Click3R: Interactive Stereo 3D Reconstruction with Sparse Correspondence Clicks
cs.CV
Submitted: 2026-11-09
Updated: 2026-11-09
Terminology
Sources
- ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data
- TTT3R: 3D Reconstruction as Test-Time Training
- Any4D: Unified Feed-Forward Metric 4D Reconstruction
- MapAnything: Universal Feed-Forward Metric 3D Reconstruction
- G-CUT3R: Guided 3D Reconstruction with Camera and Depth Prior Integration
- Rig3R: Rig-Aware Conditioning for Learned 3D Reconstruction
- LoRA3D: Low-Rank Self-Calibration of 3D Geometric Foundation Models
- SAM 2: Segment Anything in Images and Videos
- $\pi^3$: Permutation-Equivariant Visual Geometry Learning
- Toon3D: Seeing Cartoons from New Perspectives
- WOD-E2E: Waymo Open Dataset for End-to-End Driving in Challenging Long-tail Scenarios
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