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

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

23 Mar 2020ECCV 2020 8arXiv:2003.10432archive 2025-07-28

Zak Murez, Tarrence van As, James Bartolozzi, Ayan Sinha, Vijay Badrinarayanan, Andrew Rabinovich

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.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2003.10432")

Code

Syntology Ran 1 of 12 code samples harvested from 1 repository linked to this paper; 11 have no recorded run. Of those that ran: 1 ran with no contract checked.

By repository: community (archive-listed): 12 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

magicleap/Atlas mentioned on GitHubpytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

12 samples harvested; 1 ran; 0 honoured the contract we drafted; 11 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran
11unverified

Licence: 0 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from magicleap/Atlas. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

pad_scannet magicleap/Atlas/atlas/transforms.py community (archive-listed) ran Apache-2.0 (permissive) · 930cb92f559f5607 · report
conv1x1x1 magicleap/Atlas/atlas/backbone3d.py community (archive-listed) unverified Apache-2.0 (permissive) · 871844ec996c4499 · report
conv3x3x3 magicleap/Atlas/atlas/backbone3d.py community (archive-listed) unverified Apache-2.0 (permissive) · 345667d343bb0d99 · report
coordinates magicleap/Atlas/atlas/tsdf.py community (archive-listed) unverified Apache-2.0 (permissive) · 880183f37459c9c0 · report
depth_to_world magicleap/Atlas/atlas/tsdf.py community (archive-listed) unverified Apache-2.0 (permissive) · d673fe1180f63a4c · report
get_norm_3d magicleap/Atlas/atlas/backbone3d.py community (archive-listed) unverified Apache-2.0 (permissive) · 10e977bbee5162f4 · report
l1 magicleap/Atlas/atlas/evaluation.py community (archive-listed) unverified Apache-2.0 (permissive) · 60530e4179d62619 · report
load_info_json magicleap/Atlas/atlas/data.py community (archive-listed) unverified Apache-2.0 (permissive) · e0258b4df51c5013 · report
load_scannet_label_mapping magicleap/Atlas/atlas/datasets/scannet.py community (archive-listed) unverified Apache-2.0 (permissive) · 963283e33428e65d · report
log_transform magicleap/Atlas/atlas/heads3d.py community (archive-listed) unverified Apache-2.0 (permissive) · cc965a768c8eb8cb · report
map_frame magicleap/Atlas/atlas/data.py community (archive-listed) unverified Apache-2.0 (permissive) · cd19ec43da6ecc6e · report
transform_space magicleap/Atlas/atlas/transforms.py community (archive-listed) unverified Apache-2.0 (permissive) · 41439e78eb397c28 · report

Tasks

3D Reconstruction3D Scene Reconstruction3D Semantic SegmentationDepth EstimationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Reconstruction ScanNet Atlas (finetuned) 3DIoU 89.4 #1 of 1 Archive leaderboard report
3D Reconstruction ScanNet Atlas (finetuned) Chamfer Distance 37.2 #1 of 1 Archive leaderboard report
3D Reconstruction ScanNet Atlas (finetuned) L1 21.1 #1 of 1 Archive leaderboard report
Depth Estimation ScanNet Atlas (plain) RMSE 0.165 #1 of 2 Archive leaderboard report
Depth Estimation ScanNet Atlas (finetuned) RMSE 0.174 #2 of 2 Archive leaderboard report
Depth Estimation ScanNet Atlas (finetuned) absolute relative error 0.089 #2 of 2 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections