Kuis terkait panduan · Keras Tingkat

Kuis Estimasi Kedalaman Monokuler

Menilai ambiguitas kedalaman monokuler, sintesis tampilan yang diawasi sendiri, skala relatif, dan bukti model kedalaman spesifik versi.

Jalur panduan terkaitEstimasi Kedalaman Monokuler
Pertanyaan 1 dari 8

Apa yang membuat estimasi kedalaman menjadi 'bermata'?

Pratinjau setiap pertanyaan8 pertanyaan

Jawaban dan penjelasan muncul saat Anda mengikuti kuis.

  1. Apa yang membuat estimasi kedalaman menjadi 'bermata'?
    • Ini menyimpulkan kedalaman dari satu gambar atau kamera, bukan stereo atau sensor
    • Ia menggunakan dua kamera yang diberi jarak seperti mata manusia
    • Ini hanya berfungsi pada gambar hitam-putih
    • Ini membutuhkan pemindai lidar yang terpasang pada kamera
  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. Isyarat manakah yang TIDAK diandalkan secara langsung oleh jaringan monokuler untuk kedalaman?
    • Ukuran relatif suatu benda
    • Gradien tekstur dan perspektif
    • Oklusi (objek mana yang menghalangi objek lain)
    • Perbedaan stereo antara dua kamera secara bersamaan
  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