Skip to content

Latest commit

 

History

History
105 lines (81 loc) · 15.4 KB

Easy_3D.md

File metadata and controls

105 lines (81 loc) · 15.4 KB

Easy 3D

Zero Shot 3D Reconstruction

  • DUSt3R: Geometric 3D Vision Made Easy, CVPR 2024 [Paper] [Website] [Code]
  • MASt3R: Grounding Image Matching in 3D with MASt3R, arXiv 2024. [Paper] [Website] [Code]
  • Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs, arXiv 2024. [Paper] [Website] [Code]
  • Spann3R: 3D Reconstruction with Spatial Memory, 3DV 2025. [Paper] [Website] [Code]
  • MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion, arXiv 2024. [Paper] [Website] [Code]
  • No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images, arXiv 2024. [Paper] [Website] [Code]
  • ZeroGS: Training 3D Gaussian Splatting from Unposed Images, arXiv 2024. [Paper] [Website] [Code]
  • SelfSplat: Pose-Free and 3D Prior-Free Generalizable 3D Gaussian Splatting, arXiv 2024. [Paper] [Website] [Code]
  • 🔥 Large Spatial Model: End-to-end Unposed Images to Semantic 3D, NeurIPS 2024. [Paper] [Website] [Code]
  • DiffusionGS: Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation, arXiv 2024. [Paper] [Website] [Code]
  • MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds, arXiv 2024.12. [Paper] [Website] [Code]

Single View 3D Reconstruction

  • "Learning to Recover 3D Scene Shape from a Single Image", CVPR 2021. [Paper] [Code]
  • pixelNeRF: Neural Radiance Fields from One or Few Images, CVPR 2021. [Paper] [Website] [Code]
  • Behind the Scenes: Density Fields for Single View Reconstruction, CVPR 2023. [Paper] [Website] [Code]
  • Know Your Neighbors: Improving Single-View Reconstruction via Spatial Vision-Language Reasoning, CVPR 2024. [Paper] [Website] [Code]
  • Zero-1-to-3: Zero-shot One Image to 3D Object, ICCV 2023. [Paper] [Website] [Code]
  • RealFusion: 360° Reconstruction of Any Object from a Single Image, CVPR 2023. [Paper] [Website] [Code]
  • One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization, NeurIPS 2023. [Paper] [Website] [Code] [Demo]
  • One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion, CVPR 2024. [Paper] [Website] [Code] [Demo]
  • Wonder3D: Single Image to 3D using Cross-Domain Diffusion, CVPR 2024. [Paper] [Project] [Code] [Demo]
  • ImageDream: Image-Prompt Multi-view Diffusion for 3D Generation, arXiv 2023. [Paper] [Website] [Code]
  • 👍LRM: Large Reconstruction Model for Single Image to 3D, ICLR 2024. [Paper] [Website] [Code] [Demo]
  • DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Model, ICLR 2024 spotlight. [Paper] [Website]
  • TripoSR: Fast 3D Object Reconstruction from a Single Image , arXiv 2024. [Paper] [Code]
  • Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with Transformers , CVPR 2024. [Paper] [Website] [Code]
  • AGG: Amortized Generative 3D Gaussians for Single Image to 3D , TMLR 2024. [Paper] [Website]
  • LN3Diff: Scalable Latent Neural Fields Diffusion for Speedy 3D Generation , ECCV 2024. [Paper] [Website] [Code]
  • NViST: In the Wild New View Synthesis from a Single Image with Transformers , CVPR 2024. [Paper] [Website] [Code]
  • Splatter Image: Ultra-Fast Single-View 3D Reconstruction , CVPR 2024. [Paper] [Website] [Code] 1 V100
  • SSR: Single-view 3D Scene Reconstruction with High-fidelity Shape and Texture, 3DV 2024. [Paper] [Website] [Code]
  • "Dynamic Scene Reconstruction from Single Landscape Image Using 4D Gaussian in the Wild", arXiv 2024. [Paper] [Website]
  • GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation, arXiv 2024. [Paper] [Website] [Code] [Demo]
  • LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation, ECCV 2024 (Oral). [Paper] [Website] [Code] [Demo]
  • 🔥 TRELLIS: Structured 3D Latents for Scalable and Versatile 3D Generation, arXiv 2024. [Paper] [Website] [Code] [Demo]
  • MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation, arXiv 2024. [Paper] [Website] [Code]
  • DeepPriorAssembly: Zero-Shot Scene Reconstruction from Single Images with Deep Prior Assembly, NeurIPS 2024. [Paper] [Website] [Code]
  • DreamUp3D: Object-Centric Generative Models for Single-View 3D Scene Understanding and Real-to-Sim Transfer, R-AL 2024. [Paper]
  • SPAR3D: Stable Point-Aware Reconstruction of 3D Objects from Single Images, arXiv 2025.01. [Paper] [Website] [Code] [Demo]

Binocular Reconstruction

  • 🔥Binocular3DGS: Binocular-Guided 3D Gaussian Splatting with View Consistency for Sparse View Synthesis, NeurIPS 2024. [Paper] [Website] [Code]

  • ZoomGS: Dual-Camera Smooth Zoom on Mobile Phones, ECCV 2024. [Paper] [Website] [Code]

  • pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction , CVPR 2024. [Paper] [Website] [Code] 1 A100

  • latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstruction, ECCV 2024. [Paper] [Website] [Code]

  • HiSplat: Hierarchical 3D Gaussian Splatting for Generalizable Sparse-View Reconstruction, arXiv 2024. [Paper] [Website] [Code]

  • FoundationStereo: Zero-Shot Stereo Matching, arXiv 2025.01. [Paper] [Website] [Code]

  • GS2Mesh: Surface Reconstruction from Gaussian Splatting via Novel Stereo Views, ECCV 2024. [Paper] [Website] [Code]

Sparse View Reconstruction

  • InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Models, arXiv 2024. [Paper] [Website]

  • XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies, CVPR 2024. [Paper] [Website] [Code] [NVIDIA Toronto AI Lab]

  • fVDB: A Deep-Learning Framework for Sparse, Large-Scale, and High-Performance Spatial Intelligence, arXiv 2024. [Paper] [Website] [NVIDIA Toronto AI Lab]

  • SCube: Instant Large-Scale Scene Reconstruction using VoxSplats, NeurIPS 2024. [Paper] [Code] [Website]

  • MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images, ECCV2024. [Paper] [Code] [Website] 1 A100

  • MVSGaussian: Fast Generalizable Gaussian Splatting Reconstruction from Multi-View Stereo, ECCV 2024. [Paper] [Website] [Code]

  • MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Views, NeurIPS 2024. [Paper] [Website] [Code] 8 A100

  • DepthSplat: Connecting Gaussian Splatting and Depth, arXiv 2024. [Paper] [Website] [Code] 8 A100

  • SplatFormer: Point Transformer for Robust 3D Gaussian Splatting, arXiv 2024.11. [Paper] [Website] [Code]

Point Cloud Completion

  • SDS: Point-Cloud Completion with Pretrained Text-to-image Diffusion Models, NeurIPS 2023. [Paper] [Website] [Code]

Metric Depth

  • ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth, arXiv 2023. [Paper] [Code]

  • Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image, ICCV 2023. [Paper] [Code] [Website]

  • UniDepth: Universal Monocular Metric Depth Estimation, CVPR 2024. [Paper] [Code] [Website]

  • PatchFusion: An End-to-End Tile-Based Framework for High-Resolution Monocular Metric Depth Estimation, CVPR 2024. [Paper] [Website] [Code]

  • Depth Pro: Sharp Monocular Metric Depth in Less Than a Second, arXiv 2024. [Paper] [Code]

  • Depth Anything V2: A More Capable Foundation Model for Monocular Depth Estimation, NeurIPS 2024. [Paper] [Website] [Code]

  • Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimation, arXiv 2024. [Paper] [Website] [Code]