SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.14817 · ICLR · 2024

Cameras as Rays: Pose Estimation via Ray Diffusion

Deva Ramanan, Shubham Tulsiani, Jason Zhang, Amy Lin, Moneish Kumar, Tzu-Hsuan Yang

arXiv · PDF · Open in the Atlas

Code that ran

2 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 0 failures of our instrument; 1 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/2402.14817.json · badge: /api/ran/2402.14817.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
jasonyzhang/raydiffusion community
Papers with Code archive
2 ran · 1 no recorded run
FunctionStatusWhere it lives
DiTBlock Ran
ran on a synthesized input · constructed an object; no result was computed
jasonyzhang/raydiffusion/ray_diffusion/model/dit.py
code served (permissive licence) · get_code("b844dc691a16fc89")
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 an instance of its own class, DiTBlock: the run constructed the object and did not call it, so no result was computed. 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
import torch.nn as nn
from timm.models.vision_transformer import Attention, Mlp

torch.manual_seed(0)

ARGS = {
    "hidden_size": 4,
    "num_heads": 2,
    "mlp_ratio": 4.0,
    "use_xformers_attention": False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
ray_diffusion, timm, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DiTBlock — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a DiTBlock output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
FeaturePositionalEncoding Ran
ran on a synthesized input · constructed an object; no result was computed
jasonyzhang/raydiffusion/ray_diffusion/model/dit.py
code served (permissive licence) · get_code("652e2f3041b1d5a2")
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 an instance of its own class, FeaturePositionalEncoding: the run constructed the object and did not call it, so no result was computed. 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
import torch.nn as nn
import numpy as np

torch.manual_seed(0)

# The function signature shows:
# __init__(self, max_num_images=8, feature_dim=1152, num_patches=256, P=1)
# forward(self, x) where x has shape (batch_size, num_images, flattened_patches, feature_dim)

# Looking at the forward method:
# - x.shape[0] is batch_size
# - x.shape[1] is num_images
# - x needs to be reshapeable to (batch_size, num_images, num_patches, feature_dim)
# This means x.shape should be (batch_size, num_images, num_patches * feature_dim)
# or more likely (batch_size, num_images * num_patches, feature_dim) before reshape

# Let's trace through:
# x comes in with shape that gets reshaped to (batch_size, num_images, self.num_patches, feature_dim)
# self.num_patches = num_patches // P^2
# So input x should have shape (batch_size, num_images, num_patches // P^2, feature_dim)
# or (batch_size, num_images * (num_patches // P^2), feature_dim) based on how it's used

# Actually looking more carefully at forward:
# batch_size = x.shape[0]
# num_images = x.shape[1]
# x = x.reshape(batch_size, num_images, self.num_patches, self.feature_dim)
# This means x must have total elements = batch_size * num_images * self.num_patches * feature_dim
# If x comes in as (batch_size, num_images, ...), then the remaining dims must multiply to num_patches * feature_dim

# Keeping it simple: x will be (batch_size, num_images, num_patches, feature_dim) directly
# or needs to reshape properly

# Let's use small values
batch_size = 2
num_images = 3
num_patches = 16
P = 1
feature_dim = 4

# After P-based reduction: self.num_patches = 16 // 1 = 16
# Input x shape should be (batch_size, num_images, num_patches, feature_dim)
x = torch.randn(batch_size, num_images, num_patches, feature_dim)

ARGS = {
    'max_num_images': 8,
    'feature_dim': feature_dim,
    'num_patches': num_patches,
    'P': P,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type FeaturePositionalEncoding — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a FeaturePositionalEncoding output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
DiT Not yet run
unverified (harvested, no recorded run)
jasonyzhang/raydiffusion/ray_diffusion/model/dit.py
code served (permissive licence) · get_code("a50e1e7f50be84ac")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 3 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

Estimating camera poses is a fundamental task for 3D reconstruction and remains challenging given sparsely sampled views (<10). In contrast to existing approaches that pursue top-down prediction of global parametrizations of camera extrinsics, we propose a distributed representation of camera pose that treats a camera as a bundle of rays. This representation allows for a tight coupling with spatial image features improving pose precision. We observe that this representation is naturally suited for set-level transformers and develop a regression-based approach that maps image patches to corresponding rays. To capture the inherent uncertainties in sparse-view pose inference, we adapt this approach to learn a denoising diffusion model which allows us to sample plausible modes while improving performance. Our proposed methods, both regression-and diffusion-based, demonstrate state-of-the-art performance on camera pose estimation on CO3D while generalizing to unseen object categories and in-the-wild captures. Recovered Cameras Images * denotes equal contribution. Project Page: https://jasonyzhang.com/RayDiffusion.

For agents

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

get_harvested_code_for_paper("2402.14817")
get_code_for_paper("2402.14817")
have("2402.14817")

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

curl https://syntology.ai/api/ran/2402.14817.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.14817.svg)](https://syntology.ai/paper/2402.14817)

Connect an agent — have() is free.