RefracGS is a novel framework for generating novel views through refractive water surfaces. It jointly reconstructs the water surface using a neural height field and the underlying scene with a 3D Gaussian field, employing refraction‑aware Gaussian ray tracing based on Snell’s law. The method achieves high‑fidelity view synthesis, outperforms prior refractive approaches, and offers 15× faster training with real‑time rendering at 200 FPS.
By Yiming Shao, Qiyu Dai, Chong Gao, Guanbin Li, Yequan Wang, He Sun, Qiong Zeng, Baoquan Chen, Wenzheng Chen
arXiv:2608.29269v1 Announce Type: new
Abstract: Relightable interactive scene reconstruction aims to build an editable 3D model from scans of different object arrangements and render new layouts unde...
By Haonan Zhou, Gaoxiang Linghu, Youlin Jia, Hongyu Cui, Kewei Wei, Kaiyue Zhou, Bruce X. B. Yu, Gaoang Wang
Recent advances in neural scene representations enable photorealistic novel-view synthesis, yet most methods remain tightly coupled to a single rendering paradigm, limiting their versatility and integration with conventional graphics workflows. We introduce Floating Radiance Networks (FlaRe), a neural scene representation combining explicit ray-traceable geometry with continuous neural radiance functions.
arXiv:2609.31198v1 Announce Type: new
Abstract: We present Light Field Primitives (LFP), a formulation for novel view synthesis that replaces the dense ray database with a compact set of differentiab...
By Liang Chen, Jiahui Ning, Xun Jiang, Xing Xu, Jimmy Ren, Fenglei Fan, Heng Tao Shen
arXiv:2609.05738v1 Announce Type: cross
Abstract: We present 'RenderFormer-V2', a unified learned transformer-based neural rendering model, complementary to modern physics-based rendering systems, th...
By Chong Zeng, Yue Dong, Pieter Peers, Lvmin Zhang, Maneesh Agrawala
arXiv:2603. 07664v3 Announce Type: replace-cross Abstract: The reflective appearance, especially strong and typically near-field specular reflections, poses a fundamental challenge for accurate surface reconstruction and novel view synthesis.
By Ningjing Fan, Yiqun Wang, Dongming Yan, Peter Wonka
Defocus blur degrades fine image structures and limits visual perception, which can adversely affect downstream vision tasks. Although recent deep learning deblurring methods have achieved strong performance, their effectiveness depends on training data and often degrades across cameras and lenses due to limited optical diversity and realism in existing datasets.
arXiv:2607.03470v2 Announce Type: replace
Abstract: Synthesizing physically accurate mirror reflections remains a fundamental challenge for modern text-to-image diffusion models, which are increasing...
By Xuan-Bach Mai, Duy-Phuc Nguyen, Quoc-Van Le, Tam V. Nguyen, Thanh-Toan Do, Huu Le, Duong-Van Nguyen, Minh-Triet Tran, Trung-Nghia Le
RelightFormer is a feed‑forward generative Transformer that performs single‑ and multi‑view image relighting without explicit intrinsic property estimation. It incorporates a latent illumination module that injects target environment maps into spatial features via cross‑attention, and uses permutation‑invariant positional encodings to process unordered multi‑view inputs symmetrically. Trained on the large Laval Objaverse Dataset, the model achieves state‑of‑the‑art visual and photorealistic relighting quality, and demonstrates strong zero‑shot generalization across various relighting tasks.
By Hejun Wang, Jinxi Li, Junwei Jiang, Shiwei Mao, Hu Cheng, Shouwang Huang, Bo Yang
arXiv:2606. 22574v2 Announce Type: replace-cross Abstract: While synthetic data generation resolves the manual labeling bottleneck in computer vision, minimizing the syn-to-real domain gap requires optimizing rendering variables.
By Hooman Tavakoli Ghinani, Tatjana Legler, Martin Ruskowski
Editable 3D scene creation requires object instances and lights that can be inspected, moved, and imported into standard engines, yet existing single-image methods largely stop at room-scale geometry, baked/global illumination, or text-driven generation. We introduce Lumera (Light-aware Unified Engine-native Reconstruction and Assembly), a benchmark and reference pipeline for engine-native, light-aware 3D scene parsing from a single image.
arXiv:2608.29881v1 Announce Type: new
Abstract: Monocular depth estimation has achieved strong open-domain generalization, yet reliable robotic deployment remains difficult in transparent, reflective...
By Muxin Liu, Tianbo Liu, Jing Xia, Xiaoyang Lyu, Xiaoshan Wu, Bo Wang, Peng Dai, Zhongrui Wang, Shaoshuai Shi, Xiaojuan Qi