No article text was recorded for this version.
generative geometric priors
Version 1 of 1490 papers613 conceptsfrozen 2026-10-04
Papers in this version
- Blog: O^2-Recon: Completing 3D Reconstruction of Occluded Objects in the Scene with a Pre-trained 2D Diffusion Model
- Blog: Generative Scene Synthesis via Incremental View Inpainting using RGBD Diffusion Models
- Blog: MagicHOI: Leveraging 3D Priors for Accurate Hand-object Reconstruction from Short Monocular Video Clips
- Blog: GAP: Gaussianize Any Point Clouds with Text Guidance
- Blog: ARTIC3D: Learning Robust Articulated 3D Shapes from Noisy Web Image Collections
- Blog: Learning Unified Decompositional and Compositional NeRF for Editable Novel View Synthesis
- Blog: SCube: Instant Large-Scale Scene Reconstruction using VoxSplats
- Blog: Follow My Hold: Hand-Object Interaction Reconstruction through Geometric Guidance
- Blog: BIGS: Bimanual Category-agnostic Interaction Reconstruction from Monocular Videos via 3D Gaussian Splatting
- Blog: ComboVerse: Compositional 3D Assets Creation Using Spatially-Aware Diffusion Guidance
- Blog: SceneComplete: Open-World 3D Scene Completion in Complex Real World Environments for Robot Manipulation
- Blog: Gen3DSR: Generalizable 3D Scene Reconstruction via Divide and Conquer from a Single View
- Blog: LangScene-X: Reconstruct Generalizable 3D Language-Embedded Scenes with TriMap Video Diffusion
- Blog: Layered Image Vectorization via Semantic Simplification
- Blog: Semantic Visual Localization
- Blog: HoloPart: Generative 3D Part Amodal Segmentation
- Blog: ShowMak3r: Compositional TV Show Reconstruction
- Blog: PCDreamer: Point Cloud Completion Through Multi-view Diffusion Priors
- Blog: Training-Free Instance-Aware 3D Scene Reconstruction and Diffusion-Based View Synthesis from Sparse Images
- Blog: StyleLight: HDR Panorama Generation for Lighting Estimation and Editing
- Blog: CAST: Component-Aligned 3D Scene Reconstruction from an RGB Image
- Blog: Reconstructing In-the-Wild Open-Vocabulary Human-Object Interactions
- Blog: LagerNVS: Latent Geometry for Fully Neural Real-time Novel View Synthesis
- Blog: VioLA: Aligning Videos to 2D LiDAR Scans
- Blog: Zero-Shot Scene Reconstruction from Single Images with Deep Prior Assembly
- Blog: TabletopGen: Instance-Level Interactive 3D Tabletop Scene Generation from Text or Single Image
- Blog: FATE: Full-head Gaussian Avatar with Textural Editing from Monocular Video
- Blog: Towards Geometric and Textural Consistency 3D Scene Generation via Single Image-guided Model Generation and Layout Optimization
- Blog: Complete 3D Human Reconstruction from a Single Incomplete Image
- Blog: A Modular Framework for Single-View 3D Reconstruction of Indoor Environments
- Blog: Extreme Relative Pose Estimation for RGB-D Scans via Scene Completion
- Blog: DiffRF: Rendering-Guided 3D Radiance Field Diffusion
- Blog: ARTIC3D: Learning Robust Articulated 3D Shapes from Noisy Web Image Collections
- Blog: SGD: Street View Synthesis with Gaussian Splatting and Diffusion Prior
- Blog: MorpheuS: Neural Dynamic $360^{\circ}$ Surface Reconstruction from Monocular RGB-D Video
- Blog: Mind the Gap: Geometrically Accurate Generative Reconstruction from Disjoint Views
- Blog: Learning Unified Decompositional and Compositional NeRF for Editable Novel View Synthesis
- Blog: StreetCrafter: Street View Synthesis with Controllable Video Diffusion Models
- Blog: 3D Shape Generation and Completion through Point-Voxel Diffusion
- Blog: Diffusion Probabilistic Models for Scene-Scale 3D Categorical Data
- Blog: 3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting
- Blog: GroundUp: Rapid Sketch-Based 3D City Massing
- Blog: RIC: Rotate-Inpaint-Complete for Generalizable Scene Reconstruction
- Blog: CHROME: Clothed Human Reconstruction with Occlusion-Resilience and Multiview-Consistency from a Single Image
- Blog: EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wild
- Blog: Amodal3R: Amodal 3D Reconstruction from Occluded 2D Images
- Blog: DreaMo: Articulated 3D Reconstruction From A Single Casual Video
- Blog: FATE: Full-head Gaussian Avatar with Textural Editing from Monocular Video
- Blog: Guess The Unseen: Dynamic 3D Scene Reconstruction from Partial 2D Glimpses
- Blog: WonderHuman: Hallucinating Unseen Parts in Dynamic 3D Human Reconstruction
- Blog: A Recipe for Generating 3D Worlds from a Single Image
- Blog: GO-NeRF: Generating Virtual Objects in Neural Radiance Fields
- Blog: Text2Immersion: Generative Immersive Scene with 3D Gaussians
- Blog: Robust-PIFu: Robust Pixel-aligned Implicit Function for 3D Human Digitalization from a Single Image
- Blog: GGS: Generalizable Gaussian Splatting for Lane Switching in Autonomous Driving
- Blog: NovelGS: Consistent Novel-view Denoising via Large Gaussian Reconstruction Model
- Blog: SOAR: Self-Occluded Avatar Recovery from a Single Video In the Wild
- Blog: DreaMo: Articulated 3D Reconstruction From A Single Casual Video
- Blog: RICo: Rotate-Inpaint-Complete for Generalizable Scene Reconstruction
- Blog: Joint Reconstruction of Spatially-Coherent and Realistic Clothed Humans and Objects from a Single Image
Showing 60 of 490 papers.
History & citation
Current · Permanent link
- Generative Priors for Sparse-View 3D Reconstruction merged into this direction (64% overlap)
- Amodal 3D Reconstruction via Generative Inpainting merged into this direction (66% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_generative_geometric_priors_2397e968,
title = {generative geometric priors},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/generative-geometric-priors/rdr_2397e96872eb451baa78465b19234137},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_generative_geometric_priors_2397e968_v1,
title = {generative geometric priors},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/generative-geometric-priors/rdr_2397e96872eb451baa78465b19234137/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}