Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 245

The DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.

CSPN++: Learning Context and Resource Aware Convolutional Spatial Propagation Networks for Depth Completion

Open access
Cheng, Xinjing, Wang, Peng, Guan, Chenye, Yang, Ruigang · 2020 · Proceedings of the AAAI Conference on Artificial Intelligence

Abstract

Depth Completion deals with the problem of converting a sparse depth map to a dense one, given the corresponding color image. Convolutional spatial propagation network (CSPN) is one of the state-of-the-art (SoTA) methods of depth completion, which recovers structural details of the scene. In this paper, we propose CSPN++, which further improves its effectiveness and efficiency by learning adaptive convolutional kernel sizes and the number of iterations for the propagation, thus the context and computational resource needed at each pixel could be dynamically assigned upon requests. Specifically, we formulate the learning of the two hyper-parameters as an architecture selection problem where various configurations of kernel sizes and numbers of iterations are first defined, and then a set of soft weighting parameters are trained to either properly assemble or select from the pre-defined configurations at each pixel. In our experiments, we find weighted assembling can lead to significant accuracy improvements, which we referred to as "context-aware CSPN", while weighted selection, "resource-aware CSPN" can reduce the computational resource significantly with similar or better accuracy. Besides, the resource needed for CSPN++ can be adjusted w.r.t. the computational budget automatically. Finally, to avoid the side effects of noise or inaccurate sparse depths, we embed a gated network inside CSPN++, which further improves the performance. We demonstrate the effectiveness of CSPN++ on the KITTI depth completion benchmark, where it significantly improves over CSPN and other SoTA methods 1.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1609/aaai.v34i07.6635

Cites

9 of 9 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 9 references

Cited by

See all 245

Metadata

Authors
Cheng, X., Wang, P., Guan, C., & Yang, R.
Venue
Proceedings of the AAAI Conference on Artificial Intelligence
Published
2020-04-03
Volume
34
Issue
07
Pages
10615-10622
ISSN
  • 2159-5399 (ISSN-L)
  • 2374-3468
OpenAlex
W2998031326
Cited by
245
References
9
FWCI
11.35
Type
conference paper
Language
en
Open access
diamond

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: CSPN++: Learning Context and Resource Aware Convolutional Spatial Propagation Networks for Depth Completion. https://app.cochat.ai/papers/10.1609/aaai.v34i07.6635
The paper
Cheng, X., Wang, P., Guan, C., & Yang, R. (2020). CSPN++: Learning Context and Resource Aware Convolutional Spatial Propagation Networks for Depth Completion. Proceedings of the AAAI Conference on Artificial Intelligence. https://doi.org/10.1609/aaai.v34i07.6635

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.