SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2601.00359 · 2026

Efficient Prediction of Dense Visual Embeddings via Distillation and RGB-D Transformers

Robin Schmidt, Söhnke Fischedick, Daniel Seichter, Benedict Stephan, Horst-Michael Gross

arXiv · PDF · Open in the Atlas

Code that ran

2 of 4 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; 2 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/2601.00359.json · badge: /api/ran/2601.00359.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
TUI-NICR/DVEFormer canonical (classifier label)
classifier basis: census
2 ran · 2 no recorded run
FunctionStatusWhere it lives
blend_images Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
TUI-NICR/DVEFormer/dveformer/visualization.py
code served (permissive licence) · get_code("7fcd0b9de3375423")
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 ndarray, ndim 3, dtype family int, shape (4, 5, 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 numpy as np

# Create two sample images with matching dtype and ndim
# Using 3D arrays (height, width, channels) to test the mask logic
img1 = np.random.randint(0, 256, size=(4, 5, 3), dtype=np.uint8)
img2 = np.random.randint(0, 256, size=(4, 5, 3), dtype=np.uint8)

# Alpha blending parameter
alpha = 0.2

ARGS = {
    "img1": img1,
    "img2": img2,
    "alpha": alpha,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family int, shape (4, 5, 3) — shape (4, 5, 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
get_optimizer Ran
ran; our contract draft was wrong, not the code
TUI-NICR/DVEFormer/dveformer/optimizer.py
code served (permissive licence) · get_code("1a50127363dc2189")
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 Adam. 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 torch.optim import Adam, AdamW, RAdam, SGD

torch.manual_seed(0)

# Create a simple model with parameters to optimize
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

model = SimpleModel()

# Create a simple args object with the required attributes
class Args:
    def __init__(self, optimizer, learning_rate, weight_decay, momentum):
        self.optimizer = optimizer
        self.learning_rate = learning_rate
        self.weight_decay = weight_decay
        self.momentum = momentum

# Build arguments for the function
ARGS = {
    'args': Args(optimizer='adam', learning_rate=0.001, weight_decay=1e-4, momentum=0.9),
    'parameters': model.parameters()
}
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 Adam — a Adam output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Adam 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
get_lr_scheduler Not yet run
unverified (harvested, no recorded run)
TUI-NICR/DVEFormer/dveformer/lr_scheduler.py
code served (permissive licence) · get_code("e60a52fe170f233d")
How it ran

no invocation recorded.

parse_datasets Not yet run
unverified (harvested, no recorded run)
TUI-NICR/DVEFormer/dveformer/data.py
code served (permissive licence) · get_code("324bfcd690d8ff8f")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 0 later) and 0 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
blend_images 1 other paper
1 dated earlier
2309.13635 (2023-09)
PanopticNDT: Efficient and Robust Panoptic Mapping
get_lr_scheduler 1 other paper
1 dated earlier
2309.13635 (2023-09)
PanopticNDT: Efficient and Robust Panoptic Mapping
get_optimizer 1 other paper
1 dated earlier
2309.13635 (2023-09)
PanopticNDT: Efficient and Robust Panoptic Mapping
parse_datasets 1 other paper
1 dated earlier
2309.13635 (2023-09)
PanopticNDT: Efficient and Robust Panoptic Mapping

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 domestic environments, robots require a comprehensive understanding of their surroundings to interact effectively and intuitively with untrained humans. In this paper, we propose DVEFormer -an efficient RGB-D Transformerbased approach that predicts dense text-aligned visual embeddings (DVE) via knowledge distillation. Instead of directly performing classical semantic segmentation with fixed predefined classes, our method uses teacher embeddings from Alpha-CLIP to guide our efficient student model DVEFormer in learning fine-grained pixel-wise embeddings. While this approach still enables classical semantic segmentation, e.g., via linear probing, it further enables flexible text-based querying and other applications, such as creating comprehensive 3D maps. Evaluations on common indoor datasets demonstrate that our approach achieves competitive performance while meeting real-time requirements, operating at 26.3 FPS for the full model and 77.0 FPS for a smaller variant on an NVIDIA Jetson AGX Orin. Additionally, we show qualitative results that highlight the effectiveness and possible use cases in real-world applications. Overall, our method serves as a drop-in replacement for traditional segmentation approaches while enabling flexible natural-language querying and seamless integration into 3D mapping pipelines for mobile robotics.

For agents

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

get_harvested_code_for_paper("2601.00359")
get_code_for_paper("2601.00359")
have("2601.00359")

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

curl https://syntology.ai/api/ran/2601.00359.json

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

[![Syntology run record](https://syntology.ai/api/ran/2601.00359.svg)](https://syntology.ai/paper/2601.00359)

Connect an agent — have() is free.