The paper introduces SVRecon, a generalizable neural surface reconstruction framework that uses sparse volumetric representations to achieve high-resolution 3D reconstruction. It employs a two-stage architecture: first predicting occupied voxels with an occupancy network, then rendering only within those regions using specialized sparse algorithms. This approach allows reconstruction at resolutions up to 512³ on 32 GB hardware, producing smoother and more precise surfaces, especially in sparse-view scenarios.
By Aoxiang Fan, Corentin Dumery, Nicolas Talabot, Ming Xu, Hieu Le, Pascal Fua
arXiv:2607. 01164v1 Announce Type: new Abstract: Recent work has shown that implicit neural representations (INRs) can be trained to effectively compress structured and unstructured volume data, allowing for direct data querying with a reduced memory footprint.
By Landon Dyken, Sharmistha Chakrabarti, Nathan Debardeleben, Steve Petruzza, Qi Wu, Will Usher, Sidharth Kumar
The paper investigates why latent neural surrogate solvers, which compress physical system dynamics into a lower‑dimensional space, often fail during long‑horizon autoregressive rollouts. It demonstrates that training the latent representation only for reconstruction leads to instability, and proposes a set of training interventions—Koopman operator learning, Hamming noise injection, and multi‑step rollout fine‑tuning—that align the latent space with long‑horizon forecasting. These interventions reduce long‑rollout error by about 40 % and achieve accuracy comparable to full‑resolution models while using far fewer floating‑point operations and GPU memory, enabling stable extrapolation in mesoscale crystal‑plasticity simulations of high‑cycle fatigue.
By Andreas E. Robertson, Ashley T. Lenau, John D. Shimanek, Benjamin A. Jasperson, Vivek Oommen, David L. Damm, Krishna Garikipati, Remi Dingreville
arXiv:2606. 10909v1 Announce Type: cross Abstract: Reconstructing local stress fields in heterogeneous microstructures under non-linear, history-dependent loading remains a major computational bottleneck in multi-scale simulations.
By Manuel Ricardo Guevara Garban, Yves Chemisky, \'Etienne Pruli\`ere, Micha\"el Cl\'ement, Martin Abendroth, Bj\"orn Kiefer
arXiv:2508. 21022v3 Announce Type: replace Abstract: Subsampled natural gradient descent (SNG) has been used to enable high-precision scientific machine learning, but standard analyses based on stochastic preconditioning fail to provide insight into realistic small-sample settings.
By Gil Goldshlager, Jiang Hu, Lin Lin
The paper introduces a new training strategy called Staged Depth Training (SDT) that implements a representation curriculum for physics-informed neural networks (PINNs). SDT trains a shallow prefix with a temporary physics-informed head, freezes it, and then adds depth, improving performance across many benchmark problems without changing the final architecture. Experiments show significant error reductions and deeper fitted depth-scaling exponents, indicating that explicit representation learning can enhance PINN performance.
By Kejia Zhang, Youran Sun, Haizhao Yang
arXiv:2608. 13827v1 Announce Type: new Abstract: Machine-learned physical surrogate models have become promising alternatives to mesh-based numerical solvers.
By SiHun Lee, Dong-Hyuk Park, Taesoo Bang, Seung-Hoon Kang
RecGen3D is a framework that merges feed‑forward reconstruction and diffusion‑based generation to address the trade‑off between reconstruction fidelity and generative plausibility in sparse‑view 3D modeling. By aligning both models in a shared canonical space and using decoupled cooperative learning, the system stabilizes training and allows the reconstruction module to supply canonical geometric anchors while the diffusion generator refines and completes the structure. Experiments show that RecGen3D outperforms existing methods in producing complete and consistent 3D models from sparse observations.
By Zhisheng Huang, Jiahao Chen, Cheng Lin, Chenyu Hu, Hanzhuo Huang, Zhengming Yu, Mengfei Li, Yuheng Liu, Zekai Gu, Zibo Zhao, Yuan Liu, Xin Li, Wenping Wang
arXiv:2607. 00885v1 Announce Type: cross Abstract: Recent advances in neural rendering have established 3D Gaussian Splatting (3DGS) as a highly efficient representation for novel view synthesis, enabling fast training and real-time rendering with strong fidelity.
By Kangmin Seo, Sangeek Hyun, MinKyu Lee, Jae-Pil Heo
The paper introduces a new compression pipeline for scientific simulation data that combines Residual Vector Quantization (RVQ) with a U‑Net post‑processing network to correct pixel‑space residuals, followed by a Guaranteed Autoencoder (GAE) that enforces block‑wise error bounds. The U‑Net is trained to predict spatially structured residuals, addressing limitations of latent‑space only approaches. Experiments on S3D, JHTDB, and E3SM datasets show improved NRMSE and compression ratios compared to RVQ alone while maintaining strict error guarantees.
By Surya Majumder, Liangji Zhu, Sanjay Ranka, Anand Rangarajan
arXiv:2506. 11139v3 Announce Type: replace-cross Abstract: Implicit Neural Representations (INRs) have recently shown impressive results, but their fundamental capacity, implicit biases, and scaling behavior remain poorly understood.
By Namhoon Kim, Sara Fridovich-Keil
arXiv:2606. 05389v1 Announce Type: new Abstract: Lossy compression is essential for massive spatiotemporal data from scientific simulations.
By Liangji Zhu, Sanjay Ranka, Anand Rangarajan