Potentially Visible Hidden-Volume Rendering for Multi-View Warping
Janghun Kim, Sungkil Lee
Abstract
This paper presents the model and rendering algorithm of Potentially Visible Hidden Volumes (PVHVs) for multi-view image warping. PVHVs are 3D volumes that are occluded at a known source view, but potentially visible at novel views. Given a bound of novel views, we define PVHVs using the edges of foreground fragments from the known view and the bound of novel views. PVHVs can be used to batch-test the visibilities of source fragments without iterating individual novel views in multi-fragment rendering, and thereby, cull redundant fragments prior to warping. We realize the model of PVHVs in Depth Peeling (DP). Our Effective Depth Peeling (EDP) can reduce the number of completely hidden fragments, capture important fragments early, and reduce warping cost. We demonstrate the benefit of our PVHVs and EDP in terms of memory, quality, and performance in multi-view warping.
Ask about this paper
Ask your agent about it.
Lune has read the top-tier papers around this one, so every answer names the papers it rests on.
Related papers
- Trim Regions for Online Computation of From-Region Potentially Visible SetsPhilip Voglreiter, Bernhard Kerbl, Alexander Weinrauch, Joerg H. Mueller et al.SIGGRAPH 2023 · 6 citations
- Depth Peeling for High-Fidelity Gaussian-Enhanced Surfel RenderingKeyang Ye, Hongzhi Wu, Kun ZhouCVPR 2026 · 2 citations
- Extreme View SynthesisInchang Choi, Orazio Gallo, Alejandro J. Troccoli, Min H. Kim et al.ICCV 2019 · 207 citations
- Neural Point Cloud Rendering via Multi-Plane ProjectionPeng Dai, Yinda Zhang, Zhuwen Li, Shuaicheng Liu et al.CVPR 2020
- Deep 3D Mask Volume for View Synthesis of Dynamic ScenesKai-En Lin, Lei Xiao, Feng Liu, Guowei Yang et al.ICCV 2021 · 42 citations
