monocular depth estimation
Monocular depth estimation refers to the process of predicting depth information from a single image, allowing for 3D scene understanding from 2D inputs, used in applications like autonomous driving and augmented reality.
- 3D Visual Illusion Depth Estimation
- Building 3D Representations and Generating Motions From a Single Image via Video-Generation
- Distil-E2D: Distilling Image-to-Depth Priors for Event-Based Monocular Depth Estimation
- EAG3R: Event-Augmented 3D Geometry Estimation for Dynamic and Extreme-Lighting Scenes
- Evaluating Robustness of Monocular Depth Estimation with Procedural Scene Perturbations
- FlowFeat: Pixel-Dense Embedding of Motion Profiles
- Jamais Vu: Exposing the Generalization Gap in Supervised Semantic Correspondence
- Jasmine: Harnessing Diffusion Prior for Self-supervised Depth Estimation
- MS-GS: Multi-Appearance Sparse-View 3D Gaussian Splatting in the Wild
- Object Concepts Emerge from Motion
- Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformers
- QSCA: Quantization with Self-Compensating Auxiliary for Monocular Depth Estimation
- RPG360: Robust 360 Depth Estimation with Perspective Foundation Models and Graph Optimization