Prueba de estimación de profundidad monocular

Las respuestas y explicaciones aparecen a medida que realiza el cuestionario.

1. ¿Qué hace que la estimación de profundidad sea "monocular"?
   • Infiere profundidad a partir de una sola imagen o cámara, no de estéreo o sensores.
   • Utiliza dos cámaras espaciadas como ojos humanos.
   • Sólo funciona en imágenes en blanco y negro.
   • Requiere un escáner lidar conectado a la cámara.
2. What does a monocular depth estimator predict for an image?
   • A stereo disparity field that requires two camera views
   • A per-pixel depth or relative-depth map from one camera view
   • A categorical object-label map with no distance estimate
   • A dense motion-vector field between two video frames
3. What data recipe does the Depth Anything V2 paper report?
   • Train only on real labeled images and discard synthetic data
   • Train on unlabeled audio and convert speech to depth maps
   • Train a DINOv2-G teacher on synthetic labeled images, then use its pseudo-labels on real images to train students
   • Use stereo disparity as labels for every image at inference time
4. ¿En qué señal NO dependen directamente las redes monoculares para obtener profundidad?
   • Tamaño relativo de los objetos.
   • Degradados de textura y perspectiva.
   • Oclusión (qué objeto bloquea a otro)
   • Disparidad estéreo entre dos cámaras simultáneas
5. What does Monodepth2 use to reduce the effect of moving objects in self-supervised training?
   • An auto-masking procedure that excludes pixels inconsistent with camera motion
   • A learned text tokenizer
   • A region-proposal network
   • A fixed depth value for every object
6. What new evaluation benchmark does the Depth Anything V2 paper introduce?
   • A benchmark of 2,000 full metric depth maps from LiDAR only
   • DA-2K, with sparse relative-depth pairs annotated across 1,000 images
   • A corpus of six public datasets and randomly captured photos
   • A camera-calibration set containing no depth comparisons
7. How can self-supervised monocular depth training obtain a learning signal?
   • By reading depth labels from every pixel
   • By converting image colors directly to meters
   • By reconstructing one view from adjacent video frames and penalizing photometric mismatch
   • By using only language captions
8. What does a relative-depth output indicate?
   • Exact meters for every pixel
   • Camera GPS position
   • Object identity only
   • Ordering or relative distance, not necessarily calibrated metric distance