引導式測驗 · 硬 等級
DreamFusion 和 Score 蒸餾採樣測驗
了解 DreamFusion 的 NeRF 優化、2D 擴散先驗、分數蒸餾採樣和多視圖渲染過程。
問題 1 的 8
DreamFusion 優化了哪些 3D 表示?
預覽每個問題8 問題
當您參加測驗時,就會出現答案和解釋。
- DreamFusion 優化了哪些 3D 表示?
- NeRF(神經輻射場)
- 多邊形網格
- 來自深度感測器的點雲
- CT 資料的體素網格
- DreamFusion 需要多少 3D 訓練資料?
- 數百次掃描
- 無
- 數百萬個 CAD 模型
- 每個提示一個參考對象
- What is the computational shortcut in Score Distillation Sampling?
- It trains a new diffusion model every step
- 它根本不使用漸變
- It uses a stop-gradient score signal instead of backpropagating through the diffusion model’s full Jacobian
- 它只渲染一個固定的視點
- Why did DreamFusion use high classifier-free guidance in its experiments?
- 減少 GPU 內存
- 使輸出灰階化
- To guarantee accurate geometry
- To counter the oversmoothing tendency of SDS and encourage sharper prompt-conditioned results
- 最初的 DreamFusion 使用哪個 2D 模型作為其凍結先驗?
- Google 的圖像
- 穩定擴散1.5
- 達爾-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