SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2404.06842 · CVPR · 2024

MoCha-Stereo: Motif Channel Attention Network for Stereo Matching

Jia Wu, Ziyang Chen, Wei Long, Yongjun Zhang, Bingshu Wang, Yongbin Qin, He Yao

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 17 functions out of this paper's own repositories and ran 16 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
zyangchen/mocha-stereo canonical 16 of 17
FunctionStatusWhere it lives
build_gwc_volume Ran zyangchen/mocha-stereo/MoCha-Stereo/core/submodule.py
code served (permissive licence) · get_code("b2535abc79c55bba")
conv1x1 Ran zyangchen/mocha-stereo/MoCha-Stereo/nets/feature.py
code served (permissive licence) · get_code("8182b8e2a441abbd")
conv2d Ran zyangchen/mocha-stereo/MoCha-Stereo/nets/refinement.py
code served (permissive licence) · get_code("2c4f90d71c073dfe")
conv3x3 Ran zyangchen/mocha-stereo/MoCha-Stereo/nets/feature.py
code served (permissive licence) · get_code("9fba66e062846970")
conv5x5 Ran zyangchen/mocha-stereo/MoCha-Stereo/nets/feature.py
code served (permissive licence) · get_code("af5d1e93b7cc0884")
convbn Ran zyangchen/mocha-stereo/MoCha-Stereo/core/extractor.py
code served (permissive licence) · get_code("15ab3c76823aef7e")
count_parameters Ran zyangchen/mocha-stereo/MoCha-Stereo/evaluate_stereo.py
code served (permissive licence) · get_code("f6b944f50d3f15ae")
default_conv Ran zyangchen/mocha-stereo/MoCha-Stereo/nets/refinement.py
code served (permissive licence) · get_code("8b0e794d4d8f9b13")
disp_warp Ran zyangchen/mocha-stereo/MoCha-Stereo/nets/warp.py
code served (permissive licence) · get_code("9797b88373fddbcd")
groupwise_correlation Ran zyangchen/mocha-stereo/MoCha-Stereo/core/submodule.py
code served (permissive licence) · get_code("2e5c0e4dfa009847")
interp Ran zyangchen/mocha-stereo/MoCha-Stereo/core/update.py
code served (permissive licence) · get_code("08bedbc0c0447f5d")
meshgrid Ran zyangchen/mocha-stereo/MoCha-Stereo/nets/warp.py
code served (permissive licence) · get_code("d264efc1788f1659")
norm_correlation Ran zyangchen/mocha-stereo/MoCha-Stereo/core/submodule.py
code served (permissive licence) · get_code("7d2e52593158ea33")
normalize_coords Ran zyangchen/mocha-stereo/MoCha-Stereo/nets/warp.py
code served (permissive licence) · get_code("62da485d08a1a205")
pool2x Ran zyangchen/mocha-stereo/MoCha-Stereo/core/update.py
code served (permissive licence) · get_code("25894ad2a73a8142")
weight Ran zyangchen/mocha-stereo/MoCha-Stereo/nets/mogrifier.py
code served (permissive licence) · get_code("3ea274451c800fdf")
pool4x Not yet run zyangchen/mocha-stereo/MoCha-Stereo/core/update.py
code served (permissive licence) · get_code("771e8ac695af28a9")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Figure 1. Motivation. Addressing the issue of geometric structure loss in feature channels arising from deep learning. (From left to right: Input image, visualization of a Normal Channel, visualization of a Motif [39] Channel.) Due to the fuzziness of geometric edges in certain channels, achieving accurate matching of stereo image edges is a challenging problem. MoCha-Stereo guides ordinary channels to focus on edge features through motif channels, achieving more accurate detail matching. Motif Channel refers to channel that composed of repeatedly occurring geometric contours. The regions delineated by the yellow border represent the magnified details.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2404.06842")
get_code_for_paper("2404.06842")
have("2404.06842")

Connect an agent — have() is free.