SOTAVerified

3D Inpainting

3D Inpainting is the removal of unwanted objects from a 3D scene, such that the replaced region is visually plausible and consistent with its context.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–21 of 21 papers

TitleStatusHype
IDDR-NGP: Incorporating Detectors for Distractors Removal with Instant Neural Radiance FieldCode1
PrimDiffusion: Volumetric Primitives Diffusion for 3D Human GenerationCode1
Advancing Brain Tumor Inpainting with Generative Models—0
Clutter Detection and Removal in 3D Scenes with View-Consistent Inpainting—0
Constructing a 3D Town from a Single Image—0
Geometry-Aware Diffusion Models for Multiview Scene Inpainting—0
3D Gaussian Inpainting with Depth-Guided Cross-View Consistency—0
3D StreetUnveiler with Semantic-Aware 2DGS—0
RefFusion: Reference Adapted Diffusion Models for 3D Scene Inpainting—0
Sparse InSAR Data 3D Inpainting for Ground Deformation Detection Along the Rail Corridor—0
SPIn-NeRF: Multiview Segmentation and Perceptual Inpainting with Neural Radiance Fields—0
IMFine: 3D Inpainting via Geometry-guided Multi-view Refinement—0
Inpaint3D: 3D Scene Content Generation using 2D Inpainting Diffusion—0
InNeRF360: Text-Guided 3D-Consistent Object Inpainting on 360-degree Neural Radiance Fields—0
MVIP-NeRF: Multi-view 3D Inpainting on NeRF Scenes via Diffusion Prior—0
MVPaint: Synchronized Multi-View Diffusion for Painting Anything 3D—0
NeRFiller: Completing Scenes via Generative 3D Inpainting—0
RealmDreamer: Text-Driven 3D Scene Generation with Inpainting and Depth Diffusion—0
fastWDM3D: Fast and Accurate 3D Healthy Tissue InpaintingCode0
3D Shape Completion using Multi-Resolution Spectral EncodingCode0
Visibility-Uncertainty-guided 3D Gaussian Inpainting via Scene Conceptional LearningCode0
Show:102550

No leaderboard results yet.