3R-Adapter: Retrieval, Rewiring, and Refinement for Efficient Adaptation of 3D Reconstruction Model
cs.CV
Submitted: 2026-11-09
Updated: 2026-11-09
Code: https://github.com/PKU-OV3-LAB/3R-Adapter
Terminology
Sources
- $\pi^3$: Permutation-Equivariant Visual Geometry Learning
- Depth Anything 3: Recovering the Visual Space from Any Views
- Dark3R: Learning Structure from Motion in the Dark
- Human3R: Everyone Everywhere All at Once
- UniSH: Unifying Scene and Human Reconstruction in a Feed-Forward Pass
- Joint Optimization for 4D Human-Scene Reconstruction in the Wild
- Online3R: Online Learning for Consistent Sequential Reconstruction Based on Geometry Foundation Model
- DePT: Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning
- Gen3R: 3D Scene Generation Meets Feed-Forward Reconstruction
- Text-to-3D by Stitching a Multi-view Reconstruction Network to a Video Generator
- VGGRPO: Towards World-Consistent Video Generation with 4D Latent Reward
- Seeing in the Dark: Benchmarking Egocentric 3D Vision with the Oxford Day-and-Night Dataset
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs