Papers › Objects as Points
Objects as Points
Xingyi Zhou, Dequan Wang, Philipp Krähenbühl
Detection identifies objects as axis-aligned boxes in an image. Most successful object detectors enumerate a nearly exhaustive list of potential object locations and classify each. This is wasteful, inefficient, and requires additional post-processing. In this paper, we take a different approach. We model an object as a single point --- the center point of its bounding box. Our detector uses keypoint estimation to find center points and regresses to all other object properties, such as size, 3D location, orientation, and even pose. Our center point based approach, CenterNet, is end-to-end differentiable, simpler, faster, and more accurate than corresponding bounding box based detectors. CenterNet achieves the best speed-accuracy trade-off on the MS COCO dataset, with 28.1% AP at 142 FPS, 37.4% AP at 52 FPS, and 45.1% AP with multi-scale testing at 1.4 FPS. We use the same approach to estimate 3D bounding box in the KITTI benchmark and human pose on the COCO keypoint dataset. Our method performs competitively with sophisticated multi-stage methods and runs in real-time.
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="1904.07850")
Code
Syntology Ran 10 of 130 code samples harvested from 29 repositories linked to this paper; 120 have no recorded run. Of those that ran: 5 ran · our draft was wrong; 3 ran · fixture could not drive it; 2 ran with no contract checked.
By repository: official repository: 5 samples from 1 repository, 0 ran; community (archive-listed): 125 samples from 28 repositories, 10 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.
76 repositories listed; official and paper-mentioned ones first.
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
130 samples harvested; 10 ran; 0 honoured the contract we drafted; 120 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.
Licence: 0 of the 130 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 29 repositories linked to this paper, official or community; each sample names its own and says which. “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.
ddb5a5004c8da97a · report
ae6073481dbd21a1 · report
61bf3906cbd2ee87 · report
169089410e43237f · report
4f4b2ca9d5d47c31 · report
c09475f6e66fe874 · report
65d7a40d70c53ed9 · report
7df13fb9e54d592b · report
fac5364e2f53c6db · report
dd1114865f06f0fd · report
e8526a516b4f9206 · report
52810b504f0d1066 · report
7d3872168d714f89 · report
647b8865c23ab104 · report
05ae9dbdeb8c2455 · report
8601226e45f31117 · report
3b0c73e4c57ebaad · report
260ab1e46f04f7a5 · report
e2276ea79814eb8a · report
08e10cc2d227ed25 · report
d16f204f2617bc44 · report
b1d10b955686c785 · report
f7fbaa70fe5a6de2 · report
e6e47938329d032a · report
8ab1ac1884abfcd8 · report
a588ee2fcfe75c03 · report
e086f3c2ab723b33 · report
0f43310d75bd2e2b · report
7f44fb0f1807eeb5 · report
e8a87bbfe3c97021 · report
20b9cab65fabb68c · report
dd51d0a500be5964 · report
5159f7238539ec88 · report
01fb05fe7b768f7b · report
8accefa95d8419ec · report
9af0e82c0b75647e · report
cb23aed966c647fd · report
10a285b10fa42f28 · report
4583d8c3cf1a89c0 · report
0d197d0570641721 · report
8e687ffb8f93da01 · report
53e69d020bbaeda3 · report
f7fd0bb0c09ac287 · report
a94712a96a4d7c61 · report
f2a4ab894c1492d7 · report
fc3dd573616f0e98 · report
1924afcc9ed964be · report
150daf0c961f1f6a · report
5f61628f4d5e3b95 · report
3e98aeed3e833dc6 · report
b6f9a9fa5382854e · report
fa854046bf72851b · report
11dc8b9e203d5e14 · report
ddf62713b304976d · report
6013528f5d57ced7 · report
18a2466103412f3f · report
7475e8faf0ea33a5 · report
ca7ad1a4c7d4631d · report
6437d24bcf003fe4 · report
4b7b909c66e73f75 · report
d0899bd338609b66 · report
86282b7f90be63f2 · report
98749cf97ebd3dfe · report
839c0b45153e267b · report
fb5265196a6237f4 · report
03390f76a0deb944 · report
b3fc6fe78497a950 · report
76d238f8733b4413 · report
b2749fa442e73f84 · report
db60c7a7f8325ae3 · report
9d91a96e09434a52 · report
9d627c4b862db734 · report
7bf982cd2568c239 · report
8675918b6498617d · report
6b6d92280fd55255 · report
52324b791723fee9 · report
ae039cec12ddf2f5 · report
336a62eb13aca943 · report
cc17d49a7b09fc05 · report
6fa872593fc6762b · report
f0a13f31d73d7cf8 · report
96f091903118b608 · report
cbd181cdff9ecbcb · report
135d4f616c6ba5be · report
e2b28a6f3d02b9c0 · report
951049ed28977b60 · report
e315d56ddea42a3b · report
7ad1e0b22139b4f4 · report
49486c6da3aba160 · report
abeb3190defe4c24 · report
60564ec6de28bd4a · report
9bf1259e24d7137a · report
42af9659af852ebd · report
bd225652b42085b5 · report
4983bb45b0c2630b · report
cbb1e79cf3f516f7 · report
c0b3d0e6e5a858ad · report
5fe1885f18062aad · report
cc58645c20561393 · report
351e439eb141a737 · report
3f73767eb7b287c8 · report
80380fd72a861ad4 · report
812a913400b31178 · report
f901c4094be5548b · report
9c6adb62e5178684 · report
2130654d7d34a8d0 · report
b1f6197ccf78b5ab · report
94bbd1f822b3b784 · report
2051cd7dbc7620b8 · report
16f6f633bab3eed3 · report
3ae76bd0c20d21eb · report
818971ef8aeedb18 · report
17e4425f7fc080bb · report
a8b124a90bcca90c · report
bd51c61f2bca13a2 · report
a4ffe73019b1f156 · report
3a56f4e48f2b2a62 · report
1ff52afc6aa25002 · report
68ccdf85018e74af · report
135d0a926fbd1b0f · report
66744e8b3c8d06d3 · report
8e2fdb3504fc1330 · report
97a9421d2cd16747 · report
212b85f0119b4751 · report
ecd3946b49d193b5 · report
b27c466ba62a1611 · report
ccf6375e48752566 · report
5f2a57ecefb0c647 · report
4b4f9f9b41542678 · report
e150ba705d7276f6 · report
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Object Detection | COCO test-dev | CenterNet-DLA (DLA-34, multi-scale) | APL | 56.0 | #182 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | CenterNet-DLA (DLA-34, multi-scale) | APM | 43.9 | #182 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | CenterNet-DLA (DLA-34, multi-scale) | APS | 21.5 | #182 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | CenterNet-DLA (DLA-34, multi-scale) | Hardware Burden | 26G | #182 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | CenterNet-DLA (DLA-34, multi-scale) | box mAP | 41.6 | #182 of 225 | Archive leaderboard | report |
| Object Detection | PASCAL VOC 2007 | CenterNet(DLA34, Flip, 512x512) | MAP | 80.7% | #11 of 30 | Archive leaderboard | report |
| Object Detection | UA-DETRAC | CenterNet | mAP | 83.48 | #4 of 9 | 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