SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.04895 · 2022

Joint Learning of Salient Object Detection, Depth Estimation and Contour Extraction

arXiv · PDF · Open in the Atlas

Code that ran

11 of 11 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 3 honoured the contract we drafted, 0 violated it and 7 have no contract verdict; 1 failure of our instrument; 0 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2203.04895.json · badge: /api/ran/2203.04895.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
xiaoqi-zhao-dlut/mmft canonical (classifier label)
classifier basis not recorded on the link
11 ran · 0 no recorded run
FunctionStatusWhere it lives
create_window Ran
ran, honoured the contract we drafted
xiaoqi-zhao-dlut/mmft/model/ssim_loss.py
code served (permissive licence) · get_code("6154e3744ece5728")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 4, dtype family float, shape (3, 1, 5, 5) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
from torch.autograd import Variable
from math import exp

torch.manual_seed(0)

def gaussian(window_size, sigma):
    gauss = torch.Tensor([exp(-(x - window_size // 2) ** 2 / float(2 * sigma ** 2)) for x in range(window_size)])
    return gauss / gauss.sum()

def create_window(window_size, channel):
    _1D_window = gaussian(window_size, 1.5).unsqueeze(1)
    _2D_window = _1D_window.mm(_1D_window.t()).float().unsqueeze(0).unsqueeze(0)
    window = Variable(_2D_window.expand(channel, 1, window_size, window_size).contiguous())
    return window

ARGS = {
    "window_size": 5,
    "channel": 3
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (3, 1, 5, 5) — shape (3, 1, 5, 5) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
cv_random_flip Ran
ran on a synthesized input
xiaoqi-zhao-dlut/mmft/data_depth_free_multi_task.py
code served (permissive licence) · get_code("1f66fcae571ac878")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

from PIL import Image
import random

# Create small PIL Images (2x3 pixels each)
img = Image.new('RGB', (2, 3), color='red')
label = Image.new('L', (2, 3), color=128)
depth = Image.new('L', (2, 3), color=64)
contour = Image.new('L', (2, 3), color=32)

ARGS = {
    'img': img,
    'label': label,
    'depth': depth,
    'contour': contour
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
gaussian Ran
ran, honoured the contract we drafted
xiaoqi-zhao-dlut/mmft/model/ssim_loss.py
code served (permissive licence) · get_code("c56b7ef16f309a45")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 1, dtype family float, shape (5,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
from math import exp

torch.manual_seed(0)

ARGS = {
    "window_size": 5,
    "sigma": 1.0,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 1, dtype family float, shape (5,) — shape (5,) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_log_kernel2d_pt Ran
ran on a synthesized input
xiaoqi-zhao-dlut/mmft/depth_bokeh.py
code served (permissive licence) · get_code("7616d055c901e967")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 3, dtype family float, shape (441, 2, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn.functional as F

torch.manual_seed(0)

# Construct valid_ratio tensor
# The function expects a tensor where min >= 0 and max <= 1
# Shape: (2, 3) - small distinct dimensions
valid_ratio = torch.tensor([
    [0.2, 0.5, 0.8],
    [0.1, 0.6, 0.9]
], dtype=torch.float32)

ARGS = {
    "kernel_size": 21,
    "valid_ratio": valid_ratio,
    "normalize": False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (441, 2, 3) — shape (441, 2, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
l2_regularisation Ran
ran, honoured the contract we drafted
xiaoqi-zhao-dlut/mmft/utils.py
code served (permissive licence) · get_code("c23b05634625d281")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

m = SimpleModel()

ARGS = {
    "m": m
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
randomCrop Ran
ran on a synthesized input
xiaoqi-zhao-dlut/mmft/data_depth_free_multi_task.py
code served (permissive licence) · get_code("8ac93407f634dcc8")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

from PIL import Image
import numpy as np

# Create mock image objects with .size attribute and .crop() method
class MockImage:
    def __init__(self, width, height):
        self.size = (width, height)
    
    def crop(self, box):
        # Return a new MockImage with the cropped dimensions
        left, top, right, bottom = box
        new_width = right - left
        new_height = bottom - top
        return MockImage(new_width, new_height)

# Set seed for reproducibility
np.random.seed(0)

# Create image, label, depth, and contour as MockImage objects
# Using distinct sizes: 100x80 base, will be cropped
image = MockImage(100, 80)
label = MockImage(100, 80)
depth = MockImage(100, 80)
contour = MockImage(100, 80)

ARGS = {
    "image": image,
    "label": label,
    "depth": depth,
    "contour": contour
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
randomRotation Ran
ran on a synthesized input
xiaoqi-zhao-dlut/mmft/data_depth_free_multi_task.py
code served (permissive licence) · get_code("bbfbb005e8b57cb0")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

from PIL import Image
import numpy as np
import random

# Create small PIL Images for testing
# image, label, depth, and contour all need to be PIL Image objects
# with a .rotate() method

image = Image.new('RGB', (4, 3))  # 4x3 RGB image
label = Image.new('L', (4, 3))   # 4x3 grayscale label
depth = Image.new('L', (4, 3))   # 4x3 grayscale depth
contour = Image.new('L', (4, 3)) # 4x3 grayscale contour

ARGS = {
    'image': image,
    'label': label,
    'depth': depth,
    'contour': contour
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
rmse_linear Ran
ran on a synthesized input
xiaoqi-zhao-dlut/mmft/Depth_eva.py
code served (permissive licence) · get_code("2c02b53e0dbd4404")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create small tensors with distinct dimensions
# output and target should be 2D tensors (w, h)
w = 4
h = 3

output = torch.randn(w, h)
target = torch.randn(w, h)

ARGS = {
    "output": output,
    "target": target,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
rmse_log Ran
ran on a synthesized input
xiaoqi-zhao-dlut/mmft/Depth_eva.py
code served (permissive licence) · get_code("848e15a6cdbcecff")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create small tensors with distinct dimensions
# The function expects output and target to be 2D tensors
# It will reshape them to (1, 1, w, h)
output = torch.randn(4, 3)
target = torch.randn(4, 3)

ARGS = {
    "output": output,
    "target": target,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
ssim Ran
ran; our contract draft was wrong, not the code
xiaoqi-zhao-dlut/mmft/model/ssim_loss.py
code served (permissive licence) · get_code("9151c793f90473f0")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn.functional as F
from torch.autograd import Variable
from math import exp

torch.manual_seed(0)

def gaussian(window_size, sigma):
    gauss = torch.Tensor([exp(-(x - window_size // 2) ** 2 / float(2 * sigma ** 2)) for x in range(window_size)])
    return gauss / gauss.sum()

def create_window(window_size, channel):
    _1D_window = gaussian(window_size, 1.5).unsqueeze(1)
    _2D_window = _1D_window.mm(_1D_window.t()).float().unsqueeze(0).unsqueeze(0)
    window = Variable(_2D_window.expand(channel, 1, window_size, window_size).contiguous())
    return window

def _ssim(img1, img2, window, window_size, channel, size_average=True):
    mu1 = F.conv2d(img1, window, padding=window_size // 2, groups=channel)
    mu2 = F.conv2d(img2, window, padding=window_size // 2, groups=channel)
    mu1_sq = mu1.pow(2)
    mu2_sq = mu2.pow(2)
    mu1_mu2 = mu1 * mu2
    sigma1_sq = F.conv2d(img1 * img1, window, padding=window_size // 2, groups=channel) - mu1_sq
    sigma2_sq = F.conv2d(img2 * img2, window, padding=window_size // 2, groups=channel) - mu2_sq
    sigma12 = F.conv2d(img1 * img2, window, padding=window_size // 2, groups=channel) - mu1_mu2
    C1 = 0.01 ** 2
    C2 = 0.03 ** 2
    ssim_map = (2 * mu1_mu2 + C1) * (2 * sigma12 + C2) / ((mu1_sq + mu2_sq + C1) * (sigma1_sq + sigma2_sq + C2))
    if size_average:
        return ssim_map.mean()
    else:
        return ssim_map.mean(1).mean(1).mean(1)

def ssim(img1, img2, window_size=11, size_average=True):
    _, channel, _, _ = img1.size()
    window = create_window(window_size, channel)
    if img1.is_cuda:
        window = window.cuda(img1.get_device())
    window = window.type_as(img1)
    return _ssim(img1, img2, window, window_size, channel, size_average)

# Create test tensors with shape [batch=2, channels=3, height=4, width=5]
img1 = torch.randn(2, 3, 4, 5)
img2 = torch.randn(2, 3, 4, 5)

ARGS = {
    "img1": img1,
    "img2": img2,
    "window_size": 11,
    "size_average": True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
threeshold_percentage Ran
ran on a synthesized input
xiaoqi-zhao-dlut/mmft/Depth_eva.py
code served (permissive licence) · get_code("de2031d8d8e58197")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create small tensors with distinct dimensions
# output and target should be 2D tensors (w x h)
# Using 4x3 to make dimensions distinguishable
output = torch.randn(4, 3)
target = torch.randn(4, 3)

# Threshold value - a scalar float
threeshold_val = 1.5

ARGS = {
    "output": output,
    "target": target,
    "threeshold_val": threeshold_val,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 2 the same month, 4 later) and 7 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
gaussian 160 other papers
18 dated earlier, 1 the same month, 140 later, 1 same year, order not determinable · 7 only as an assembly brick
1812.11941 (2018-12)
High Quality Monocular Depth Estimation via Transfer Learning
1904.01538 (2019-04)
Spatial Attentive Single-Image Deraining with a High Quality Real Rain Dataset
1907.11628 (2019-07)
Unsupervised Learning for Optical Flow Estimation Using Pyramid Convolution LSTM
and 157 more not named here
create_window 52 other papers
11 dated earlier, 1 the same month, 40 later · 5 only as an assembly brick
1904.01538 (2019-04)
Spatial Attentive Single-Image Deraining with a High Quality Real Rain Dataset
1907.11628 (2019-07)
Unsupervised Learning for Optical Flow Estimation Using Pyramid Convolution LSTM
2002.11616 (2020-02)
Zooming Slow-Mo: Fast and Accurate One-Stage Space-Time Video Super-Resolution
and 49 more not named here
ssim 28 other papers
5 dated earlier, 23 later
1904.01538 (2019-04)
Spatial Attentive Single-Image Deraining with a High Quality Real Rain Dataset
1907.11628 (2019-07)
Unsupervised Learning for Optical Flow Estimation Using Pyramid Convolution LSTM
2002.11616 (2020-02)
Zooming Slow-Mo: Fast and Accurate One-Stage Space-Time Video Super-Resolution
and 25 more not named here
l2_regularisation 6 other papers
2 dated earlier, 4 later
1806.05034 (2018-06)
A Probabilistic U-Net for Segmentation of Ambiguous Images
1907.01949 (2019-07)
Supervised Uncertainty Quantification for Segmentation with Multiple Annotations
2207.02466 (2022-07)
GLENet: Boosting 3D Object Detectors with Generative Label Uncertainty Estimation
and 3 more not named here

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

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

Abstract

Benefiting from color independence, illumination invariance and location discrimination attributed by the depth map, it can provide important supplemental information for extracting salient objects in complex environments. However, high-quality depth sensors are expensive and can not be widely applied. While general depth sensors produce the noisy and sparse depth information, which brings the depth-based networks with irreversible interference. In this paper, we propose a novel multi-task and multi-modal filtered transformer (MMFT) network for RGB-D salient object detection (SOD). Specifically, we unify three complementary tasks: depth estimation, salient object detection and contour estimation. The multi-task mechanism promotes the model to learn the task-aware features from the auxiliary tasks. In this way, the depth information can be completed and purified. Moreover, we introduce a multi-modal filtered transformer (MFT) module, which equips with three modality-specific filters to generate the transformer-enhanced feature for each modality. The proposed model works in a depth-free style during the testing phase. Experiments show that it not only significantly surpasses the depth-based RGB-D SOD methods on multiple datasets, but also precisely predicts a high-quality depth map and salient contour at the same time. And, the resulted depth map can help existing RGB-D SOD methods obtain significant performance gain. The source code will be publicly available at https://github.com/Xiaoqi-Zhao-DLUT/MMFT.

For agents

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

get_harvested_code_for_paper("2203.04895")
get_code_for_paper("2203.04895")
have("2203.04895")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2203.04895.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2203.04895.svg)](https://syntology.ai/paper/2203.04895)

Connect an agent — have() is free.