引導式測驗 · 中等 等級
Plenoxels 和體素輻射場測驗
測試 Plenoxels 如何儲存稀疏體素中的輻射度、在沒有 MLP 的情況下優化係數以及正規化表示。
問題 1 的 8
與 NeRF 相比,Plenoxels 最令人驚訝的設計選擇是什麼?
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。
- 與 NeRF 相比,Plenoxels 最令人驚訝的設計選擇是什麼?
- 它根本不使用神經網絡
- 它使用更深層的神經網絡
- 它僅適用於 2D
- 它需要光達掃描儀
- Plenoxels 中的每個佔用體素儲存什麼來捕捉依賴視圖的顏色?
- 完整的 RGB 紋理貼圖
- 球諧係數
- 單獨的神經網絡
- 僅深度值
- What optimization-time comparison did the Plenoxels paper report on its evaluated benchmarks?
- Exactly the same optimization time on every scene
- About two orders of magnitude slower in all cases
- About two orders of magnitude faster than NeRF in the reported settings
- No measurable difference under any setup
- 如何沿著射線從體素網格取得值?
- 僅最近鄰查找
- 隨機抽樣
- 卷積濾波器
- 三線性插值
- What conclusion is supported by Plenoxels’ benchmark results?
- An explicit sparse grid can achieve NeRF-comparable results on the evaluated tasks without an MLP
- Neural networks are never useful for 3D vision
- Voxels always outperform every neural representation
- Volume rendering requires no optimization
- 為了保持效率,Plenoxels 體素網格如何儲存?
- 作為一個緻密的完全填充的立方體
- 作為僅保留佔用體素的稀疏網格
- 作為單一平面圖像
- 作為壓縮視訊幀
- What regularizer did the Plenoxels paper use to encourage spatial smoothness?
- 語音辨識損失
- A KL penalty between language models
- A total-variation regularizer on voxel coefficients
- A bitrate constraint on rendered images
- What does “Plenoxels” expand to?
- Planar neural outputs
- Perceptual linear voxels
- Point-level network samples
- Plenoptic voxels