# FineRecon: Depth-aware Feed-forward Network for Detailed 3D Reconstruction

arXiv: https://arxiv.org/abs/2304.01480 · HTML: https://mlsanity.com/paper/2304.01480/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 33 references that are in the map.
- First posted on arXiv 4 Apr 2023.

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction](https://mlsanity.com/paper/2106.10689/) (2021)
- [3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation](https://mlsanity.com/paper/1606.06650/) (2016)
- [EfficientNetV2: Smaller Models and Faster Training](https://mlsanity.com/paper/2104.00298/) (2021)
- [Volume Rendering of Neural Implicit Surfaces](https://mlsanity.com/paper/2106.12052/) (2021)
- [MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction](https://mlsanity.com/paper/2206.00665/) (2022)
- [Dense Depth Priors for Neural Radiance Fields from Sparse Input Views](https://mlsanity.com/paper/2112.03288/) (2021)
- [NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video](https://mlsanity.com/paper/2104.00681/) (2021)
- [Atlas: End-to-End 3D Scene Reconstruction from Posed Images](https://mlsanity.com/paper/2003.10432/) (2020)
- [NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo](https://mlsanity.com/paper/2109.01129/) (2021)
- [Efficient Neural Radiance Fields for Interactive Free-viewpoint Video](https://mlsanity.com/paper/2112.01517/) (2021)
- [DPSNet: End-to-end Deep Plane Sweep Stereo](https://mlsanity.com/paper/1905.00538/) (2019)
- [TransformerFusion: Monocular RGB Scene Reconstruction using Transformers](https://mlsanity.com/paper/2107.02191/) (2021)
- [SimpleRecon: 3D Reconstruction Without 3D Convolutions](https://mlsanity.com/paper/2208.14743/) (2022)
- [SG-NN: Sparse Generative Neural Networks for Self-Supervised Scene Completion of RGB-D Scans](https://mlsanity.com/paper/1912.00036/) (2019)
- [DeepVideoMVS: Multi-View Stereo on Video with Recurrent Spatio-Temporal Fusion](https://mlsanity.com/paper/2012.02177/) (2020)
- [Multi-View Stereo by Temporal Nonparametric Fusion](https://mlsanity.com/paper/1904.06397/) (2019)
- [VolumeFusion: Deep Depth Fusion for 3D Scene Reconstruction](https://mlsanity.com/paper/2108.08623/) (2021)
- [VoRTX: Volumetric 3D Reconstruction With Transformers for Voxelwise View Selection and Fusion](https://mlsanity.com/paper/2112.00236/) (2021)
- [3DVNet: Multi-View Depth Prediction and Volumetric Refinement](https://mlsanity.com/paper/2112.00202/) (2021)
- [MonoNeuralFusion: Online Monocular Neural 3D Reconstruction with Geometric Priors](https://mlsanity.com/paper/2209.15153/) (2022)
- [3D Former: Monocular Scene Reconstruction with 3D SDF Transformers](https://mlsanity.com/paper/2301.13510/) (2023)

## Built on by (most cited first, 17 of 17)

- [Learning Signed Distance Functions from Noisy 3D Point Clouds via Noise to Noise Mapping](https://mlsanity.com/paper/2306.01405/) (2023)
- [CVRecon: Rethinking 3D Geometric Feature Learning For Neural Reconstruction](https://mlsanity.com/paper/2304.14633/) (2023)
- [Reconstructing 4D Spatial Intelligence: A Survey](https://mlsanity.com/paper/2507.21045/) (2025)
- [AirPlanes: Accurate Plane Estimation via 3D-Consistent Embeddings](https://mlsanity.com/paper/2406.08960/) (2024)
- [DoubleTake: Geometry Guided Depth Estimation](https://mlsanity.com/paper/2406.18387/) (2024)
- [PlanarNeRF: Online Learning of Planar Primitives with Neural Radiance Fields](https://mlsanity.com/paper/2401.00871/) (2023)
- [Understanding while Exploring: Semantics-driven Active Mapping](https://mlsanity.com/paper/2506.00225/) (2025)
- [GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction](https://mlsanity.com/paper/2605.23888/) (2026)
- [Dynamic Scene 3D Reconstruction of an Uncooperative Resident Space Object](https://mlsanity.com/paper/2509.07932/) (2025)
- [PointRecon: Online Point-based 3D Reconstruction via Ray-based 2D-3D Matching](https://mlsanity.com/paper/2410.23245/) (2024)
- [Image-Plane Geometric Decoding for View-Invariant Indoor Scene Reconstruction](https://mlsanity.com/paper/2509.25744/) (2025)
- [UniFField: A Generalizable Unified Neural Feature Field for Visual, Semantic, and Spatial Uncertainties in Any Scene](https://mlsanity.com/paper/2510.06754/) (2025)
- [Privacy-Aware Sharing of Raw Spatial Sensor Data for Cooperative Perception](https://mlsanity.com/paper/2512.16265/) (2025)
- [Diffusion-Driven Inter-Outer Surface Separation for Point Clouds with Open Boundaries](https://mlsanity.com/paper/2602.00739/) (2026)
- [VFM-Recon: Unlocking Cross-Domain Scene-Level Neural Reconstruction with Scale-Aligned Foundation Priors](https://mlsanity.com/paper/2603.12657/) (2026)
- [TopoGS: Planar Reconstruction via Topology-aware 3D Gaussian Splatting](https://mlsanity.com/paper/2607.16838/) (2026)
- [WorldRecon: Generative Multi-View Mesh Reconstruction for Large-Scale 3D World](https://mlsanity.com/paper/2610.18846/) (2026)

## Abstract (arXiv)

Recent works on 3D reconstruction from posed images have demonstrated that direct inference of scene-level 3D geometry without test-time optimization is feasible using deep neural networks, showing remarkable promise and high efficiency. However, the reconstructed geometry, typically represented as a 3D truncated signed distance function (TSDF), is often coarse without fine geometric details. To address this problem, we propose three effective solutions for improving the fidelity of inference-based 3D reconstructions. We first present a resolution-agnostic TSDF supervision strategy to provide the network with a more accurate learning signal during training, avoiding the pitfalls of TSDF interpolation seen in previous work. We then introduce a depth guidance strategy using multi-view depth estimates to enhance the scene representation and recover more accurate surfaces. Finally, we develop a novel architecture for the final layers of the network, conditioning the output TSDF prediction on high-resolution image features in addition to coarse voxel features, enabling sharper reconstruction of fine details. Our method, FineRecon, produces smooth and highly accurate reconstructions, showing significant improvements across multiple depth and 3D reconstruction metrics.