{"total":148,"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":"2312.16256","title":"DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision","created":"2023-12-26","cited_by_count":537,"area":null},{"id":"2411.15738","title":"AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea","created":"2024-11-24","cited_by_count":241,"area":null},{"id":"2311.09217","title":"DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Model","created":"2023-11-15","cited_by_count":214,"area":null},{"id":"2312.17142","title":"DreamGaussian4D: Generative 4D Gaussian Splatting","created":"2023-12-28","cited_by_count":194,"area":null},{"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":"2504.02160","title":"Less-to-More Generalization: Unlocking More Controllability by In-Context Generation","created":"2025-04-02","cited_by_count":154,"area":null},{"id":"2412.03632","title":"MV-Adapter: Multi-view Consistent Image Generation Made Easy","created":"2024-12-04","cited_by_count":112,"area":null},{"id":"2405.20853","title":"MeshXL: Neural Coordinate Field for Generative 3D Foundation Models","created":"2024-05-31","cited_by_count":103,"area":null},{"id":"2403.12365","title":"GaussianFlow: Splatting Gaussian Dynamics for 4D Content Creation","created":"2024-03-19","cited_by_count":100,"area":null},{"id":"2503.22236","title":"Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridging","created":"2025-03-28","cited_by_count":99,"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":"2403.15624","title":"Semantic Gaussians: Open-Vocabulary Scene Understanding with 3D Gaussian Splatting","created":"2024-03-22","cited_by_count":82,"area":null},{"id":"2509.09676","title":"SpatialVID: A Large-Scale Video Dataset with Spatial Annotations","created":"2025-09-11","cited_by_count":77,"area":null},{"id":"2403.20309","title":"InstantSplat: Sparse-view Gaussian Splatting in Seconds","created":"2024-03-29","cited_by_count":70,"area":null},{"id":"2403.10701","title":"IMPRINT: Generative Object Compositing by Learning Identity-Preserving Representation","created":"2024-03-15","cited_by_count":64,"area":null},{"id":"2401.17807","title":"Advances in 3D Generation: A Survey","created":"2024-01-31","cited_by_count":63,"area":null},{"id":"2305.06131","title":"Generative AI meets 3D: A Survey on Text-to-3D in AIGC Era","created":"2023-05-10","cited_by_count":61,"area":null},{"id":"2504.15009","title":"Insert Anything: Image Insertion via In-Context Editing in DiT","created":"2025-04-21","cited_by_count":61,"area":null},{"id":"2406.11819","title":"MegaScenes: Scene-Level View Synthesis at Scale","created":"2024-06-17","cited_by_count":58,"area":null},{"id":"2412.14963","title":"IDOL: Instant Photorealistic 3D Human Creation from a Single Image","created":"2024-12-19","cited_by_count":55,"area":null},{"id":"2312.02963","title":"MVHumanNet: A Large-scale Dataset of Multi-view Daily Dressing Human Captures","created":"2023-12-05","cited_by_count":54,"area":null},{"id":"2306.09109","title":"NAVI: Category-Agnostic Image Collections with High-Quality 3D Shape and Pose Annotations","created":"2023-06-15","cited_by_count":53,"area":null},{"id":"2401.04099","title":"AGG: Amortized Generative 3D Gaussians for Single Image to 3D","created":"2024-01-08","cited_by_count":53,"area":null},{"id":"2411.02319","title":"GenXD: Generating Any 3D and 4D Scenes","created":"2024-11-04","cited_by_count":50,"area":null},{"id":"2412.03526","title":"Feed-Forward Bullet-Time Reconstruction of Dynamic Scenes from Monocular Videos","created":"2024-12-04","cited_by_count":49,"area":null},{"id":"2501.01427","title":"VideoAnydoor: High-fidelity Video Object Insertion with Precise Motion Control","created":"2025-01-02","cited_by_count":42,"area":null},{"id":"2412.09573","title":"FreeSplatter: Pose-free Gaussian Splatting for Sparse-view 3D Reconstruction","created":"2024-12-12","cited_by_count":41,"area":null},{"id":"2502.07685","title":"Matrix3D: Large Photogrammetry Model All-in-One","created":"2025-02-11","cited_by_count":40,"area":null},{"id":"2406.09371","title":"LRM-Zero: Training Large Reconstruction Models with Synthesized Data","created":"2024-06-13","cited_by_count":35,"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":"2306.10988","title":"Tame a Wild Camera: In-the-Wild Monocular Camera Calibration","created":"2023-06-19","cited_by_count":34,"area":null},{"id":"2312.05295","title":"Disentangled Clothed Avatar Generation from Text Descriptions","created":"2023-12-08","cited_by_count":33,"area":null},{"id":"2406.03184","title":"Ouroboros3D: Image-to-3D Generation via 3D-aware Recursive Diffusion","created":"2024-06-05","cited_by_count":31,"area":null},{"id":"2408.08000","title":"MVInpainter: Learning Multi-View Consistent Inpainting to Bridge 2D and 3D Editing","created":"2024-08-15","cited_by_count":30,"area":null},{"id":"2412.09606","title":"Feat2GS: Probing Visual Foundation Models with Gaussian Splatting","created":"2024-12-12","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":"2510.20155","title":"PartNeXt: A Next-Generation Dataset for Fine-Grained and Hierarchical 3D Part Understanding","created":"2025-10-23","cited_by_count":26,"area":null},{"id":"2406.08479","title":"Real3D: Scaling Up Large Reconstruction Models with Real-World Images","created":"2024-06-12","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":"2412.11258","title":"GaussianProperty: Integrating Physical Properties to 3D Gaussians with LMMs","created":"2024-12-15","cited_by_count":23,"area":null},{"id":"2406.00609","title":"SuperGaussian: Repurposing Video Models for 3D Super Resolution","created":"2024-06-02","cited_by_count":22,"area":null},{"id":"2512.10950","title":"E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-training","created":"2025-12-11","cited_by_count":22,"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":"2409.04559","title":"Thinking Outside the BBox: Unconstrained Generative Object Compositing","created":"2024-09-06","cited_by_count":19,"area":null},{"id":"2408.15235","title":"Learning-based Multi-View Stereo: A Survey","created":"2024-08-27","cited_by_count":18,"area":null},{"id":"2412.08641","title":"3D Mesh Editing using Masked LRMs","created":"2024-12-11","cited_by_count":18,"area":null},{"id":"2504.07083","title":"GenDoP: Auto-regressive Camera Trajectory Generation as a Director of Photography","created":"2025-04-09","cited_by_count":18,"area":null},{"id":"2409.17280","title":"Disco4D: Disentangled 4D Human Generation and Animation from a Single Image","created":"2024-09-25","cited_by_count":17,"area":null},{"id":"2501.07574","title":"UnCommon Objects in 3D","created":"2025-01-13","cited_by_count":17,"area":null},{"id":"2404.02185","title":"NeRFCodec: Neural Feature Compression Meets Neural Radiance Fields for Memory-Efficient Scene Representation","created":"2024-04-02","cited_by_count":16,"area":null},{"id":"2406.10475","title":"Discrete Latent Perspective Learning for Segmentation and Detection","created":"2024-06-15","cited_by_count":16,"area":null},{"id":"2408.09744","title":"RealCustom++: Representing Images as Real Textual Word for Real-Time Customization","created":"2024-08-19","cited_by_count":16,"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":"2504.20026","title":"LIRM: Large Inverse Rendering Model for Progressive Reconstruction of Shape, Materials and View-dependent Radiance Fields","created":"2025-04-28","cited_by_count":16,"area":null},{"id":"2501.01425","title":"Free-Form Motion Control: Controlling the 6D Poses of Camera and Objects in Video Generation","created":"2025-01-02","cited_by_count":15,"area":null},{"id":"2503.04641","title":"Simulating the Real World: A Unified Survey of Multimodal Generative Models","created":"2025-03-06","cited_by_count":15,"area":null},{"id":"2503.12024","title":"SteerX: Creating Any Camera-Free 3D and 4D Scenes with Geometric Steering","created":"2025-03-15","cited_by_count":15,"area":null},{"id":"2411.00144","title":"Self-Ensembling Gaussian Splatting for Few-Shot Novel View Synthesis","created":"2024-10-31","cited_by_count":14,"area":null},{"id":"2411.19458","title":"Multiview Equivariance Improves 3D Correspondence Understanding with Minimal Feature Finetuning","created":"2024-11-29","cited_by_count":14,"area":null},{"id":"2503.06235","title":"StreamGS: Online Generalizable Gaussian Splatting Reconstruction for Unposed Image Streams","created":"2025-03-08","cited_by_count":14,"area":null},{"id":"2503.15855","title":"VideoRFSplat: Direct Scene-Level Text-to-3D Gaussian Splatting Generation with Flexible Pose and Multi-View Joint Modeling","created":"2025-03-20","cited_by_count":14,"area":null},{"id":"2506.18839","title":"4Real-Video-V2: Fused View-Time Attention and Feedforward Reconstruction for 4D Scene Generation","created":"2025-06-18","cited_by_count":14,"area":null},{"id":"2308.09694","title":"Invariant Training 2D-3D Joint Hard Samples for Few-Shot Point Cloud Recognition","created":"2023-08-18","cited_by_count":13,"area":null},{"id":"2409.05606","title":"CustomContrast: A Multilevel Contrastive Perspective For Subject-Driven Text-to-Image Customization","created":"2024-09-09","cited_by_count":13,"area":null},{"id":"2409.08520","title":"GroundingBooth: Grounding Text-to-Image Customization","created":"2024-09-13","cited_by_count":13,"area":null},{"id":"2406.11579","title":"Duoduo CLIP: Efficient 3D Understanding with Multi-View Images","created":"2024-06-17","cited_by_count":12,"area":null},{"id":"2412.09997","title":"GT23D-Bench: A Comprehensive General Text-to-3D Generation Benchmark","created":"2024-12-13","cited_by_count":12,"area":null},{"id":"2501.18804","title":"Zero-Shot Novel View and Depth Synthesis with Multi-View Geometric Diffusion","created":"2025-01-30","cited_by_count":12,"area":null},{"id":"2312.07315","title":"NVS-Adapter: Plug-and-Play Novel View Synthesis from a Single Image","created":"2023-12-12","cited_by_count":11,"area":null},{"id":"2503.15485","title":"TULIP: Towards Unified Language-Image Pretraining","created":"2025-03-19","cited_by_count":11,"area":null},{"id":"2506.02265","title":"Rig3R: Rig-Aware Conditioning for Learned 3D Reconstruction","created":"2025-06-02","cited_by_count":11,"area":null},{"id":"2311.15510","title":"CaesarNeRF: Calibrated Semantic Representation for Few-shot Generalizable Neural Rendering","created":"2023-11-27","cited_by_count":10,"area":null},{"id":"2407.06704","title":"Self-supervised visual learning from interactions with objects","created":"2024-07-09","cited_by_count":10,"area":null},{"id":"2505.21974","title":"BOFormer: Learning to Solve Multi-Objective Bayesian Optimization via Non-Markovian RL","created":"2025-05-28","cited_by_count":10,"area":null},{"id":"2408.17027","title":"ConDense: Consistent 2D/3D Pre-training for Dense and Sparse Features from Multi-View Images","created":"2024-08-30","cited_by_count":9,"area":null},{"id":"2502.17053","title":"PointSea: Point Cloud Completion via Self-structure Augmentation","created":"2025-02-24","cited_by_count":9,"area":null},{"id":"2505.01838","title":"MVHumanNet++: A Large-scale Dataset of Multi-view Daily Dressing Human Captures with Richer Annotations for 3D Human Digitization","created":"2025-05-03","cited_by_count":9,"area":null},{"id":"2411.12592","title":"SPARS3R: Semantic Prior Alignment and Regularization for Sparse 3D Reconstruction","created":"2024-11-15","cited_by_count":8,"area":null},{"id":"2505.02178","title":"Sparfels: Fast Reconstruction from Sparse Unposed Imagery","created":"2025-05-04","cited_by_count":8,"area":null},{"id":"2603.11421","title":"ShotVerse: Advancing Cinematic Camera Control for Text-Driven Multi-Shot Video Creation","created":"2026-03-12","cited_by_count":7,"area":null},{"id":"2306.02243","title":"Retrieval-Enhanced Visual Prompt Learning for Few-shot Classification","created":"2023-06-04","cited_by_count":6,"area":null},{"id":"2503.06053","title":"DropletVideo: A Dataset and Approach to Explore Integral Spatio-Temporal Consistent Video Generation","created":"2025-03-08","cited_by_count":6,"area":null},{"id":"2505.15287","title":"GS2E: Gaussian Splatting is an Effective Data Generator for Event Stream Generation","created":"2025-05-21","cited_by_count":6,"area":null},{"id":"2508.01464","title":"Can3Tok: Canonical 3D Tokenization and Latent Modeling of Scene-Level 3D Gaussians","created":"2025-08-02","cited_by_count":6,"area":null},{"id":"2604.07279","title":"Mem3R: Streaming 3D Reconstruction with Hybrid Memory via Test-Time Training","created":"2026-04-08","cited_by_count":6,"area":null},{"id":"2405.05143","title":"Learning Object Semantic Similarity with Self-Supervision","created":"2024-04-19","cited_by_count":5,"area":null},{"id":"2410.23658","title":"GS-Blur: A 3D Scene-Based Dataset for Realistic Image Deblurring","created":"2024-10-31","cited_by_count":5,"area":null},{"id":"2502.17860","title":"UniGS: Unified Language-Image-3D Pretraining with Gaussian Splatting","created":"2025-02-25","cited_by_count":5,"area":null},{"id":"2504.03875","title":"3D Scene Understanding Through Local Random Access Sequence Modeling","created":"2025-04-04","cited_by_count":5,"area":null},{"id":"2504.06178","title":"Flash Sculptor: Modular 3D Worlds from Objects","created":"2025-04-08","cited_by_count":5,"area":null},{"id":"2506.11924","title":"Aligned Novel View Image and Geometry Synthesis via Cross-modal Attention Instillation","created":"2025-06-13","cited_by_count":5,"area":null},{"id":"2506.14315","title":"ImmerseGen: Agent-Guided Immersive World Generation with Alpha-Textured Proxies","created":"2025-06-17","cited_by_count":5,"area":null},{"id":"2306.10730","title":"UniG3D: A Unified 3D Object Generation Dataset","created":"2023-06-19","cited_by_count":4,"area":null},{"id":"2406.09305","title":"Toffee: Efficient Million-Scale Dataset Construction for Subject-Driven Text-to-Image Generation","created":"2024-06-13","cited_by_count":4,"area":null},{"id":"2410.18962","title":"Where Am I and What Will I See: An Auto-Regressive Model for Spatial Localization and View Prediction","created":"2024-10-24","cited_by_count":4,"area":null},{"id":"2503.08352","title":"Mitigating Ambiguities in 3D Classification with Gaussian Splatting","created":"2025-03-11","cited_by_count":4,"area":null},{"id":"2507.16406","title":"Sparse-View 3D Reconstruction: Recent Advances and Open Challenges","created":"2025-07-22","cited_by_count":4,"area":null},{"id":"2508.21222","title":"Generalizable Object Re-Identification via Visual In-Context Prompting","created":"2025-08-28","cited_by_count":4,"area":null},{"id":"2509.06950","title":"Scaling Transformer-Based Novel View Synthesis Models with Token Disentanglement and Synthetic Data","created":"2025-09-08","cited_by_count":4,"area":null}],"next_cursor":"100"}