Papers › Direct-PoseNet: Absolute Pose Regression with Photometric Consistency

Direct-PoseNet: Absolute Pose Regression with Photometric Consistency

8 Apr 2021arXiv:2104.04073archive 2025-07-28

Shuai Chen, ZiRui Wang, Victor Prisacariu

We present a relocalization pipeline, which combines an absolute pose regression (APR) network with a novel view synthesis based direct matching module, offering superior accuracy while maintaining low inference time. Our contribution is twofold: i) we design a direct matching module that supplies a photometric supervision signal to refine the pose regression network via differentiable rendering; ii) we modify the rotation representation from the classical quaternion to SO(3) in pose regression, removing the need for balancing rotation and translation loss terms. As a result, our network Direct-PoseNet achieves state-of-the-art performance among all other single-image APR methods on the 7-Scenes benchmark and the LLFF dataset.

PaperPDFCodeCode 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="2104.04073")

Code

Syntology Ran 5 of 22 code samples harvested from 1 repository linked to this paper; 17 have no recorded run. Of those that ran: 1 ran · violated contract; 3 ran · our draft was wrong; 1 ran · fixture could not drive it.

By repository: official repository: 22 samples from 1 repository, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

ActiveVisionLab/direct-posenet officialmentioned on GitHubpytorchMIT 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

22 samples harvested; 5 ran; 0 honoured the contract we drafted; 17 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 · violated contract
3ran · our draft was wrong
1ran · fixture could not drive it
17unverified

Licence: 0 of the 22 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 ActiveVisionLab/direct-posenet. “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.

batchify ActiveVisionLab/direct-posenet/script/run_nerf.py official repository ran · our draft was wrong MIT (permissive) · fd57e365830d09de · report
ndc_rays ActiveVisionLab/direct-posenet/dataset_loaders/frustum/frustum_util.py official repository ran · our draft was wrong MIT (permissive) · 4366d225ac2fe16d · report
normalize ActiveVisionLab/direct-posenet/dataset_loaders/load_llff.py official repository ran · violated contract fingerprinted MIT (permissive) · 1d6f8390d799f055 · report
run_network ActiveVisionLab/direct-posenet/script/run_nerf.py official repository ran · our draft was wrong MIT (permissive) · 8f235fb889b93174 · report
viewmatrix ActiveVisionLab/direct-posenet/dataset_loaders/load_llff.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · aa52acee18f54d38 · report
PoseLoss ActiveVisionLab/direct-posenet/script/direct_pose_model.py official repository unverified MIT (permissive) · 019452c6c4769152 · report
camera_frustum_initializer ActiveVisionLab/direct-posenet/dataset_loaders/load_7Scenes.py official repository unverified MIT (permissive) · c9625d568955ffac · report
filter_hook ActiveVisionLab/direct-posenet/script/pose_model.py official repository unverified MIT (permissive) · c7bea2e25b534df3 · report
get_embedder ActiveVisionLab/direct-posenet/script/run_nerf_helpers.py official repository unverified MIT (permissive) · 737c403b9968484c · report
get_rays ActiveVisionLab/direct-posenet/script/run_nerf_helpers.py official repository unverified MIT (permissive) · c03007b6cafd9690 · report
get_rays ActiveVisionLab/direct-posenet/dataset_loaders/frustum/frustum_util.py official repository unverified MIT (permissive) · 3627b1373cfa4e33 · report
get_rays_np ActiveVisionLab/direct-posenet/script/run_nerf_helpers.py official repository unverified MIT (permissive) · 929e526ea6fc4975 · report
initK ActiveVisionLab/direct-posenet/dataset_loaders/load_7Scenes.py official repository unverified MIT (permissive) · 13be307ef0c24c0e · report
is_inside_frustum ActiveVisionLab/direct-posenet/dataset_loaders/load_7Scenes.py official repository unverified MIT (permissive) · f869aad3a90d4156 · report
prepare_data ActiveVisionLab/direct-posenet/script/prepare_data.py official repository unverified MIT (permissive) · 6e2a649fb0ac265e · report
preprocess_data ActiveVisionLab/direct-posenet/script/pose_model.py official repository unverified MIT (permissive) · 1d4f466dd0b12111 · report
process_poses_rotmat ActiveVisionLab/direct-posenet/dataset_loaders/seven_scenes.py official repository unverified MIT (permissive) · ecb54915a44f88b3 · report
ptstocam ActiveVisionLab/direct-posenet/dataset_loaders/load_llff.py official repository unverified MIT (permissive) · 36f5de7a0aae4a9b · report
qlog ActiveVisionLab/direct-posenet/dataset_loaders/seven_scenes.py official repository unverified MIT (permissive) · 667f7d75349dad79 · report
quaternion_angular_error ActiveVisionLab/direct-posenet/script/pose_model.py official repository unverified MIT (permissive) · d93282ce062190e1 · report
rgb_loss ActiveVisionLab/direct-posenet/script/direct_pose_model.py official repository unverified MIT (permissive) · 26d5443e570cf251 · report
run_network_DNeRF ActiveVisionLab/direct-posenet/script/run_nerf.py official repository unverified MIT (permissive) · 5bd6e1cb35d8420a · report

Tasks

Camera RelocalizationNovel View Synthesisregression

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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