Pose-Free Feed-Forward 3D Inpainting via Learnable Mask Attention and Support Token Refinement
cs.CV
Submitted: 2026-10-08
Updated: 2026-10-08
Project page: https://rorisis.github.io/FreeInpaint
Terminology
Sources
- Multi-layer Learnable Attention Mask for Multimodal Tasks
- ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth
- Demystifying MMD GANs
- Depth Pro: Sharp Monocular Metric Depth in Less Than a Second
- LRM: Large Reconstruction Model for Single Image to 3D
- MapAnything: Universal Feed-Forward Metric 3D Reconstruction
- InFusion: Inpainting 3D Gaussians via Learning Depth Completion from Diffusion Prior
- SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations
- DINOv2: Learning Robust Visual Features without Supervision
- NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction
- IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models