Kuiz berkaitan panduan · Keras Tahap
DreamFusion dan Kuiz Pensampelan Penyulingan Skor
Fahami pengoptimuman NeRF DreamFusion, resapan 2D sebelumnya, Pensampelan Penyulingan Skor dan proses pemaparan berbilang paparan.
soalan 1 daripada 8
Apakah perwakilan 3D yang dioptimumkan oleh DreamFusion?
Pratonton setiap soalan8 soalan
Jawapan dan penjelasan muncul semasa anda mengambil kuiz.
- Apakah perwakilan 3D yang dioptimumkan oleh DreamFusion?
- A NeRF (Medan Sinaran Neural)
- Jaring poligon
- Awan titik daripada penderia kedalaman
- Grid voxel daripada data CT
- Berapa banyak data latihan 3D yang diperlukan oleh DreamFusion?
- Beberapa ratus imbasan
- tiada
- Berjuta-juta model CAD
- Satu objek rujukan setiap gesaan
- What is the computational shortcut in Score Distillation Sampling?
- It trains a new diffusion model every step
- Ia tidak menggunakan kecerunan sama sekali
- It uses a stop-gradient score signal instead of backpropagating through the diffusion model’s full Jacobian
- Ia hanya memberikan satu sudut pandangan tetap
- Why did DreamFusion use high classifier-free guidance in its experiments?
- Untuk mengurangkan memori GPU
- Untuk menjadikan output skala kelabu
- To guarantee accurate geometry
- To counter the oversmoothing tendency of SDS and encourage sharper prompt-conditioned results
- Model 2D manakah yang DreamFusion asal gunakan sebagai model beku sebelumnya?
- Imej Google
- Resapan Stabil 1.5
- DALL-E 2
- Midjourney
- 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
- 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
- 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