"Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervision","created":"2023-06-20","cited_by_count":112,"area":"diffusion"},{"id":"2412.03632","title":"MV-Adapter: Multi-view Consistent Image Generation Made Easy","created":"2024-12-04","cited_by_count":112,"area":null},{"id":"2112.09687","title":"Light Field Neural Rendering","created":"2021-12-17","cited_by_count":108,"area":null},{"id":"2507.10496","title":"Cameras as Relative Positional Encoding","created":"2025-07-14","cited_by_count":105,"area":null},{"id":"2207.05736","title":"Vision Transformer for NeRF-Based View Synthesis from a Single Input Image","created":"2022-07-12","cited_by_count":104,"area":null},{"id":"2304.08463","title":"Learning to Render Novel Views from Wide-Baseline Stereo Pairs","created":"2023-04-17","cited_by_count":104,"area":null},{"id":"2403.12019","title":"LN3DIFF++: Scalable Latent Neural Fields Diffusion for Speedy 3D Generation","created":"2024-03-18","cited_by_count":92,"area":null},{"id":"2206.06922","title":"Object Scene Representation Transformer","created":"2022-06-14","cited_by_count":90,"area":null},{"id":"2403.06738","title":"V3D: Video Diffusion Models are Effective 3D Generators","created":"2024-03-11","cited_by_count":89,"area":"diffusion"},{"id":"2303.12791","title":"SHERF: Generalizable Human NeRF from a Single Image","created":"2023-03-22","cited_by_count":88,"area":null},{"id":"2310.08092","title":"Consistent123: Improve Consistency for One Image to 3D Object Synthesis","created":"2023-10-12","cited_by_count":84,"area":"diffusion"},{"id":"2310.03020","title":"Consistent-1-to-3: Consistent Image to 3D View Synthesis via Geometry-aware Diffusion Models","created":"2023-10-04","cited_by_count":79,"area":"diffusion"},{"id":"2310.10375","title":"GTA: A Geometry-Aware Attention Mechanism for Multi-View Transformers","created":"2023-10-16","cited_by_count":79,"area":null},{"id":"2311.17901","title":"SODA: Bottleneck Diffusion Models for Representation Learning","created":"2023-11-29","cited_by_count":77,"area":"diffusion"},{"id":"2505.00702","title":"RayZer: A Self-supervised Large View Synthesis Model","created":"2025-05-01","cited_by_count":77,"area":null},{"id":"2304.10700","title":"Long-Term Photometric Consistent Novel View Synthesis with Diffusion Models","created":"2023-04-21","cited_by_count":76,"area":"diffusion"},{"id":"2410.18956","title":"Large Spatial Model: End-to-end Unposed Images to Semantic 3D","created":"2024-10-24","cited_by_count":73,"area":null},{"id":"2312.04551","title":"Free3D: Consistent Novel View Synthesis without 3D Representation","created":"2023-12-07","cited_by_count":72,"area":null},{"id":"2312.06725","title":"EpiDiff: Enhancing Multi-View Synthesis via Localized Epipolar-Constrained Diffusion","created":"2023-12-11","cited_by_count":72,"area":"diffusion"},{"id":"2312.04565","title":"MuRF: Multi-Baseline Radiance Fields","created":"2023-12-07","cited_by_count":71,"area":null},{"id":"2406.18524","title":"MultiDiff: Consistent Novel View Synthesis from a Single Image","created":"2024-06-26","cited_by_count":68,"area":"diffusion"},{"id":"2407.07860","title":"Controlling Space and Time with Diffusion Models","created":"2024-07-10","cited_by_count":66,"area":"diffusion"},{"id":"2310.01410","title":"LEAP: Liberate Sparse-view 3D Modeling from Camera Poses","created":"2023-10-02","cited_by_count":65,"area":null},{"id":"2305.02310","title":"Real-Time Radiance Fields for Single-Image Portrait View Synthesis","created":"2023-05-03","cited_by_count":64,"area":null},{"id":"2301.07668","title":"Behind the Scenes: Density Fields for Single View Reconstruction","created":"2023-01-18","cited_by_count":63,"area":null},{"id":"2401.17807","title":"Advances in 3D Generation: A Survey","created":"2024-01-31","cited_by_count":63,"area":null},{"id":"2402.05235","title":"SPAD : Spatially Aware Multiview Diffusers","created":"2024-02-07","cited_by_count":62,"area":null},{"id":"2501.01895","title":"EnerVerse: Envisioning Embodied Future Space for Robotics Manipulation","created":"2025-01-03","cited_by_count":61,"area":"wm"},{"id":"2210.08990","title":"Improving Object-centric Learning with Query Optimization","created":"2022-10-17","cited_by_count":60,"area":null},{"id":"2503.14445","title":"Bolt3D: Generating 3D Scenes in Seconds","created":"2025-03-18","cited_by_count":59,"area":"diffusion"},{"id":"2512.08924","title":"Efficiently Reconstructing Dynamic Scenes One D4RT at a Time","created":"2025-12-09","cited_by_count":54,"area":null},{"id":"2211.16991","title":"SparsePose: Sparse-View Camera Pose Regression and Refinement","created":"2022-11-29","cited_by_count":53,"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":"2308.12967","title":"NeO 360: Neural Fields for Sparse View Synthesis of Outdoor Scenes","created":"2023-08-24","cited_by_count":53,"area":null},{"id":"2302.04973","title":"Invariant Slot Attention: Object Discovery with Slot-Centric Reference Frames","created":"2023-02-09","cited_by_count":51,"area":null},{"id":"2403.12010","title":"VideoMV: Consistent Multi-View Generation Based on Large Video Generative Model","created":"2024-03-18","cited_by_count":45,"area":null},{"id":"2211.14306","title":"RUST: Latent Neural Scene Representations from Unposed Imagery","created":"2022-11-25","cited_by_count":43,"area":null},{"id":"2508.01171","title":"No Pose at All: Self-Supervised Pose-Free 3D Gaussian Splatting from Sparse Views","created":"2025-08-02","cited_by_count":40,"area":null},{"id":"2306.00180","title":"FlowCam: Training Generalizable 3D Radiance Fields without Camera Poses via Pixel-Aligned Scene Flow","created":"2023-05-31","cited_by_count":39,"area":null},{"id":"2306.05407","title":"SNAP: Self-Supervised Neural Maps for Visual Positioning and Semantic Understanding","created":"2023-06-08","cited_by_count":38,"area":null},{"id":"2408.10195","title":"SpaRP: Fast 3D Object Reconstruction and Pose Estimation from Sparse Views","created":"2024-08-19","cited_by_count":35,"area":"diffusion"},{"id":"2302.06833","title":"VQ3D: Learning a 3D-Aware Generative Model on ImageNet","created":"2023-02-14","cited_by_count":32,"area":null},{"id":"2306.03414","title":"DreamSparse: Escaping from Plato's Cave with 2D Frozen Diffusion Model Given Sparse Views","created":"2023-06-06","cited_by_count":31,"area":"diffusion"},{"id":"2409.19405","title":"G3R: Gradient Guided Generalizable Reconstruction","created":"2024-09-28","cited_by_count":31,"area":null},{"id":"2304.08971","title":"SurfelNeRF: Neural Surfel Radiance Fields for Online Photorealistic Reconstruction of Indoor Scenes","created":"2023-04-18","cited_by_count":30,"area":null},{"id":"2305.18832","title":"ReTR: Modeling Rendering Via Transformer for Generalizable Neural Surface Reconstruction","created":"2023-05-30","cited_by_count":30,"area":null},{"id":"2512.03422","title":"What Is The Best 3D Scene Representation for Robotics? From Geometric to Foundation Models","created":"2025-12-03","cited_by_count":29,"area":null},{"id":"2510.22706","title":"IGGT: Instance-Grounded Geometry Transformer for Semantic 3D Reconstruction","created":"2025-10-26","cited_by_count":28,"area":null},{"id":"2304.06700","title":"Control3Diff: Learning Controllable 3D Diffusion Models from Single-view Images","created":"2023-04-13","cited_by_count":27,"area":"diffusion"},{"id":"2308.11793","title":"Enhancing NeRF akin to Enhancing LLMs: Generalizable NeRF Transformer with Mixture-of-View-Experts","created":"2023-08-22","cited_by_count":27,"area":"moe"},{"id":"2310.08587","title":"Pseudo-Generalized Dynamic View Synthesis from a Video","created":"2023-10-12","cited_by_count":27,"area":null},{"id":"2412.04842","title":"UniMLVG: Unified Framework for Multi-view Long Video Generation with Comprehensive Control Capabilities for Autonomous Driving","created":"2024-12-06","cited_by_count":27,"area":null},{"id":"2507.14501","title":"Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Survey","created":"2025-07-19","cited_by_count":27,"area":null},{"id":"2501.05763","title":"StarGen: A Spatiotemporal Autoregression Framework with Video Diffusion Model for Scalable and Controllable Scene Generation","created":"2025-01-10","cited_by_count":26,"area":"diffusion"},{"id":"2603.04385","title":"ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Training","created":"2026-03-04","cited_by_count":26,"area":null},{"id":"2303.15555","title":"Object Discovery from Motion-Guided Tokens","created":"2023-03-27","cited_by_count":25,"area":null},{"id":"2304.02163","title":"GINA-3D: Learning to Generate Implicit Neural Assets in the Wild","created":"2023-04-04","cited_by_count":25,"area":null},{"id":"2308.14078","title":"Sparse3D: Distilling Multiview-Consistent Diffusion for Object Reconstruction from Sparse Views","created":"2023-08-27","cited_by_count":25,"area":"diffusion"},{"id":"2405.05768","title":"FastScene: Text-Driven Fast 3D Indoor Scene Generation via Panoramic Gaussian Splatting","created":"2024-05-09","cited_by_count":24,"area":null},{"id":"2408.14211","title":"MagicMan: Generative Novel View Synthesis of Humans with 3D-Aware Diffusion and Iterative Refinement","created":"2024-08-26","cited_by_count":24,"area":"diffusion"},{"id":"2501.00358","title":"Embodied VideoAgent: Persistent Memory from Egocentric Videos and Embodied Sensors Enables Dynamic Scene Understanding","created":"2024-12-31","cited_by_count":24,"area":null},{"id":"2412.07770","title":"From an Image to a Scene: Learning to Imagine the World from a Million 360 Videos","created":"2024-12-10","cited_by_count":23,"area":null},{"id":"2505.21925","title":"RenderFormer: Transformer-based Neural Rendering of Triangle Meshes with Global Illumination","created":"2025-05-28","cited_by_count":23,"area":null},{"id":"2412.14166","title":"MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data","created":"2024-12-18","cited_by_count":21,"area":null},{"id":"2209.10684","title":"Attention Beats Concatenation for Conditioning Neural Fields","created":"2022-09-21","cited_by_count":20,"area":null},{"id":"2310.16167","title":"iNVS: Repurposing Diffusion Inpainters for Novel View Synthesis","created":"2023-10-24","cited_by_count":20,"area":null},{"id":"2403.10147","title":"GGRt: Towards Pose-free Generalizable 3D Gaussian Splatting in Real-time","created":"2024-03-15","cited_by_count":20,"area":null},{"id":"2211.16630","title":"DINER: Depth-aware Image-based NEural Radiance fields","created":"2022-11-29","cited_by_count":19,"area":null},{"id":"2312.08568","title":"NViST: In the Wild New View Synthesis from a Single Image with Transformers","created":"2023-12-13","cited_by_count":19,"area":null},{"id":"2410.18979","title":"PixelGaussian: Generalizable 3D Gaussian Reconstruction from Arbitrary Views","created":"2024-10-24","cited_by_count":19,"area":null},{"id":"2503.13272","title":"Generative Gaussian Splatting: Generating 3D Scenes with Video Diffusion Priors","created":"2025-03-17","cited_by_count":19,"area":"diffusion"},{"id":"2410.22817","title":"Epipolar-Free 3D Gaussian Splatting for Generalizable Novel View Synthesis","created":"2024-10-30","cited_by_count":18,"area":null},{"id":"2206.14797","title":"3D-Aware Video Generation","created":"2022-06-29","cited_by_count":17,"area":null},{"id":"2207.11232","title":"Neural Groundplans: Persistent Neural Scene Representations from a Single Image","created":"2022-07-22","cited_by_count":17,"area":null},{"id":"2207.14287","title":"Depth Field Networks for Generalizable Multi-view Scene Representation","created":"2022-07-28","cited_by_count":17,"area":null},{"id":"2303.17842","title":"Shepherding Slots to Objects: Towards Stable and Robust Object-Centric Learning","created":"2023-03-31","cited_by_count":17,"area":null},{"id":"2210.14267","title":"A Survey on Deep Generative 3D-aware Image Synthesis","created":"2022-10-25","cited_by_count":16,"area":null},{"id":"2306.08068","title":"DORSal: Diffusion for Object-centric Representations of Scenes et al","created":"2023-06-13","cited_by_count":16,"area":"diffusion"}],"next_cursor":"100"}