SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2103.14910 · ICCV · 2021

MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthesis

Qi She, Changhu Wang, Gim Lee, Henghui Ding, Jiaxin Li, Zijian Feng

arXiv · PDF · Open in the Atlas

Code that ran

5 of 7 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; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 5 failures of our instrument; 2 no recorded run), measured 2026-11-22; 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/2103.14910.json · badge: /api/ran/2103.14910.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
vincentfung13/MINE marked official in Papers with Code
Papers with Code archive
5 ran · 2 no recorded run
FunctionStatusWhere it lives
alpha_composition Ran
ran; our contract draft was wrong, not the code
vincentfung13/MINE/operations/mpi_rendering.py
code served (permissive licence) · get_code("7525a41074955b82")
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.

import torch

torch.manual_seed(0)

# Construct arguments for alpha_composition
B = 2  # batch size
K = 4  # number of planes
C = 3  # channels (RGB)
H = 5  # height
W = 6  # width

# alpha_BK1HW: shape (B, K, 1, H, W)
# Alpha values should be between 0 and 1
alpha_BK1HW = torch.rand(B, K, 1, H, W)

# value_BKCHW: shape (B, K, C, H, W)
# Can be RGB or disparity values
value_BKCHW = torch.randn(B, K, C, H, W)

ARGS = {
    "alpha_BK1HW": alpha_BK1HW,
    "value_BKCHW": value_BKCHW,
}
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 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
inverse Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
vincentfung13/MINE/operations/mpi_rendering.py
code served (permissive licence) · get_code("3c56cc2b3ae0cce5")
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; no output shape is stated. 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 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.

import torch

torch.manual_seed(0)

# Create a batch of 2 invertible 3x3 matrices
matrices = torch.randn(2, 3, 3)
# Ensure they are invertible by making them well-conditioned
matrices = matrices + torch.eye(3) * 3

ARGS = {
    "matrices": matrices
}
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 — no output shape is stated: observe_signature.py could not observe it (call:AssertionError)
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
plane_volume_rendering Ran
ran; our contract draft was wrong, not the code
vincentfung13/MINE/operations/mpi_rendering.py
code served (permissive licence) · get_code("1c9f33a62f20f378")
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.

import torch

torch.manual_seed(0)

# Construct tensors with distinct sizes for different dimensions
B = 2  # batch size
S = 4  # number of planes/samples
H = 3  # height
W = 5  # width

# rgb_BS3HW: (B, S, 3, H, W) - RGB values at each plane
rgb_BS3HW = torch.randn(B, S, 3, H, W)

# sigma_BS1HW: (B, S, 1, H, W) - density/sigma values
sigma_BS1HW = torch.abs(torch.randn(B, S, 1, H, W)) + 0.1

# xyz_BS3HW: (B, S, 3, H, W) - XYZ coordinates (depth in channel 2)
xyz_BS3HW = torch.randn(B, S, 3, H, W)
# Make z-coordinates (depth) positive and increasing
xyz_BS3HW[:, :, 2, :, :] = torch.linspace(1.0, 10.0, S).view(1, S, 1, 1).expand(B, S, H, W)

# is_bg_depth_inf: boolean flag
is_bg_depth_inf = True

ARGS = {
    "rgb_BS3HW": rgb_BS3HW,
    "sigma_BS1HW": sigma_BS1HW,
    "xyz_BS3HW": xyz_BS3HW,
    "is_bg_depth_inf": is_bg_depth_inf,
}
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 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
render Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
vincentfung13/MINE/operations/mpi_rendering.py
code served (permissive licence) · get_code("5ecf76e78c778112")
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. 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 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)

# Define tensor dimensions following the function signatures
# B = batch size (2)
# S = number of planes (4)
# C = channels (3 for RGB)
# H = height (5)
# W = width (6)

B = 2
S = 4
C = 3
H = 5
W = 6

# Create test tensors with appropriate shapes and values
rgb_BS3HW = torch.randn(B, S, C, H, W)
sigma_BS1HW = torch.rand(B, S, 1, H, W) * 0.5  # Keep values reasonable
xyz_BS3HW = torch.randn(B, S, 3, H, W)
xyz_BS3HW[:, :, 2, :, :] = torch.abs(xyz_BS3HW[:, :, 2, :, :]) + 0.1  # Ensure positive depth values

use_alpha = False
is_bg_depth_inf = False

ARGS = {
    "rgb_BS3HW": rgb_BS3HW,
    "sigma_BS1HW": sigma_BS1HW,
    "xyz_BS3HW": xyz_BS3HW,
    "use_alpha": use_alpha,
    "is_bg_depth_inf": is_bg_depth_inf,
}
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 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
weighted_sum_mpi Ran
ran; our contract draft was wrong, not the code
vincentfung13/MINE/operations/mpi_rendering.py
code served (permissive licence) · get_code("9aefbf4f8f6698cd")
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.

import torch

torch.manual_seed(0)

# Analyzing the function:
# - rgb_BS3HW: tensor with shape (B, S, 3, H, W) - RGB values
# - xyz_BS3HW: tensor with shape (B, S, 3, H, W) - XYZ coordinates
# - weights: tensor used in element-wise multiplication with rgb_BS3HW and xyz_BS3HW, summed over dim=1
#   So weights should have shape (B, S, 1, H, W) or broadcastable to (B, S, 3, H, W)
# - is_bg_depth_inf: boolean flag

B = 2  # batch size
S = 4  # number of samples/views
H = 5  # height
W = 6  # width

# Create rgb_BS3HW with shape (B, S, 3, H, W)
rgb_BS3HW = torch.randn(B, S, 3, H, W)

# Create xyz_BS3HW with shape (B, S, 3, H, W)
xyz_BS3HW = torch.randn(B, S, 3, H, W)

# Create weights with shape (B, S, 1, H, W) for broadcasting
weights = torch.rand(B, S, 1, H, W)

# Boolean flag
is_bg_depth_inf = True

ARGS = {
    "rgb_BS3HW": rgb_BS3HW,
    "xyz_BS3HW": xyz_BS3HW,
    "weights": weights,
    "is_bg_depth_inf": is_bg_depth_inf,
}
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 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
HomographySample Not yet run
unverified (harvested, no recorded run)
vincentfung13/MINE/operations/mpi_rendering.py
code served (permissive licence) · get_code("896f18a21e472ff2")
How it ran

no invocation recorded.

render_tgt_rgb_depth Not yet run
unverified (harvested, no recorded run)
vincentfung13/MINE/operations/mpi_rendering.py
code served (permissive licence) · get_code("ff9fe99c79e58e72")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 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.

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

In this paper, we propose MINE to perform novel view synthesis and depth estimation via dense 3D reconstruction from a single image. Our approach is a continuous depth generalization of the Multiplane Images (MPI) by introducing the NEural radiance fields (NeRF). Given a single image as input, MINE predicts a 4-channel image (RGB and volume density) at arbitrary depth values to jointly reconstruct the camera frustum and fill in occluded contents. The reconstructed and inpainted frustum can then be easily rendered into novel RGB or depth views using differentiable rendering. Extensive experiments on RealEstate10K, KITTI and Flowers Light Fields show that our MINE outperforms state-of-the-art by a large margin in novel view synthesis. We also achieve competitive results in depth estimation on iBims-1 and NYU-v2 without annotated depth supervision. Our source code is available at https://github.com/vincentfung13/MINE.

For agents

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

get_harvested_code_for_paper("2103.14910")
get_code_for_paper("2103.14910")
have("2103.14910")

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

curl https://syntology.ai/api/ran/2103.14910.json

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

[![Syntology run record](https://syntology.ai/api/ran/2103.14910.svg)](https://syntology.ai/paper/2103.14910)

Connect an agent — have() is free.