{"total":95,"rows":[{"id":"2403.12008","title":"SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusion","created":"2024-03-18","cited_by_count":364,"area":"diffusion"},{"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":"2512.14614","title":"WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling","created":"2025-12-16","cited_by_count":170,"area":"wm"},{"id":"2507.10496","title":"Cameras as Relative Positional Encoding","created":"2025-07-14","cited_by_count":105,"area":null},{"id":"2405.00915","title":"EchoScene: Indoor Scene Generation via Information Echo over Scene Graph Diffusion","created":"2024-05-02","cited_by_count":67,"area":"diffusion"},{"id":"2408.00653","title":"SF3D: Stable Fast 3D Mesh Reconstruction with UV-unwrapping and Illumination Disentanglement","created":"2024-08-01","cited_by_count":65,"area":null},{"id":"2408.10198","title":"MeshFormer: High-Quality Mesh Generation with 3D-Guided Reconstruction Model","created":"2024-08-19","cited_by_count":55,"area":"diffusion"},{"id":"2606.17846","title":"Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Models","created":"2026-06-16","cited_by_count":50,"area":null},{"id":"2406.08475","title":"Human-3Diffusion: Realistic Avatar Creation via Explicit 3D Consistent Diffusion Models","created":"2024-06-12","cited_by_count":44,"area":"diffusion"},{"id":"2411.16318","title":"One Diffusion to Generate Them All","created":"2024-11-25","cited_by_count":41,"area":"diffusion"},{"id":"2406.04875","title":"3DRealCar: An In-the-wild RGB-D Car Dataset with 360-degree Views","created":"2024-06-07","cited_by_count":39,"area":null},{"id":"2407.06191","title":"Tailor3D: Customized 3D Assets Editing and Generation with Dual-Side Images","created":"2024-07-08","cited_by_count":35,"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":"2411.19189","title":"Video Depth without Video Models","created":"2024-11-28","cited_by_count":29,"area":null},{"id":"2603.25716","title":"Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models","created":"2026-03-26","cited_by_count":26,"area":"wm"},{"id":"2412.12083","title":"IDArb: Intrinsic Decomposition for Arbitrary Number of Input Views and Illuminations","created":"2024-12-16","cited_by_count":22,"area":null},{"id":"2405.18515","title":"Atlas3D: Physically Constrained Self-Supporting Text-to-3D for Simulation and Fabrication","created":"2024-05-28","cited_by_count":20,"area":"diffusion"},{"id":"2404.06091","title":"Hash3D: Training-free Acceleration for 3D Generation","created":"2024-04-09","cited_by_count":19,"area":"diffusion"},{"id":"2603.11633","title":"MV-SAM3D: Adaptive Multi-View Fusion for Layout-Aware 3D Generation","created":"2026-03-12","cited_by_count":19,"area":null},{"id":"2411.06390","title":"SplatFormer: Point Transformer for Robust 3D Gaussian Splatting","created":"2024-11-10","cited_by_count":16,"area":null},{"id":"2412.06698","title":"Gen-3Diffusion: Realistic Image-to-3D Generation via 2D & 3D Diffusion Synergy","created":"2024-12-09","cited_by_count":16,"area":"diffusion"},{"id":"2503.19913","title":"PartRM: Modeling Part-Level Dynamics with Large Cross-State Reconstruction Model","created":"2025-03-25","cited_by_count":15,"area":"wm"},{"id":"2511.20186","title":"Exo2EgoSyn: Unlocking Foundation Video Generation Models for Exocentric-to-Egocentric Video Synthesis","created":"2025-11-25","cited_by_count":15,"area":null},{"id":"2601.15275","title":"RayRoPE: Projective Ray Positional Encoding for Multi-view Attention","created":"2026-01-21","cited_by_count":14,"area":null},{"id":"2504.11389","title":"VideoPanda: Video Panoramic Diffusion with Multi-view Attention","created":"2025-04-15","cited_by_count":13,"area":null},{"id":"2506.10507","title":"Edit360: 2D Image Edits to 3D Assets from Any Angle","created":"2025-06-12","cited_by_count":13,"area":"diffusion"},{"id":"2602.08068","title":"ReRoPE: Repurposing RoPE for Relative Camera Control","created":"2026-02-08","cited_by_count":13,"area":"diffusion"},{"id":"2503.21745","title":"3DGen-Bench: Comprehensive Benchmark Suite for 3D Generative Models","created":"2025-03-27","cited_by_count":12,"area":null},{"id":"2505.21437","title":"CoDA: Coordinated Diffusion Noise Optimization for Whole-Body Manipulation of Articulated Objects","created":"2025-05-27","cited_by_count":12,"area":null},{"id":"2602.07854","title":"Geometry-Aware Rotary Position Embedding for Consistent Video World Model","created":"2026-02-08","cited_by_count":12,"area":"wm"},{"id":"2511.19827","title":"ReDirector: Creating Any-Length Video Retakes with Rotary Camera Encoding","created":"2025-11-25","cited_by_count":11,"area":null},{"id":"2403.14279","title":"Zero123-6D: Zero-shot Novel View Synthesis for RGB Category-level 6D Pose Estimation","created":"2024-03-21","cited_by_count":10,"area":"diffusion"},{"id":"2406.13099","title":"Sampling 3D Gaussian Scenes in Seconds with Latent Diffusion Models","created":"2024-06-18","cited_by_count":10,"area":"diffusion"},{"id":"2412.11457","title":"MOVIS: Enhancing Multi-Object Novel View Synthesis for Indoor Scenes","created":"2024-12-16","cited_by_count":10,"area":"diffusion"},{"id":"2406.20077","title":"HouseCrafter: Lifting Floorplans to 3D Scenes with 2D Diffusion Model","created":"2024-06-28","cited_by_count":9,"area":"diffusion"},{"id":"2410.09009","title":"Semantic Score Distillation Sampling for Compositional Text-to-3D Generation","created":"2024-10-11","cited_by_count":9,"area":"diffusion"},{"id":"2412.13111","title":"Motion-2-To-3: Leveraging 2D Motion Data for 3D Motion Generations","created":"2024-12-17","cited_by_count":9,"area":null},{"id":"2507.00006","title":"MVGBench: Comprehensive Benchmark for Multi-view Generation Models","created":"2025-06-11","cited_by_count":9,"area":"mllm"},{"id":"2602.21341","title":"Scaling View Synthesis Transformers","created":"2026-02-24","cited_by_count":9,"area":null},{"id":"2510.04236","title":"Scaling Sequence-to-Sequence Generative Neural Rendering","created":"2025-10-05","cited_by_count":8,"area":null},{"id":"2512.08269","title":"EgoX: Egocentric Video Generation from a Single Exocentric Video","created":"2025-12-09","cited_by_count":8,"area":null},{"id":"2605.21472","title":"Stream3D: Sequential Multi-View 3D Generation via Evidential Memory","created":"2026-05-20","cited_by_count":7,"area":null},{"id":"2405.03894","title":"MVDiff: Scalable and Flexible Multi-View Diffusion for 3D Object Reconstruction from Single-View","created":"2024-05-06","cited_by_count":6,"area":"diffusion"},{"id":"2508.06014","title":"ExploreGS: Explorable 3D Scene Reconstruction with Virtual Camera Samplings and Diffusion Priors","created":"2025-08-08","cited_by_count":6,"area":"diffusion"},{"id":"2509.06579","title":"CausNVS: Autoregressive Multi-view Diffusion for Flexible 3D Novel View Synthesis","created":"2025-09-08","cited_by_count":6,"area":"diffusion"},{"id":"2509.25001","title":"LVT: Large-Scale Scene Reconstruction via Local View Transformers","created":"2025-09-29","cited_by_count":6,"area":null},{"id":"2512.19678","title":"WorldWarp: Propagating 3D Geometry with Asynchronous Video Diffusion","created":"2025-12-22","cited_by_count":6,"area":"diffusion"},{"id":"2606.10135","title":"BiWM: Advancing Open-Source Interactive Video World Models with Bidirectional Autoregression","created":"2026-06-08","cited_by_count":6,"area":"wm"},{"id":"2507.08776","title":"CLiFT: Compressive Light-Field Tokens for Compute-Efficient and Adaptive Neural Rendering","created":"2025-07-11","cited_by_count":5,"area":null},{"id":"2508.11603","title":"CoreEditor: Correspondence-constrained Diffusion for Consistent 3D Editing","created":"2025-08-15","cited_by_count":5,"area":null},{"id":"2606.27345","title":"SCoPE: Sightline-Coordinate Positional Encoding for Video Diffusion Transformers","created":"2026-06-25","cited_by_count":5,"area":"diffusion"},{"id":"2608.13391","title":"Context-Matched Distillation: Teacher Causality for Autoregressive Video Distillation","created":"2026-08-13","cited_by_count":5,"area":"distill"},{"id":"2511.05449","title":"How Many Tokens Do 3D Point Cloud Transformer Architectures Really Need?","created":"2025-11-07","cited_by_count":4,"area":null},{"id":"2511.22264","title":"DriveVGGT: Calibration-Constrained Visual Geometry Transformers for Multi-Camera Autonomous Driving","created":"2025-11-27","cited_by_count":4,"area":null},{"id":"2604.08500","title":"FrameCrafter: Novel View Synthesis as Video Completion","created":"2026-04-09","cited_by_count":4,"area":"diffusion"},{"id":"2605.12938","title":"CRePE: Curved Ray Expectation Positional Encoding for Unified-Camera-Controlled Video Generation","created":"2026-05-13","cited_by_count":4,"area":"wm"},{"id":"2504.01960","title":"Diffusion-Guided Gaussian Splatting for Large-Scale Unconstrained 3D Reconstruction and Novel View Synthesis","created":"2025-04-02","cited_by_count":3,"area":null},{"id":"2508.05609","title":"Hi3DEval: Advancing 3D Generation Evaluation with Hierarchical Validity","created":"2025-08-07","cited_by_count":3,"area":null},{"id":"2509.20607","title":"Reflect3r: Single-View 3D Stereo Reconstruction Aided by Mirror Reflections","created":"2025-09-24","cited_by_count":3,"area":null},{"id":"2607.20660","title":"Axolotl3D: a Unified Framework for Faithful 3D Shape Completion","created":"2026-07-22","cited_by_count":3,"area":null},{"id":"2404.06429","title":"Magic-Boost: Boost 3D Generation with Multi-View Conditioned Diffusion","created":"2024-04-09","cited_by_count":2,"area":"diffusion"},{"id":"2412.08412","title":"Pragmatist: Multiview Conditional Diffusion Models for High-Fidelity 3D Reconstruction from Unposed Sparse Views","created":"2024-12-11","cited_by_count":2,"area":"diffusion"},{"id":"2504.11674","title":"DM-OSVP++: One-Shot View Planning Using 3D Diffusion Models for Active RGB-Based Object Reconstruction","created":"2025-04-16","cited_by_count":2,"area":"diffusion"},{"id":"2509.06191","title":"Learning in ImaginationLand: Omnidirectional Policies through 3D Generative Models (OP-Gen)","created":"2025-09-07","cited_by_count":2,"area":null},{"id":"2510.20726","title":"AutoScape: Geometry-Consistent Long-Horizon Scene Generation","created":"2025-10-23","cited_by_count":2,"area":"diffusion"},{"id":"2512.09112","title":"GimbalDiffusion: Gravity-Aware Camera Control for Video Generation","created":"2025-12-09","cited_by_count":2,"area":null},{"id":"2512.10959","title":"StereoSpace: Depth-Free Synthesis of Stereo Geometry via End-to-End Diffusion in a Canonical Space","created":"2025-12-11","cited_by_count":2,"area":null},{"id":"2602.23224","title":"UniScale: Unified Scale-Aware 3D Reconstruction for Multi-View Understanding via Prior Injection for Robotic Perception","created":"2026-02-26","cited_by_count":2,"area":null},{"id":"2603.01010","title":"GeodesicNVS: Probability Density Geodesic Flow Matching for Novel View Synthesis","created":"2026-03-01","cited_by_count":2,"area":"diffusion"},{"id":"2603.01194","title":"RnG: A Unified Transformer for Complete 3D Modeling from Partial Observations","created":"2026-03-01","cited_by_count":2,"area":null},{"id":"2605.29891","title":"DVSM: Decoder-only View Synthesis Model Done Right","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2501.04144","title":"Chirpy3D: Part-Aware Multi-View Diffusion for Creative Fine-Grained Object Generation","created":"2025-01-07","cited_by_count":1,"area":null},{"id":"2503.13588","title":"Next-Scale Autoregressive Models are Zero-Shot Single-Image Object View Synthesizers","created":"2025-03-17","cited_by_count":1,"area":null},{"id":"2504.14606","title":"MP-Mat: A 3D-and-Instance-Aware Human Matting and Editing Framework with Multiplane Representation","created":"2025-04-20","cited_by_count":1,"area":null},{"id":"2507.07410","title":"EscherNet++: Simultaneous Amodal Completion and Scalable View Synthesis through Masked Fine-Tuning and Enhanced Feed-Forward 3D Reconstruction","created":"2025-07-10","cited_by_count":1,"area":"diffusion"},{"id":"2508.06392","title":"FVGen: Accelerating Novel-View Synthesis with Adversarial Video Diffusion Distillation","created":"2025-08-08","cited_by_count":1,"area":"diffusion"},{"id":"2509.04932","title":"UniView: Enhancing Novel View Synthesis From A Single Image By Unifying Reference Features","created":"2025-09-05","cited_by_count":1,"area":null},{"id":"2603.19613","title":"OrbitNVS: Harnessing Video Diffusion Priors for Novel View Synthesis","created":"2026-03-20","cited_by_count":1,"area":"diffusion"},{"id":"2606.31585","title":"DPPE: Rethinking Camera-Based Positional Encoding for Scaling Multi-View Transformers","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2607.24591","title":"CameraAnything: Refilming Videos with Arbitrary Camera Control","created":"2026-07-27","cited_by_count":1,"area":null},{"id":"2608.08132","title":"ASV3D: Adapting Diffusion-Based Single-View 3D Reconstruction with Extra Imagery","created":"2026-08-08","cited_by_count":1,"area":null},{"id":"2609.01252","title":"MeRoPE: Metric Rotary Position Embedding for Camera-Controlled Video Generation","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2412.10273","title":"How to Spin an Object: First, Get the Shape Right","created":"2024-12-13","cited_by_count":0,"area":null},{"id":"2501.12393","title":"Towards Affordance-Aware Articulation Synthesis for Rigged Objects","created":"2025-01-21","cited_by_count":0,"area":null},{"id":"2505.23054","title":"Zero-P-to-3: Zero-Shot Partial-View Images to 3D Object","created":"2025-05-29","cited_by_count":0,"area":null},{"id":"2506.00600","title":"SatDreamer360: Multiview-Consistent Generation of Ground-Level Scenes from Satellite Imagery","created":"2025-05-31","cited_by_count":0,"area":null},{"id":"2507.12336","title":"Unsupervised Monocular 3D Keypoint Discovery from Multi-View Diffusion Priors","created":"2025-07-16","cited_by_count":0,"area":"diffusion"},{"id":"2604.12309","title":"Towards Realistic and Consistent Orbital Video Generation via 3D Foundation Priors","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2605.18132","title":"Who Generated This 3D Asset? Learning Source Attribution for Generative 3D Models","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2606.01590","title":"Effective Multi-sensor Conditioning for Street-view Novel-view Synthesis","created":"2026-06-01","cited_by_count":0,"area":"diffusion"},{"id":"2607.02712","title":"Global Pose Control for Generative View Synthesis in Normalized Object Coordinate Space","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2608.23410","title":"Photorealistic Novel View Synthesis of Human Faces using Next-Scale Transformers","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.10531","title":"Guiding Image-to-3D Generation with Test-Time Partial Observations","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.33253","title":"VGGT-Diff: Visual Geometry Meets Diffusion for Sparse-View Novel View Synthesis","created":"2026-09-27","cited_by_count":0,"area":"diffusion"},{"id":"2610.04722","title":"NAMVIS: Next-Scale Autoregressive Multi-View Image Synthesis","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}