Papers › Self-Distilled Depth Refinement with Noisy Poisson Fusion

Self-Distilled Depth Refinement with Noisy Poisson Fusion

26 Sep 2024arXiv:2409.17880archive 2025-07-28

Jiaqi Li, Yiran Wang, Jinghong Zheng, Zihao Huang, Ke Xian, Zhiguo Cao, Jianming Zhang

Depth refinement aims to infer high-resolution depth with fine-grained edges and details, refining low-resolution results of depth estimation models. The prevailing methods adopt tile-based manners by merging numerous patches, which lacks efficiency and produces inconsistency. Besides, prior arts suffer from fuzzy depth boundaries and limited generalizability. Analyzing the fundamental reasons for these limitations, we model depth refinement as a noisy Poisson fusion problem with local inconsistency and edge deformation noises. We propose the Self-distilled Depth Refinement (SDDR) framework to enforce robustness against the noises, which mainly consists of depth edge representation and edge-based guidance. With noisy depth predictions as input, SDDR generates low-noise depth edge representations as pseudo-labels by coarse-to-fine self-distillation. Edge-based guidance with edge-guided gradient loss and edge-based fusion loss serves as the optimization objective equivalent to Poisson fusion. When depth maps are better refined, the labels also become more noise-free. Our model can acquire strong robustness to the noises, achieving significant improvements in accuracy, edge quality, efficiency, and generalizability on five different benchmarks. Moreover, directly training another model with edge labels produced by SDDR brings improvements, suggesting that our method could help with training robust refinement models in future works.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 18 code samples harvested from 1 repository linked to this paper: 16 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 1 violated, 6 with no contract checked; 8 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 8 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 18 samples from 1 repository, 16 ran (8 with no instrument failure; 8 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 16 samples that ran has no recorded date.

lijia7/sddr officialmentioned in paperpytorchSyntology: 18 samples, 16 ran (8 instrument-failed) · 2 unverified 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

18 samples harvested: 16 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 1 violated, 6 with no contract checked; 8 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · violated contract
8ran · our draft was wrong
6ran
2unverified

Licence: 18 of the 18 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 lijia7/sddr. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

lijia7/sddr official repository 18 samples, 16 ran (8 instrument-failed) · 2 unverified
conv3x3 in 1,376 papers utils/Resnet.py ran · our draft was wrong no licence file found · pointer only · fac5364e2f53c6db · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded
convbn in 26 papers utils/submodule.py ran no licence file found · pointer only · 4589ab426bdcfbb8 · report fixture: signature in_channels:int/0/int, out_channels:int/0/int, kernel_size:int/0/int, stride:int/0/int, pad:int/0/int, dilation:int/0/int · returned Sequential · level recorded 2026-09-24
convbn_3d in 20 papers utils/submodule.py ran no licence file found · pointer only · 252c55c642e6a443 · report fixture: signature in_channels:int/0/int, out_channels:int/0/int, kernel_size:int/0/int, stride:int/0/int, pad:int/0/int · returned Sequential · level recorded 2026-09-24
convbn_group utils/submodule.py ran no licence file found · pointer only · ccefa291f3655847 · report fixture: signature in_channels:int/0/int, out_channels:int/0/int, groups:int/0/int, kernel_size:int/0/int, stride:int/0/int, pad:int/0/int, dilation:int/0/int · returned Sequential · level recorded 2026-09-24
extract_key utils/loss.py ran · honoured contract no licence file found · pointer only · 43506a7194f2d0e4 · report fixture: signature prediction:dict/0/?, key:str/0/str · returned Tensor · level recorded 2026-09-24
grad in 23 papers utils/loss.py ran · our draft was wrong fingerprinted no licence file found · pointer only · fc7d07b4f4b62c14 · report fixture: signature x:Tensor/3/float · returned tuple · level recorded 2026-09-24
grad_mask utils/loss.py ran · violated contract no licence file found · pointer only · 5e9fbfb37c21ea67 · report fixture: signature mask:Tensor/4/bool · returned Tensor · level recorded 2026-09-24
ind2sub utils/loss_my.py ran no licence file found · pointer only · 1028b315ba01565f · report fixture: signature idx:int/0/int, cols:int/0/int · returned tuple · level recorded 2026-09-24
randomSampling utils/loss_my.py ran no licence file found · pointer only · a2e302ea004c458d · report fixture: signature inputs:Tensor/1/float, targets:Tensor/1/float, masks:Tensor/1/float, threshold:float/0/float, sample_num:int/0/int · returned tuple · level recorded 2026-09-24
read_calib previous_evaluate_mid21.py ran · our draft was wrong no licence file found · pointer only · 64cb11b628183c55 · report fixture: signature calib_file_path:str/0/str · returned dict · level recorded 2026-09-24
read_pfm in 24 papers previous_evaluate_mid21.py ran · our draft was wrong no licence file found · pointer only · e8a81b58ad0c60f6 · report fixture: signature pfm_file_path:str/0/str · returned tuple · level recorded 2026-09-24
resnet18 in 432 papers utils/Resnet.py ran · our draft was wrong no licence file found · pointer only · 42823db097a59e8e · report fixture: signature pretrained:bool/0/bool · returned ResNet · level recorded 2026-09-24
resnet34 in 148 papers utils/Resnet.py ran · our draft was wrong no licence file found · pointer only · 39037cdb0fe985b1 · report fixture: signature pretrained:bool/0/bool · returned ResNet · level recorded 2026-09-24
strip_prefix_if_present in 16 papers thirdrepo/LeRes/net_tools.py ran · our draft was wrong no licence file found · pointer only · 5a951495ac113177 · report fixture: signature state_dict:dict/0/?, prefix:str/0/str · returned OrderedDict · level recorded 2026-09-22
strip_prefix_if_present in 16 papers thirdrepo/LeRes/multi_depth_model_woauxi.py ran · our draft was wrong no licence file found · pointer only · 1ded370f638346f4 · report fixture: signature state_dict:dict/0/?, prefix:str/0/str · returned OrderedDict · level recorded 2026-09-24
sub2ind in 11 papers utils/loss_my.py ran fingerprinted no licence file found · pointer only · c3cb701013b82647 · report fixture: signature r:int/0/int, c:int/0/int, cols:int/0/int · returned int · level recorded 2026-09-24
create_depth_map previous_evaluate_mid21.py unverified no licence file found · pointer only · 7f3fbdd3504065df · report
get_func in 5 papers thirdrepo/LeRes/net_tools.py unverified no licence file found · pointer only · c7599c5d5834563f · report

Tasks

Depth Estimation

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