# Atlas: End-to-End 3D Scene Reconstruction from Posed Images

arXiv: https://arxiv.org/abs/2003.10432 · HTML: https://mlsanity.com/paper/2003.10432/

## Key facts

- Cited by 206 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Mar 2020.

## Built on by (most cited first, 30 of 206)

- [NICE-SLAM: Neural Implicit Scalable Encoding for SLAM](https://mlsanity.com/paper/2112.12130/) (2021)
- [SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving](https://mlsanity.com/paper/2303.09551/) (2023)
- [Cross-view Transformers for real-time Map-view Semantic Segmentation](https://mlsanity.com/paper/2205.02833/) (2022)
- [Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representation](https://mlsanity.com/paper/2205.04334/) (2022)
- [NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video](https://mlsanity.com/paper/2104.00681/) (2021)
- [MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors](https://mlsanity.com/paper/2412.12392/) (2024)
- [NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo](https://mlsanity.com/paper/2109.01129/) (2021)
- [Point-SLAM: Dense Neural Point Cloud-based SLAM](https://mlsanity.com/paper/2304.04278/) (2023)
- [ESLAM: Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fields](https://mlsanity.com/paper/2211.11704/) (2022)
- [ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection](https://mlsanity.com/paper/2106.01178/) (2021)
- [GaussianFormer: Scene as Gaussians for Vision-Based 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2405.17429/) (2024)
- [M2BEV: Multi-Camera Joint 3D Detection and Segmentation with Unified Birds-Eye View Representation](https://mlsanity.com/paper/2204.05088/) (2022)
- [Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splatting](https://mlsanity.com/paper/2312.10070/) (2023)
- [NeuMesh: Learning Disentangled Neural Mesh-based Implicit Field for Geometry and Texture Editing](https://mlsanity.com/paper/2207.11911/) (2022)
- [DN-Splatter: Depth and Normal Priors for Gaussian Splatting and Meshing](https://mlsanity.com/paper/2403.17822/) (2024)
- [Improving neural implicit surfaces geometry with patch warping](https://mlsanity.com/paper/2112.09648/) (2021)
- [Unconstrained Scene Generation with Locally Conditioned Radiance Fields](https://mlsanity.com/paper/2104.00670/) (2021)
- [NeuRIS: Neural Reconstruction of Indoor Scenes Using Normal Priors](https://mlsanity.com/paper/2206.13597/) (2022)
- [Neural 3D Scene Reconstruction with the Manhattan-world Assumption](https://mlsanity.com/paper/2205.02836/) (2022)
- [NeSF: Neural Semantic Fields for Generalizable Semantic Segmentation of 3D Scenes](https://mlsanity.com/paper/2111.13260/) (2021)
- [Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splats](https://mlsanity.com/paper/2410.12781/) (2024)
- [TransformerFusion: Monocular RGB Scene Reconstruction using Transformers](https://mlsanity.com/paper/2107.02191/) (2021)
- [GaussianFormer-2: Probabilistic Gaussian Superposition for Efficient 3D Occupancy Prediction](https://mlsanity.com/paper/2412.04384/) (2024)
- [SimpleRecon: 3D Reconstruction Without 3D Convolutions](https://mlsanity.com/paper/2208.14743/) (2022)
- [Neural 3D Reconstruction in the Wild](https://mlsanity.com/paper/2205.12955/) (2022)
- [GaussianWorld: Gaussian World Model for Streaming 3D Occupancy Prediction](https://mlsanity.com/paper/2412.10373/) (2024)
- [Fully Sparse 3D Occupancy Prediction](https://mlsanity.com/paper/2312.17118/) (2023)
- [VolRecon: Volume Rendering of Signed Ray Distance Functions for Generalizable Multi-View Reconstruction](https://mlsanity.com/paper/2212.08067/) (2022)
- [GO-Surf: Neural Feature Grid Optimization for Fast, High-Fidelity RGB-D Surface Reconstruction](https://mlsanity.com/paper/2206.14735/) (2022)
- [NeO 360: Neural Fields for Sparse View Synthesis of Outdoor Scenes](https://mlsanity.com/paper/2308.12967/) (2023)

## Abstract (arXiv)

We present an end-to-end 3D reconstruction method for a scene by directly regressing a truncated signed distance function (TSDF) from a set of posed RGB images. Traditional approaches to 3D reconstruction rely on an intermediate representation of depth maps prior to estimating a full 3D model of a scene. We hypothesize that a direct regression to 3D is more effective. A 2D CNN extracts features from each image independently which are then back-projected and accumulated into a voxel volume using the camera intrinsics and extrinsics. After accumulation, a 3D CNN refines the accumulated features and predicts the TSDF values. Additionally, semantic segmentation of the 3D model is obtained without significant computation. This approach is evaluated on the Scannet dataset where we significantly outperform state-of-the-art baselines (deep multiview stereo followed by traditional TSDF fusion) both quantitatively and qualitatively. We compare our 3D semantic segmentation to prior methods that use a depth sensor since no previous work attempts the problem with only RGB input.