# Sparse-input reconstruction Area: [3D reconstruction and neural rendering](https://mlsanity.com/recon3d/index.md). HTML: https://mlsanity.com/recon3d/sparse-input-reconstruction/ ## Key facts - Sparse-input reconstruction: 883 papers on arXiv since 2021 (data through 19 Oct 2026). - 270 of its 883 mapped papers (31%) cite “DUSt3R: Geometric 3D Vision Made Easy” (2023, arXiv 2312.14132). - 235 of its 883 mapped papers (27%) cite “Zero-1-to-3: Zero-shot One Image to 3D Object” (2023, arXiv 2303.11328). - 42 new papers 1 Oct–19 Oct. ## Most cited here - [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023), cited by 270 papers here - [Zero-1-to-3: Zero-shot One Image to 3D Object](https://mlsanity.com/paper/2303.11328/) (2023), cited by 235 papers here - [Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction](https://mlsanity.com/paper/2109.00512/) (2021), cited by 164 papers here - [LRM: Large Reconstruction Model for Single Image to 3D](https://mlsanity.com/paper/2311.04400/) (2023), cited by 138 papers here - [Continuous 3D Perception Model with Persistent State](https://mlsanity.com/paper/2501.12387/) (2025), cited by 127 papers here - [SyncDreamer: Generating Multiview-consistent Images from a Single-view Image](https://mlsanity.com/paper/2309.03453/) (2023), cited by 126 papers here - [IBRNet: Learning Multi-View Image-Based Rendering](https://mlsanity.com/paper/2102.13090/) (2021), cited by 122 papers here - [DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision](https://mlsanity.com/paper/2312.16256/) (2023), cited by 115 papers here - [Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass](https://mlsanity.com/paper/2501.13928/) (2025), cited by 106 papers here - [Wonder3D: Single Image to 3D using Cross-Domain Diffusion](https://mlsanity.com/paper/2310.15008/) (2023), cited by 105 papers here ## New (1 Oct–19 Oct) - [ReDT: Resolution-Decoupled Visual Geometry Transformer](https://mlsanity.com/paper/2610.25517/) (2026-10-18) - [LonGaussian: Tracking Foundation Priors for Long-Context Feedforward Gaussian Reconstruction](https://mlsanity.com/paper/2610.23250/) (2026-10-16) - [Motion- and Gravity-Aware Feedforward 3D Reconstruction](https://mlsanity.com/paper/2610.22177/) (2026-10-15) - [GeoPano: Towards Geometrically Accurate 3D Reconstruction from a Single Panorama](https://mlsanity.com/paper/2610.21297/) (2026-10-15) - [ESC: Escaping 2D Diffusion Ambiguity with Geometric Constraints for Consistent Novel View Synthesis](https://mlsanity.com/paper/2610.23732/) (2026-10-14) - [InfiniSplat v2: Analyzing and Improving Feed-Forward 3DGS from Any Views](https://mlsanity.com/paper/2610.20341/) (2026-10-14) - [Remember, Revisit, Revise: Scaffold Memory for Long-Horizon 3D Geometry](https://mlsanity.com/paper/2610.19674/) (2026-10-14) - [MagicGarment: Benchmarking Single-Image Standalone 3D Garment Reconstruction](https://mlsanity.com/paper/2610.19623/) (2026-10-14) - [Holi-Spatial 360: Generative Reconstruction from Sparse Panoramas for Spatial Rendering and Intelligence](https://mlsanity.com/paper/2610.19502/) (2026-10-14) - [3D-VITAL: Visibility-aware Identity Training from Artificial Liftings of 3D Reconstruction model for Cross-View Object Re-Identification](https://mlsanity.com/paper/2610.16692/) (2026-10-12) - [BAT3R: Robust Online 3D Reconstruction with Bayesian Adaptive State Updates](https://mlsanity.com/paper/2610.16330/) (2026-10-12) - [Graph3R: Unifying View Graph Initialization with Feed-Forward Reconstruction](https://mlsanity.com/paper/2610.16272/) (2026-10-12) - [Sharper Frames, Worse Rooms: Viewpoint Coverage Dominates Image Quality in Feed-Forward 3D Reconstruction](https://mlsanity.com/paper/2610.15854/) (2026-10-11) - [UniForge3D: Joint 3D Reconstruction and Generation in a Shared Anchor-Guided Space](https://mlsanity.com/paper/2610.15357/) (2026-10-11) - [Drive3R: Block-wise Streaming Geometric Foundation Models for Autonomous Driving](https://mlsanity.com/paper/2610.15112/) (2026-10-10) - [PURE: Refining Feed-forward 3D Reconstruction with Unlabeled Post-training](https://mlsanity.com/paper/2610.14698/) (2026-10-10) - [Demiurge: Forging Navigable 4D Worlds via Autoregressive Video Rerendering](https://mlsanity.com/paper/2610.14685/) (2026-10-10) - [NOFACE3D: NOise-scheduled Focused Anchoring and Controlled Enhancement for 3D Generation](https://mlsanity.com/paper/2610.13050/) (2026-10-09) - [Zebra3D: Efficient Hybrid Foundation Models For Scalable 3D Reconstruction](https://mlsanity.com/paper/2610.12727/) (2026-10-08) - [LEGO: A Lifting-Free Approach for Exocentric-to-Egocentric Video Generation](https://mlsanity.com/paper/2610.12442/) (2026-10-08) - [Slot3R: Set-Associative Spatial Memory for Streaming 3D Reconstruction](https://mlsanity.com/paper/2610.12282/) (2026-10-08) - [Pose-Free Feed-Forward 3D Inpainting via Learnable Mask Attention and Support Token Refinement](https://mlsanity.com/paper/2610.11857/) (2026-10-08) - [Tetris3D: 3D Scene Generation With Objects That Fit Together](https://mlsanity.com/paper/2610.10539/) (2026-10-07) - [OmniCam: Omni-Camera Trajectory Generation via Geometry-Grounded Pose Token Learning](https://mlsanity.com/paper/2610.09513/) (2026-10-07) - [Hardware-aware Calibrated Clustered Attention for Efficient Visual Geometric Transformers](https://mlsanity.com/paper/2610.09274/) (2026-10-07) - [RDGSplat: Render-Dedicated Geometry for Novel View Synthesis](https://mlsanity.com/paper/2610.09173/) (2026-10-06) - [Revar3r: gauge-aware perturbation uncertainty for feed-forward 3d reconstruction](https://mlsanity.com/paper/2610.07883/) (2026-10-06) - [AIMS: Anchor-Integrated Multi-View Synthesis for Scalable Novel View Rendering](https://mlsanity.com/paper/2610.07566/) (2026-10-06) - [Less Context, Better Geometry: Masked Geometric Encoder for Robust 3D Foundation Models](https://mlsanity.com/paper/2610.06813/) (2026-10-05) - [VGGT-Bridge: Beyond Sequential Pose Graphs via Coarse-Stride Skip Edges](https://mlsanity.com/paper/2610.06594/) (2026-10-05)