Low-light image enhancement is severely ill-posed when the input frame contains missing structure, saturated noise, and weak local contrast. Event cameras provide asynchronous brightness-change observations with high temporal resolution, but prior works often treat voxel channels as an unordered or static feature stack before fusion, rather than explicitly modeling their within-window temporal evolution, weakening the temporal evidence that makes events useful.
The paper introduces GPERT, a framework that separates event-based 3D Gaussian Splatting into two rendering branches: event-by-event geometry rendering and snapshot-based radiance rendering. By employing ray-tracing and warped event images, GPERT balances accuracy and temporal resolution, achieving state‑of‑the‑art results on real‑world datasets and competitive performance on synthetic data. The method operates without pretrained models or COLMAP initialization, offers flexible event selection, and produces sharp reconstructions of scene edges with rapid training.
By Kai Kohyama, Yoshimitsu Aoki, Guillermo Gallego, Shintaro Shiba
arXiv:2609.12682v1 Announce Type: new
Abstract: Reconstructing 3D scenes under real-world low-light conditions remains challenging due to severe sensor noise, low signal-to-noise ratios, and degraded...
By Shaurya Pavan A, Vemunuri Divya Madhuri, Yash Pradeep Gawande, Kaushik Mitra
arXiv:2505. 08438v4 Announce Type: replace-cross Abstract: Event cameras are rapidly emerging as powerful vision sensors for 3D reconstruction, uniquely capable of asynchronously capturing per-pixel brightness changes.
By Chuanzhi Xu, Haoxian Zhou, Langyi Chen, Haodong Chen, Zeke Zexi Hu, Zhicheng Lu, Ying Zhou, Vera Chung, Qiang Qu, Weidong Cai
arXiv:2609.23161v1 Announce Type: new
Abstract: A conventional camera uses millions of pixels to measure radiance from all directions within its field of view. We present an omnidirectional irradianc...
By Jeremy Klotz, Shree K. Nayar
arXiv:2608.27584v1 Announce Type: new
Abstract: Autonomous systems rely on extracting information from light, yet remain brittle in extreme environments, from nighttime navigation to high-speed robot...
By Varun Sundar, Pavan Thodima, Sacha Jungerman, Mohit Gupta
The SEE Challenge 2026 invites participants to restore RGB images using synchronized event camera data and a target brightness statistic across a wide illumination range. Using the SEE-600K dataset of 610,126 image‑event pairs from 202 real‑world scenes, teams compete under an open‑system protocol, with PSNR as the primary ranking metric and SSIM as a secondary measure. Fifteen valid submissions were evaluated, revealing closely spaced top scores and consistent local errors under severe underexposure, while the report also examines exposure subsets, semantic test cases, shared failure patterns, and system design choices.
By Yunfan Lu, Mingchao Xu, Hanyu Zhou, Shaoyu Liu, Haoyue Liu, Peiqi Duan, Shihan Peng, Yinqiang Zheng, Boxin Shi, Gim Hee Lee, Hui Xiong, Davide Scaramuzza
RawSLAM introduces the first online Gaussian SLAM framework that operates directly on single‑exposure 16‑bit linear HDR images, overcoming the limitations of traditional 8‑bit LDR SLAM systems in extreme lighting. The approach combines an HDR Gaussian splatting module with a Reinhard‑compressed photometric objective and structure‑guided spatial weighting, achieving superior trajectory and reconstruction accuracy compared to a direct HDR adaptation of MonoGS. The same formulation also improves performance on standard 8‑bit inputs and can be transferred to other SLAM systems such as SplaTAM, Gaussian SLAM, and DROID‑W, eliminating tracking failures in challenging illumination sequences. Additionally, RawSLAM provides a new dataset of 10 real‑world indoor sequences with 16‑bit RAW imagery, depth, IMU, and OptiTrack poses.
By Marina Orozco Gonz\'alez, Luis Merino
Projector-camera (ProCams) systems achieve active scene perception and controllable appearance manipulation via structured illumination, serving as a core infrastructure for spatial augmented reality, projection mapping, and surface reflectance acquisition. Existing inverse-rendering methods for ProCams deliver high-fidelity results but rely on time-consuming per-scene optimization, while mainstream feed-forward 3D reconstruction models produce baked appearance that cannot adapt to spatially varying projector illumination.
arXiv:2606. 20856v2 Announce Type: replace-cross Abstract: Multi-view surface reconstruction is a core problem in computer vision.
By Hiroki Sakuma, Masatoshi Okutomi
FlashNormal is a diffusion-based method that estimates detailed surface normals from flash/no-flash image pairs, leveraging flash-induced shading variations and a curvature-guided detail enhancement strategy to improve surface detail recovery and reduce shape‑reflectance ambiguity. The approach is designed for practical use on modern smartphones and is evaluated on EvalFlash, a new real‑world dataset of 20 objects with ground‑truth normals. Experiments show FlashNormal outperforms existing single‑image methods and surpasses prior flash/no‑flash normal estimation techniques on EvalFlash.
By Ruiyang Chen, Feiran Li, Heng Guo, Zhanyu Ma
The paper investigates how knowledge distillation from event cameras to RGB images can alter the inductive biases of convolutional neural networks. By transferring learning from the event domain, the authors find that models gain color invariance, a shape bias, and improved robustness to high‑frequency noise, largely due to reduced reliance on texture and increased emphasis on edge‑based object shape. These changes are evidenced by early‑layer processing differences and a spectral trade‑off between robustness to missing high‑frequency content and vulnerability to its contamination or geometric disruption.
By Soshun Kihara, Shunsuke Yasuki, Masato Taki