Three-dimensional Conditional Diffusion Models for Cosmological 21 cm Lightcone Emulation

• URL: http://arxiv.org/abs/2605.29016v1
• Date: Wed, 27 May 2026 19:16:49 GMT
• Title: Three-dimensional Conditional Diffusion Models for Cosmological 21 cm Lightcone Emulation
• Abstract summary: We investigate conditional diffusion modeling for three-dimensional 21 cm lightcone emulation.<n>We focus on cubes with a sky-plane size of $64times64$ and a line-of-sight depth up to 1024 cells.<n>We perform controlled comparisons across preprocessing choices, dynamic-range compression settings, architecture depth, and training duration.
• Score: 4.210446607355696
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We investigate conditional diffusion modeling for three-dimensional 21 cm lightcone emulation, focusing on cubes with a sky-plane size of $64\times64$ and a line-of-sight depth up to 1024 cells. Relative to earlier 2D studies, the 3D setting is substantially harder because memory limits enforce very small micro-batches while the underlying voxel distribution is highly skewed and long tailed. We perform controlled comparisons across preprocessing choices, dynamic-range compression settings, architecture depth, and training duration using $25{,}600$ training lightcones and validation ensembles at fixed parameter points. For validation, each reference parameter point contains 800 21cmFAST realizations with independent initial conditions, and we use 800 samples per model and per reference set for the reported ensemble comparisons. We evaluate generated lightcones with complementary diagnostics in both image and summary-statistic spaces: brightness-temperature slices, the global signal, the power spectrum, and reduced scattering coefficients. Across the tested configurations, preprocessing is the dominant factor governing stable training and the resulting physical fidelity. Among the configurations explored here, Yeo-Johnson preprocessing combined with moderate amplitude compression gives the most consistently favorable trade-off, with the strongest quantitative support coming from rankings based on the standard-deviation-normalized mean absolute error ($\mathrm{MAE}_{\rm std}$) of the global signal and qualitatively compatible behavior in the complementary diagnostics. At the same time, visually plausible 3D samples still retain measurable biases in two-point and higher-order statistics. We therefore view the present work as a simulation-level baseline for three-dimensional 21 cm emulation and for future studies that incorporate more realistic observational effects.

Related papers

• Solution for UCF UrbanTwin V2X-Real Track: Sim-to-Real Urban LiDAR 3D Object Detection [54.03436243843709]
  This report presents a multi-source collaborative training and class-aware fusion framework for Sim2Real 3D detection.<n>The method organizes digital-twin scans, diffusion-redrawn scans, density-stabilized scans, and pedestrian morphology-aligned samples into a unified training pool with complementary roles.
  arXiv  Detail & Related papers  (2026-09-07T15:16:15Z)
• A Unified Resolution-Conditioned Framework for Orthogonal Line-Scanning Image Fusion [5.000212382506099]
  We present a resolution-conditioned fusion framework based on Rank Enhanced Linear Attention (RELA)<n>We also introduce Adaptive RELA, which replaces fixed- kernel rank enhancement with ratio-conditioned multi-scale depthwise convolutions.<n>The resulting model achieves 34-40 dB PSNR across configurations, whereas unconditioned multi-slit training collapses to 24.3 dB and per-slit specialists lose 4-9 dB outside their training setting.
  arXiv  Detail & Related papers  (2026-08-04T04:28:39Z)
• DepthART: Scaling Foundation Monocular Depth to Tiny Models [51.10174763031444]
  DepthART is a compact MDE model for on-device deployment across diverse scenes.<n>We show how DepthART consistently surpasses previous tiny baselines in both zero-shot generalization and metric accuracy.<n>We also provide a scalable model family, with DepthART-S reaching 347/245 FPS (strict FP32) on an GTX A6000 at $2242/4482$, 102 FPS (TF32) on a Orin NX 8GB, and over 15 FPS (FP32) on a Jetson Nano 4GB.
  arXiv  Detail & Related papers  (2026-07-19T06:54:52Z)
• Articulating then Matching: Zero-Shot Shape Matching for Uncurated Data [0.5014513738509991]
  Finding dense correspondences between 3D shapes is a fundamental yet unresolved challenge, especially in real-world environments.<n>We present ATM, a framework that requires no correspondence-specific training and robustly addresses these issues at once.
  arXiv  Detail & Related papers  (2026-06-28T03:05:46Z)
• 21cmEMUv3: a hybrid diffusion-LSTM emulator of 21cmFAST summary observables [1.631115063641726]
  We present 21cmEMUv3, an emulator trained on 21cmFASTv3 simulations that model both atomically and molecularly cooling galaxies.<n>21cmEMUv3 is conditioned on $_8$ and ten astrophysical parameters to produce seven summary observables.<n>We use the emulator to reinterpret current 21cm PS upper limits from HERA, for the first time using state-of-the-art hydrodynamical simulations.
  arXiv  Detail & Related papers  (2026-05-29T18:00:05Z)
• Diffusion Image Generation with Explicit Modeling of Data Manifold Geometry [64.61931485161833]
  Image generative models aim to sample data points from the underlying data manifold.<n>We propose the Data Manifold-aware Image diffusioN moDel (MIND)<n>MIND integrates discrete patch tokenization into the score function of a continuous diffusion model.
  arXiv  Detail & Related papers  (2026-05-25T08:43:14Z)
• OmniLiDAR: A Unified Diffusion Framework for Multi-Domain 3D LiDAR Generation [100.36917520403227]
  We present a unified text-conditioned diffusion framework that generates LiDAR scans in a shared range-image representation across eight representative domains.<n>In the absence of a public consolidated benchmark, we construct an 8-domain dataset by combining real-world scans with physically based weather simulation and systematic beam reduction.
  arXiv  Detail & Related papers  (2026-05-13T17:42:20Z)
• M^3: Dense Matching Meets Multi-View Foundation Models for Monocular Gaussian Splatting SLAM [36.28718478194476]
  M3 augments the Multi-view foundation model with a dedicated Matching head to facilitate fine-grained dense correspondences.<n>Experiments on diverse indoor and outdoor benchmarks demonstrate state-of-the-art accuracy in both pose estimation and scene reconstruction.
  arXiv  Detail & Related papers  (2026-03-17T17:52:37Z)
• Stereo-Inertial Poser: Towards Metric-Accurate Shape-Aware Motion Capture Using Sparse IMUs and a Single Stereo Camera [54.967647497048205]
  We present Stereo-Inertial Poser, a real-time motion capture system that estimates metric-accurate and shape-aware 3D human motion.<n>We replace the monocular RGB with stereo vision, enabling direct 3D keypoint extraction and body shape parameter estimation.<n>Our method produces drift-free global translation under a long recording time and reduces foot-skating effects.
  arXiv  Detail & Related papers  (2026-03-02T17:46:38Z)
• Silent Inconsistency in Data-Parallel Full Fine-Tuning: Diagnosing Worker-Level Optimization Misalignment [27.352639822596146]
  Cross-worker divergence in losses and gradients can remain invisible under conventional monitoring signals.<n>We propose a model-agnostic diagnostic framework that quantifies worker-level consistency using training signals readily available in standard pipelines.
  arXiv  Detail & Related papers  (2026-02-16T04:42:30Z)
• Robust Mesh Saliency GT Acquisition in VR via View Cone Sampling and Geometric Smoothing [59.12032628787018]
  3D mesh saliency ground truth is essential for human-centric visual modeling in virtual reality (VR)<n>Current VR eye-tracking pipelines rely on single ray sampling and Euclidean smoothing, triggering texture attention and signal leakage across gaps.<n>This paper proposes a robust framework to address these limitations.
  arXiv  Detail & Related papers  (2026-01-06T05:20:12Z)
• Agentic World Modeling for 6G: Near-Real-Time Generative State-Space Reasoning [70.56067503630486]
  We argue that sixth-generation (6G) intelligence is not fluent token prediction but calibrated the capacity to imagine and choose.<n>We show that WM-MS3M cuts mean absolute error (MAE) by 1.69% versus MS3M with 32% fewer parameters and similar latency, and achieves 35-80% lower root mean squared error (RMSE) than attention/hybrid baselines with 2.3-4.1x faster inference.
  arXiv  Detail & Related papers  (2025-11-04T17:22:22Z)
• Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistency [60.74505433956616]
  continuous-time consistency model (sCM) is theoretically principled and empirically powerful for accelerating academic-scale diffusion.<n>We first develop a parallelism-compatible FlashAttention-2 JVP kernel, enabling sCM training on models with over 10 billion parameters and high-dimensional video tasks.<n>We propose the score-regularized continuous-time consistency model (rCM), which incorporates score distillation as a long-skip regularizer.
  arXiv  Detail & Related papers  (2025-10-09T16:45:30Z)
• Point-wise Diffusion Models for Physical Systems with Shape Variations: Application to Spatio-temporal and Large-scale system [1.474723404975345]
  We propose a point-wise diffusion model that processes-temporal points independently to efficiently predict complex physical systems with shape variations.<n>We validate our approach across three distinct physical domains with complex geometric configurations.<n>Our proposed model achieves superior performance compared to image-based diffusion model.
  arXiv  Detail & Related papers  (2025-08-02T06:55:59Z)
• DIMM: Decoupled Multi-hierarchy Kalman Filter for 3D Object Tracking [50.038098341549095]
  State estimation is challenging for 3D object tracking with high maneuverability.<n>We propose a novel framework, DIMM, to effectively combine estimates from different motion models in each direction.<n>DIMM significantly improves the tracking accuracy of existing state estimation methods by 31.61%99.23%.
  arXiv  Detail & Related papers  (2025-05-18T10:12:41Z)
• A unified framework for 21cm tomography sample generation and parameter inference with Progressively Growing GANs [7.6146285961466]
  We utilise a specific type of neural network, a Progressively Growing Generative Adversarial Network (PGGAN), to produce realistic tomography images of the 21cm brightness temperature during the Epoch of Reionisation (EoR) The network generates new samples at a resolution of $sim 3'$ in a second (on a laptop CPU), and the resulting global 21cm signal, power spectrum, and pixel distribution function agree well with those of the training data.
  arXiv  Detail & Related papers  (2020-02-19T00:39:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.