InfiniDepth：基於神經隱式場的任意分辨率與細粒度深度估計

摘要

現有的深度估計方法本質上受限於離散影像網格上的深度預測。這種表示方式限制了其向任意輸出解析度的擴展性，並阻礙了幾何細節的恢復。本文提出InfiniDepth方法，將深度表示為神經隱式場。通過簡單而有效的局部隱式解碼器，我們能夠在連續二維座標上查詢深度，實現任意解析度與細粒度深度估計。為更好評估方法性能，我們從五款不同遊戲中精選建構了高品質4K合成基準數據集，涵蓋具有豐富幾何與外觀細節的多樣化場景。大量實驗表明，InfiniDepth在相對深度與度量深度估計任務中，於合成與真實場景基準測試上均達到最先進性能，尤其在精細細節區域表現卓越。該方法還能在大幅視角變化下提升新視角合成任務的表現，生成更少空洞與偽影的高品質結果。

English

Existing depth estimation methods are fundamentally limited to predicting depth on discrete image grids. Such representations restrict their scalability to arbitrary output resolutions and hinder the geometric detail recovery. This paper introduces InfiniDepth, which represents depth as neural implicit fields. Through a simple yet effective local implicit decoder, we can query depth at continuous 2D coordinates, enabling arbitrary-resolution and fine-grained depth estimation. To better assess our method's capabilities, we curate a high-quality 4K synthetic benchmark from five different games, spanning diverse scenes with rich geometric and appearance details. Extensive experiments demonstrate that InfiniDepth achieves state-of-the-art performance on both synthetic and real-world benchmarks across relative and metric depth estimation tasks, particularly excelling in fine-detail regions. It also benefits the task of novel view synthesis under large viewpoint shifts, producing high-quality results with fewer holes and artifacts.

InfiniDepth：基於神經隱式場的任意分辨率與細粒度深度估計

InfiniDepth: Arbitrary-Resolution and Fine-Grained Depth Estimation with Neural Implicit Fields

摘要

Support