Kuis Pengambilan Sampel Distilasi DreamFusion dan Skor

Jawaban dan penjelasan muncul saat Anda mengikuti kuis.

1. Representasi 3D apa yang dioptimalkan DreamFusion?
   • NeRF (Bidang Cahaya Neural)
   • Jaring poligon
   • Awan titik dari sensor kedalaman
   • Kotak voxel dari data CT
2. Berapa banyak data pelatihan 3D yang dibutuhkan DreamFusion?
   • Beberapa ratus pemindaian
   • Tidak ada
   • Jutaan model CAD
   • Satu objek referensi per prompt
3. What is the computational shortcut in Score Distillation Sampling?
   • It trains a new diffusion model every step
   • Itu tidak menggunakan gradien sama sekali
   • It uses a stop-gradient score signal instead of backpropagating through the diffusion model’s full Jacobian
   • Ini hanya menghasilkan satu sudut pandang yang tetap
4. Why did DreamFusion use high classifier-free guidance in its experiments?
   • Untuk mengurangi memori GPU
   • Untuk membuat keluaran menjadi abu-abu
   • To guarantee accurate geometry
   • To counter the oversmoothing tendency of SDS and encourage sharper prompt-conditioned results
5. Model 2D manakah yang digunakan DreamFusion asli sebagai model beku sebelumnya?
   • Gambar Google
   • Difusi Stabil 1.5
   • DALL-E 2
   • Midjourney
6. What artifact can arise when a 2D image prior guides a 3D scene across views?
   • A guaranteed watertight mesh
   • Duplicated faces or features on different sides of the object
   • A single grayscale output
   • A 3D object with no rendered views
7. Why does DreamFusion render the NeRF from sampled camera angles during optimization?
   • To avoid using the NeRF representation
   • To replace the text prompt with camera metadata
   • To let the 2D prior provide guidance from multiple views of the 3D scene
   • To create an audio soundtrack
8. What does an optimized NeRF allow a user to do with the generated scene?
   • Recover the original 3D training scan
   • Guarantee physically correct materials
   • Generate only the original training image
   • Render it from new viewpoints and relight it