Behind the Scenes: Density Fields for Single View Reconstruction
Felix Wimbauer, Nan Yang, Christian Rupprecht, Daniel Cremers
2023Year
33Top-tier citations
Abstract
Figure 1 . Predicting a Density Field from a Single Image. Through a novel "density field" formulation, which decouples geometry from color, architectural improvements, and a novel self-supervised training scheme, our method learns to predict a volumetric scene representation from a single image in challenging conditions. The voxel occupancy view shows that our method predicts accurate density even in occluded regions, which is not possible in traditional depth prediction. Please check out our project page at fwmb.github.io/bts/.
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.
Cited by top-tier papers33
- SceneRF: Self-Supervised Monocular 3D Scene Reconstruction with Radiance FieldsAnh-Quan Cao, Raoul de CharetteICCV 2023 · 73 citations
- 3DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint VideosJiakai Sun, Han Jiao, Guangyuan Li, Zhanjie Zhang et al.CVPR 2024 · 72 citations
- HUGS: Holistic Urban 3D Scene Understanding via Gaussian SplattingHongyu Zhou, Jiahao Shao, Lu Xu, Dongfeng Bai et al.CVPR 2024 · 50 citations
- ViP-NeRF: Visibility Prior for Sparse Input Neural Radiance FieldsNagabhushan Somraj, Rajiv SoundararajanSIGGRAPH 2023 · 38 citations
- Sat2Density: Faithful Density Learning from Satellite-Ground Image PairsMing Qian, Jincheng Xiong, Gui-Song Xia, Nan XueICCV 2023 · 29 citations
Builds on24
- Instant neural graphics primitives with a multiresolution hash encodingThomas Müller, Alex Evans, Christoph Schied, Alexander KellerSIGGRAPH 2022 · 4,089 citations
- Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance FieldsJonathan T. Barron, Ben Mildenhall, Matthew Tancik, Peter Hedman et al.ICCV 2021 · 2,700 citations
- Digging Into Self-Supervised Monocular Depth EstimationClément Godard, Oisin Mac Aodha, Michael Firman, Gabriel J. BrostowICCV 2019 · 2,416 citations
- Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance FieldsJonathan T. Barron, Ben Mildenhall, Dor Verbin, Pratul P. Srinivasan et al.CVPR 2022 · 1,603 citations
- Neural Sparse Voxel FieldsLingjie Liu, Jiatao Gu, Kyaw Zaw Lin, Tat-Seng Chua et al.NeurIPS 2020 · 1,535 citations
Related papers
- SelfOcc: Self-Supervised Vision-Based 3D Occupancy PredictionYuanhui Huang, Wenzhao Zheng, Borui Zhang, Jie Zhou et al.CVPR 2024
- Boosting Self-Supervision for Single-View Scene Completion via Knowledge DistillationKeonhee Han, Dominik Muhle, Felix Wimbauer, Daniel CremersCVPR 2024
- Dream-to-Recon: Monocular 3D Reconstruction with Diffusion-Depth Distillation from Single ImagesPhilipp Wulff, Felix Wimbauer, Dominik Muhle, Daniel CremersICCV 2025 · 1 citation
- UnO: Unsupervised Occupancy Fields for Perception and ForecastingBen Agro, Quinlan Sykora, Sergio Casas, Thomas Gilles et al.CVPR 2024
- Mask3D: Pretraining 2D Vision Transformers by Learning Masked 3D PriorsJi Hou, Xiaoliang Dai, Zijian He, Angela Dai et al.CVPR 2023
