AniGrad: Anisotropic Gradient-Adaptive Sampling for 3D Reconstruction From Monocular Video
Noah Stier, Alex Rich, Pradeep Sen, Tobias Höllerer
Abstract
Figure 1 . Reconstruction with adaptive & anisotropic resolution. Our 3D reconstruction system allocates computational resources effectively, using a variable sample pattern that adapts to the local surface complexity and orientation. A) The floor, which is flat and consistently oriented, is accurately reconstructed with a coarse resolution (4 cm). B) The cabinet is coarsely sampled in the vertical dimension because it exhibits no variation along that axis. Horizontally, however, it is sampled finely enough to accurately localize the surface. C) Object boundaries and other high-curvature structures are densely sampled to avoid aliasing, and to maintain high fidelity. The scene shown here is from ScanNet++ [39] .
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 37d13f35-95ae-4da4-b837-a8b8ba26215dBuilds on13
- ScanNet++: A High-Fidelity Dataset of 3D Indoor ScenesChandan Yeshwanth, Yueh-Cheng Liu, Matthias Nießner, Angela DaiICCV 2023 · 659 citations
- TransformerFusion: Monocular RGB Scene Reconstruction using TransformersAljaz Bozic, Pablo R. Palafox, Justus Thies, Angela Dai et al.NeurIPS 2021 · 185 citations
- NeRFusion: Fusing Radiance Fields for Large-Scale Scene ReconstructionXiaoshuai Zhang, Sai Bi, Kalyan Sunkavalli, Hao Su et al.CVPR 2022 · 94 citations
- VolumeFusion: Deep Depth Fusion for 3D Scene ReconstructionJaesung Choe, Sunghoon Im, François Rameau, Minjun Kang et al.ICCV 2021 · 83 citations
- FineRecon: Depth-aware Feed-forward Network for Detailed 3D ReconstructionNoah Stier, Anurag Ranjan, Alex Colburn, Yajie Yan et al.ICCV 2023 · 29 citations
Related papers
- VisFusion: Visibility-Aware Online 3D Scene Reconstruction from VideosHuiyu Gao, Wei Mao, Miaomiao LiuCVPR 2023
- 3D Gaussian Flats: Hybrid 2D/3D Photometric Scene ReconstructionMaria Taktasheva, Lily Goli, Alessandro Fiorini, Zhen Li et al.NeurIPS 2025 · 3 citations
- PlanarSplatting: Accurate Planar Surface Reconstruction in 3 MinutesBin Tan, Rui Yu, Yujun Shen, Nan XueCVPR 2025
- Boosting Multi-View Indoor 3D Object Detection Via Adaptive 3D Volume ConstructionRunmin Zhang, Zhu Yu, Si-Yuan Cao, Lingyu Zhu et al.ICCV 2025 · 3 citations
- ScanBot: Autonomous Reconstruction via Deep Reinforcement LearningHezhi Cao, Xi Xia, Guan Wu, Ruizhen Hu et al.SIGGRAPH 2023 · 13 citations
