CORTEXA
← Browse
arxivcs.GRcs.CVcs.LG2026-06-29

RenderFormer++: Scalable and Physically Grounded Feed-Forward Neural Rendering

Huangsheng Du, Haoran Zhu, Youcheng Cai, Jinyang Meng, Ligang Liu

We present RenderFormer++, a scalable and physically grounded feed-forward neural rendering framework for global illumination in mesh scenes. Existing Transformer-based neural rendering methods such as RenderFormer achieve promising cross-scene generalization, but suffer from limited physical consistency and poor scalability due to the quadratic attention complexity of triangle-level tokenization. To address these issues, we introduce Physics-Informed Transport Guidance (PITG), which embeds rendering-equation inductive biases into the attention mechanism and enforces transport consistency loss, enabling physically consistent light transport modeling. We further propose Hierarchical Object-Centric Tokenization (HOCT), which aggregates triangle-level features into compact object-level tokens via cross-attention with learnable queries, substantially reducing computational and memory costs while preserving geometric and radiometric information. Extensive experiments demonstrate that RenderFormer++ achieves scalable, stable, and generalizable feed-forward global illumination rendering across complex large-scale scenes with improved physical accuracy and efficiency over prior neural rendering methods.

View free PDFSource page

Related papers

arxivcs.CVcs.AIcs.GRcs.LGcs.RO2026-07-07

SPEAR: A Simulator for Photorealistic Embodied AI Research

Mike Roberts, Renhan Wang, Rushikesh Zawar, Rachith Dey-Prakash, Quentin Leboutet, Stephan R. Richter, et al.

Interactive simulators have become powerful tools for training embodied agents and generating synthetic visual data, but existing photorealistic simulators suffer from limited generality, programmability, and rendering speed. We address these limitations by introducing SPEAR: A S…

View free PDFSource page
arxivcs.ROcs.CVcs.GRcs.LG2026-07-13

NeuralActuator: Neural Actuation Modeling for Robot Dynamics and External Force Perception

Zhiyang Dou, John U. Onyemelukwe, Hangxing Zhang, Heng Zhang, Minghao Guo, Yunsheng Tian, et al.

Differentiable simulators have advanced policy learning and model-based control across robotic tasks. Yet actuator dynamics remain underexplored and can be a major source of sim-to-real error, particularly on low-cost platforms, where the linear current-to-joint-torque approximat…

View free PDFSource page
arxivcs.LGcs.CVcs.GR2026-07-11

Error Aware Distribution Prediction for Lightweight Implicit Neural Representations

Zhimin Li, Jake D. Balla, Joshua A. Levine

Implicit neural representations (INRs) offer compact encoding of volumes, but as lossy approximators, inevitably have prediction errors. We consider INRs that can simultaneously encode relative error scales by predicting distributions using tools from uncertainty estimation. Typi…

View free PDFSource page
arxivcs.LGcs.CVcs.GReess.IV2026-07-17

DebrisTracer: Reliable Tracking in Hypervelocity Impact Fast Imaging

Théophane Loloum, Fabien Vivodtzev, David Hébert, Baptiste Reynier, Michel Arrigoni, Julien Tierny

This application paper presents DebrisTracer, a framework for the reliable tracking of debris in hypervelocity impact fast imaging. These noisy and highly specific datasets capture the ejection of a large number of debris fragments after the impact of a projectile launched at hyp…

View free PDFSource page
arxivcs.CVcs.GRcs.LG2026-07-16

Online Neural Space Time Memory for Dynamic Novel View Synthesis

Baback Elmieh, Lynn Tsai, Zeman Li, Srinivas Kaza, Tiancheng Sun, Gabor Csapo, et al.

Online novel view synthesis from multi-view streaming videos faces a fundamental trade-off: maintaining a persistent, long-horizon memory to reconstruct temporarily occluded regions while operating under strict real-time constraints. While Test-Time Training (TTT) offers a powerf…

View free PDFSource page
arxivcs.CVcs.GRcs.LG2026-07-20

SciForma: Structure-Faithful Generation of Scientific Diagrams

Yuxuan Luo, Peng Zhang, Xinjie Zhang, Xun Guo, Zhouhui Lian, Yan Lu

Structural fidelity is essential to scientific methodology diagrams. To communicate research logic, these diagrams must faithfully render components, directional relations, and textual annotations. Since a single error, such as a reversed arrow or an unreadable equation, can inva…

View free PDFSource page