Papers › QuartDepth: Post-Training Quantization for Real-Time Depth Estimation on the Edge

QuartDepth: Post-Training Quantization for Real-Time Depth Estimation on the Edge

20 Mar 2025CVPR 2025 1arXiv:2503.16709archive 2025-07-28

Xuan Shen, Weize Ma, Jing Liu, Changdi Yang, Rui Ding, Quanyi Wang, Henghui Ding, Wei Niu, Yanzhi Wang, Pu Zhao, Jun Lin, Jiuxiang Gu

Monocular Depth Estimation (MDE) has emerged as a pivotal task in computer vision, supporting numerous real-world applications. However, deploying accurate depth estimation models on resource-limited edge devices, especially Application-Specific Integrated Circuits (ASICs), is challenging due to the high computational and memory demands. Recent advancements in foundational depth estimation deliver impressive results but further amplify the difficulty of deployment on ASICs. To address this, we propose QuartDepth which adopts post-training quantization to quantize MDE models with hardware accelerations for ASICs. Our approach involves quantizing both weights and activations to 4-bit precision, reducing the model size and computation cost. To mitigate the performance degradation, we introduce activation polishing and compensation algorithm applied before and after activation quantization, as well as a weight reconstruction method for minimizing errors in weight quantization. Furthermore, we design a flexible and programmable hardware accelerator by supporting kernel fusion and customized instruction programmability, enhancing throughput and efficiency. Experimental results demonstrate that our framework achieves competitive accuracy while enabling fast inference and higher energy efficiency on ASICs, bridging the gap between high-performance depth estimation and practical edge-device applicability. Code: https://github.com/shawnricecake/quart-depth

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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 20 code samples harvested from 1 repository linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 12 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 20 samples from 1 repository, 8 ran (4 with no instrument failure; 4 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

shawnricecake/quart-depth officialmentioned in papermentioned on GitHubpytorchSyntology: 20 samples, 8 ran (4 instrument-failed) · 12 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

20 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 12 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
3ran · our draft was wrong
1ran; the contract check could not run
3ran
12unverified

Licence: 20 of the 20 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 shawnricecake/quart-depth. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

shawnricecake/quart-depth official repository 20 samples, 8 ran (4 instrument-failed) · 12 unverified
Conv2dLoRA metric3d/mono/model/decode_heads/RAFTDepthNormalDPTDecoder5_quant.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 20c34221b37d6e5a · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
ConvLoRA metric3d/mono/model/decode_heads/RAFTDepthNormalDPTDecoder5_quant.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 49d1c4292adc4fa0 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
LayerNorm2d in 18 papers metric3d/mono/model/decode_heads/RAFTDepthNormalDPTDecoder5_quant.py ran · metamorphic tier: invariant no licence file found · pointer only · 1a6b2908a95d686d · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
compute_depth_expectation metric3d/mono/model/decode_heads/RAFTDepthNormalDPTDecoder5_quant.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 5d5d6423c18aaa27 · report fixture: signature prob:Tensor/4/float, depth_values:Tensor/1/float · returned Tensor · level recorded 2026-09-22
coords_grid in 24 papers metric3d/mono/model/decode_heads/RAFTDepthNormalDPTDecoder5_quant.py ran · honoured contract fingerprinted no licence file found · pointer only · bd06769ee467a01c · report fixture: signature batch:int/0/int, ht:int/0/int, wd:int/0/int · returned Tensor · level recorded 2026-09-22
interp in 22 papers metric3d/mono/model/decode_heads/RAFTDepthNormalDPTDecoder5_quant.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 01dbab41e1e09abf · report fixture: signature x:Tensor/4/float, dest:Tensor/4/float · returned Tensor · level recorded 2026-09-22
interpolate_float32 metric3d/mono/model/decode_heads/RAFTDepthNormalDPTDecoder5_quant.py ran · our draft was wrong no licence file found · pointer only · b16ff203c09cec37 · report fixture: signature x:Tensor/4/float, size:tuple/1/int, scale_factor:NoneType/0/?, mode:str/0/str, align_corners:NoneType/0/? · returned Tensor · level recorded 2026-09-22
upflow4 metric3d/mono/model/decode_heads/RAFTDepthNormalDPTDecoder5_quant.py ran; the contract check could not run (RAISES) no licence file found · pointer only · d7471be3ef7422f3 · report fixture: signature flow:Tensor/4/float, mode:str/0/str · returned Tensor · level recorded 2026-09-22
BasicMultiUpdateBlock metric3d/mono/model/decode_heads/RAFTDepthNormalDPTDecoder5_quant.py unverified no licence file found · pointer only · 97ef81770d5725a5 · report
ContextFeatureEncoder metric3d/mono/model/decode_heads/RAFTDepthNormalDPTDecoder5_quant.py unverified no licence file found · pointer only · 59e47872dbb9fbb0 · report
ConvGRU metric3d/mono/model/decode_heads/RAFTDepthNormalDPTDecoder5_quant.py unverified no licence file found · pointer only · ac0c4a21d0fec5a5 · report
DecoderFeature metric3d/mono/model/decode_heads/RAFTDepthNormalDPTDecoder5_quant.py unverified no licence file found · pointer only · 2f3363af00cd2b17 · report
EncoderFeature metric3d/mono/model/decode_heads/RAFTDepthNormalDPTDecoder5_quant.py unverified no licence file found · pointer only · d59aec780269a9da · report
FlowHead in 7 papers metric3d/mono/model/decode_heads/RAFTDepthNormalDPTDecoder5_quant.py unverified no licence file found · pointer only · ae321a434f934a35 · report
FuseBlock metric3d/mono/model/decode_heads/RAFTDepthNormalDPTDecoder5_quant.py unverified no licence file found · pointer only · b4cd659ea28ba555 · report
RAFTDepthNormalDPT5 metric3d/mono/model/decode_heads/RAFTDepthNormalDPTDecoder5_quant.py unverified no licence file found · pointer only · f74546d1b74d3d4e · report
Readout metric3d/mono/model/decode_heads/RAFTDepthNormalDPTDecoder5_quant.py unverified no licence file found · pointer only · 0c6e843e898fb7dd · report
ResidualBlock in 100 papers metric3d/mono/model/decode_heads/RAFTDepthNormalDPTDecoder5_quant.py unverified no licence file found · pointer only · bc5d266138ef30e4 · report
Token2Feature metric3d/mono/model/decode_heads/RAFTDepthNormalDPTDecoder5_quant.py unverified no licence file found · pointer only · 4c305e858ce9013c · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for QuartDepth (graph method: QuartDepth). 23 bricks; individually on a fixture: 11 ran (of which 1 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 6 where Syntology's instrument failed) · 12 unverified. The assembly has not been run end-to-end.

  1. RAFTDepthNormalDPT5 entry · level 0 · unverified · f74546d1b74d3d4e
  2. BasicMultiUpdateBlock model · level 0 · unverified · 97ef81770d5725a5
  3. ContextFeatureEncoder model · level 0 · unverified · 59e47872dbb9fbb0
  4. DecoderFeature model · level 0 · unverified · 2f3363af00cd2b17
  5. EncoderFeature model · level 0 · unverified · d59aec780269a9da
  6. compute_depth_expectation helper · level 1 · ran · our draft was wrong · 5d5d6423c18aaa27
  7. coords_grid helper · level 1 · ran · honoured contract · bd06769ee467a01c
  8. interpolate_float32 helper · level 1 · ran · our draft was wrong · b16ff203c09cec37
  9. norm_normalize helper · level 1 · ran · our draft was wrong · 4bb632c166c85093
  10. upflow4 helper · level 1 · ran; the contract check could not run (RAISES) · d7471be3ef7422f3
  11. Conv2dLoRA helper · level 1 · ran · 20c34221b37d6e5a
  12. ConvGRU model · level 0 · unverified · ac0c4a21d0fec5a5
  13. FlowHead model · level 0 · unverified · ae321a434f934a35
  14. interp helper · level 1 · ran · our draft was wrong · 01dbab41e1e09abf
  15. pool2x helper · level 1 · ran; the contract check could not run · 25894ad2a73a8142
  16. ResidualBlock model · level 0 · unverified · bc5d266138ef30e4
  17. FuseBlock model · level 0 · unverified · b4cd659ea28ba555
  18. Token2Feature model · level 0 · unverified · 4c305e858ce9013c
  19. ConvLoRA helper · level 1 · ran · 49d1c4292adc4fa0
  20. LayerNorm2d helper · level 1 · ran · 1a6b2908a95d686d
  21. ConvBlock model · level 0 · unverified · e5eb7617d20f9cf2
  22. Readout model · level 0 · unverified · 0c6e843e898fb7dd
  23. LoRALayer helper · level 1 · ran · 562c6b943203b573

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2503.16709") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Depth EstimationMonocular Depth EstimationQuantization

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