3D 视觉

SymDrive: Realistic and Controllable Driving Simulator via Symmetric Auto-regressive Online Restoration

SymDrive: 通过对称自回归在线修复实现逼真且可控的驾驶模拟器

Zhiyuan Liu, Daocheng Fu, Pinlong Cai, Lening Wang, Ying Liu, Yilong Ren, Botian Shi, Jianqiang Wang

机构 * School of Vehicle and Mobility, Tsinghua University（清华大学车辆与移动系统学院） ； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） ； State Key Lab of Intelligent Transportation System, Beihang University（北航智能交通系统国家重点实验室） 纠错

专题命中 新视角合成 ：novel view synthesis(abstract)；分类 cs.CV、cs.RO

AI总结 SymDrive通过对称自回归在线修复技术，实现了逼真可控的驾驶模拟，解决了高保真渲染与交互式交通编辑的难题。

OLATverse: A Large-scale Real-world Object Dataset with Precise Lighting Control

OLATverse：一个具有精确光照控制的大规模真实世界物体数据集

Xilong Zhou, Jianchun Chen, Pramod Rao, Timo Teufel, Linjie Lyu, Tigran Minasian, Oleksandr Sotnychenko, Xiao-Xiao Long, Marc Habermann, Christian Theobalt

机构 * Max Planck Institute for Informatics（马克斯·普朗克信息研究所） ； Nanjing University（南京大学） 纠错

专题命中 新视角合成 ：novel view synthesis(abstract)；分类 cs.CV、cs.GR

AI总结 OLATverse通过大规模真实物体和精确光照控制，为反向渲染和法线估计提供首个全面的现实世界基准数据集。

HybridWorldSim: A Scalable and Controllable High-fidelity Simulator for Autonomous Driving

HybridWorldSim: 一种可扩展且可控的高保真驾驶仿真器

Qiang Li, Yingwenqi Jiang, Tuoxi Li, Duyu Chen, Xiang Feng, Yucheng Ao, Shangyue Liu, Xingchen Yu, Youcheng Cai, Yumeng Liu, Yuexin Ma, Xin Hu, Li Liu, Yu Zhang, Linkun Xu, Bingtao Gao, Xueyuan Wang, Shuchang Zhou, Xianming Liu, Ligang Liu

机构 * XPeng Motors ； ShanghaiTech University（上海科技大学） ； University of Science and Technology of China（中国科学技术大学） 纠错

专题命中 新视角合成 ：novel view synthesis(abstract)；分类 cs.CV、cs.RO

AI总结 HybridWorldSim通过整合多遍神经重建与生成模型，实现高保真驾驶仿真，提供可扩展且可控的仿真环境及新的多遍数据集MIRROR，推动自动驾驶研究。

Comments Project page: https://hybridworldsim.github.io/

RealEngine: Simulating Autonomous Driving in Realistic Context

Junzhe Jiang, Nan Song, Jingyu Li, Xiatian Zhu, Li Zhang

机构 * School of Data Science, Fudan University（复旦大学数据科学学院） ； University of Surrey（萨里大学） 纠错

专题命中 新视角合成 ：novel view synthesis(abstract)；分类 cs.CV、cs.RO

Unsupervised Continual Semantic Adaptation through Neural Rendering

Zhizheng Liu, Francesco Milano, Jonas Frey, Roland Siegwart, Hermann Blum, Cesar Cadena

专题命中 新视角合成 ：NeRF(abstract)；分类 cs.CV、cs.RO

Comments Accepted by the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023. Zhizheng Liu and Francesco Milano share first authorship. Hermann Blum and Cesar Cadena share senior authorship. 18 pages, 8 figures, 9 tables

GaVS: 3D-Grounded Video Stabilization via Temporally-Consistent Local Reconstruction and Rendering

Zinuo You, Stamatios Georgoulis, Anpei Chen, Siyu Tang, Dengxin Dai

机构 * ETH Z\"urich Z\"urich Switzerland ； Huawei Research Z\"urich Z\"urich Switzerland ； ETH Z\"urich ； Huawei Research Z\"urich 纠错

专题命中 新视角合成 ：Gaussian Splatting(abstract)；分类 cs.CV、cs.GR

Comments siggraph 2025, project website: https://sinoyou.github.io/gavs. version 2, update discussion

Anisotropic Neural Representation Learning for High-Quality Neural Rendering

Y. Wang, J. Xu, Y. Zeng, Y. Gong

机构 * Southern University of Science and Technology（南方科技大学） 纠错

专题命中 新视角合成 ：NeRF(abstract)；分类 cs.CV、cs.GR

Journal ref 2025

Next-Scale Autoregressive Models are Zero-Shot Single-Image Object View Synthesizers

Shiran Yuan, Hao Zhao

机构 * UC Berkeley（加州大学伯克利分校） ； Tsinghua University（清华大学） 纠错

专题命中 新视角合成 ：novel view synthesis(abstract)；分类 cs.CV、cs.GR

Comments Full codebase, training set, and eval benchmark at https://github.com/Shiran-Yuan/ArchonView

GeoDrive: 3D Geometry-Informed Driving World Model with Precise Action Control

Anthony Chen, Wenzhao Zheng, Yida Wang, Xueyang Zhang, Kun Zhan, Peng Jia, Kurt Keutzer, Shanghang Zhang

机构 * State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University（多媒体信息处理国家重点实验室，计算机学院，北京大学） ； Li Auto Inc.（利亚德公司） ； UC Berkeley（加州大学伯克利分校） 纠错

专题命中 新视角合成 ：spatial understanding(abstract)；分类 cs.CV、cs.RO

Comments code will be released at https://github.com/antonioo-c/GeoDrive

TesserAct: Learning 4D Embodied World Models

Haoyu Zhen, Qiao Sun, Hongxin Zhang, Junyan Li, Siyuan Zhou, Yilun Du, Chuang Gan

机构 * UMass Amherst（马萨诸塞大学阿默斯特分校） ； HKUST（香港科技大学） ； Harvard University（哈佛大学） 纠错

专题命中 新视角合成 ：novel view synthesis(abstract)；分类 cs.CV、cs.RO

Comments Project Page: https://tesseractworld.github.io/

Sparse Voxels Rasterization: Real-time High-fidelity Radiance Field Rendering

Cheng Sun, Jaesung Choe, Charles Loop, Wei-Chiu Ma, Yu-Chiang Frank Wang

专题命中 新视角合成 ：Gaussian Splatting(abstract)；分类 cs.CV、cs.GR

Comments CVPR 2025; Project page at https://svraster.github.io/ ; Code at https://github.com/NVlabs/svraster

SPA: 3D Spatial-Awareness Enables Effective Embodied Representation

Haoyi Zhu, Honghui Yang, Yating Wang, Jiange Yang, Limin Wang, Tong He

专题命中 新视角合成 ：spatial understanding(abstract)；分类 cs.CV、cs.RO

Comments Project Page: https://haoyizhu.github.io/spa/

VistaFlow: Photorealistic Volumetric Reconstruction with Dynamic Resolution Management via Q-Learning

Jayram Palamadai, William Yu

专题命中 新视角合成 ：novel view synthesis(abstract)；分类 cs.CV、cs.GR

GISR: Geometric Initialization and Silhouette-based Refinement for Single-View Robot Pose and Configuration Estimation

Ivan Bilić, Filip Marić, Fabio Bonsignorio, Ivan Petrović

专题命中 新视角合成 ：spatial understanding(abstract)；分类 cs.CV、cs.RO

Comments Accepted for publication in the Robotics and Automation Letters 2024

LiftRefine: Progressively Refined View Synthesis from 3D Lifting with Volume-Triplane Representations

Tung Do, Thuan Hoang Nguyen, Anh Tuan Tran, Rang Nguyen, Binh-Son Hua

专题命中 新视角合成 ：3D generation(abstract)；分类 cs.CV、cs.GR

SimVS: Simulating World Inconsistencies for Robust View Synthesis

Alex Trevithick, Roni Paiss, Philipp Henzler, Dor Verbin, Rundi Wu, Hadi Alzayer, Ruiqi Gao, Ben Poole, Jonathan T. Barron, Aleksander Holynski, Ravi Ramamoorthi, Pratul P. Srinivasan

专题命中 新视角合成 ：3D reconstruction(abstract)；分类 cs.CV、cs.GR

Comments Project page: https://alextrevithick.github.io/simvs

VoxNeRF: Bridging Voxel Representation and Neural Radiance Fields for Enhanced Indoor View Synthesis

Sen Wang, Qing Cheng, Stefano Gasperini, Wei Zhang, Shun-Cheng Wu, Niclas Zeller, Daniel Cremers, Nassir Navab

专题命中 新视角合成 ：novel view synthesis(abstract)；分类 cs.CV、cs.RO

Comments 8 pages, 4 figures

CRAYM: Neural Field Optimization via Camera RAY Matching

Liqiang Lin, Wenpeng Wu, Chi-Wing Fu, Hao Zhang, Hui Huang

专题命中 新视角合成 ：novel view synthesis(abstract)；分类 cs.CV、cs.GR

Comments Published in NeurIPS 2024

InstantGeoAvatar: Effective Geometry and Appearance Modeling of Animatable Avatars from Monocular Video

Alvaro Budria, Adrian Lopez-Rodriguez, Oscar Lorente, Francesc Moreno-Noguer

专题命中 新视角合成 ：novel view synthesis(abstract)；分类 cs.CV、cs.GR

Comments Accepted as poster to Asian Conference on Computer Vison (ACCV 2024)

Learning Generalizable Feature Fields for Mobile Manipulation

Ri-Zhao Qiu, Yafei Hu, Yuchen Song, Ge Yang, Yang Fu, Jianglong Ye, Jiteng Mu, Ruihan Yang, Nikolay Atanasov, Sebastian Scherer, Xiaolong Wang

专题命中 新视角合成 ：novel view synthesis(abstract)；分类 cs.CV、cs.RO

Comments Preprint. Project website is at: https://geff-b1.github.io/

Quark: Real-time, High-resolution, and General Neural View Synthesis

John Flynn, Michael Broxton, Lukas Murmann, Lucy Chai, Matthew DuVall, Clément Godard, Kathryn Heal, Srinivas Kaza, Stephen Lombardi, Xuan Luo, Supreeth Achar, Kira Prabhu, Tiancheng Sun, Lynn Tsai, Ryan Overbeck

专题命中 新视角合成 ：novel view synthesis(abstract)；分类 cs.CV、cs.GR

Comments SIGGRAPH Asia 2024 camera ready version; project page https://quark-3d.github.io/

IllumiNeRF: 3D Relighting Without Inverse Rendering

Xiaoming Zhao, Pratul P. Srinivasan, Dor Verbin, Keunhong Park, Ricardo Martin Brualla, Philipp Henzler

专题命中 新视角合成 ：NeRF(abstract)；分类 cs.CV、cs.GR

Comments NeurIPS 2024; v2 (for camera-ready) added single-GPU results and discussions on Stanford-ORB illuminations; Project page: https://illuminerf.github.io/

DistillNeRF: Perceiving 3D Scenes from Single-Glance Images by Distilling Neural Fields and Foundation Model Features

Letian Wang, Seung Wook Kim, Jiawei Yang, Cunjun Yu, Boris Ivanovic, Steven L. Waslander, Yue Wang, Sanja Fidler, Marco Pavone, Peter Karkus

专题命中 新视角合成 ：novel view synthesis(abstract)；分类 cs.CV、cs.RO

Comments Accepted by Advances in Neural Information Processing Systems (NeurIPS 2024)

Neural Isometries: Taming Transformations for Equivariant ML

Thomas W. Mitchel, Michael Taylor, Vincent Sitzmann

专题命中 新视角合成 ：3D vision(abstract)；分类 cs.CV、cs.GR

Comments NeurIPS 2024

Generative Image as Action Models

Mohit Shridhar, Yat Long Lo, Stephen James

专题命中 新视角合成 ：novel view synthesis(abstract)；分类 cs.CV、cs.RO

Comments CoRL 2024. Website, code, checkpoints: https://genima-robot.github.io/

Flash Cache: Reducing Bias in Radiance Cache Based Inverse Rendering

Benjamin Attal, Dor Verbin, Ben Mildenhall, Peter Hedman, Jonathan T. Barron, Matthew O'Toole, Pratul P. Srinivasan

专题命中 新视角合成 ：3D reconstruction(abstract)；分类 cs.CV、cs.GR

Comments Website: https://benattal.github.io/flash-cache/

GaussianHeads: End-to-End Learning of Drivable Gaussian Head Avatars from Coarse-to-fine Representations

Kartik Teotia, Hyeongwoo Kim, Pablo Garrido, Marc Habermann, Mohamed Elgharib, Christian Theobalt

专题命中 新视角合成 ：novel view synthesis(abstract)；分类 cs.CV、cs.GR

Comments ACM Transaction on Graphics (SIGGRAPH Asia 2024); Project page: https://vcai.mpi-inf.mpg.de/projects/GaussianHeads/

ReShader: View-Dependent Highlights for Single Image View-Synthesis

Avinash Paliwal, Brandon Nguyen, Andrii Tsarov, Nima Khademi Kalantari

专题命中 新视角合成 ：novel view synthesis(abstract)；分类 cs.CV、cs.GR

Comments SIGGRAPH Asia 2023. Project page at https://people.engr.tamu.edu/nimak/Papers/SIGAsia2023_Reshader/index.html and video at https://www.youtube.com/watch?v=XW-tl48D3Ok

Journal ref ACM Transactions on Graphics (ToG) 42,6 (2023) 1-9

Objects With Lighting: A Real-World Dataset for Evaluating Reconstruction and Rendering for Object Relighting

Benjamin Ummenhofer, Sanskar Agrawal, Rene Sepulveda, Yixing Lao, Kai Zhang, Tianhang Cheng, Stephan Richter, Shenlong Wang, German Ros

专题命中 新视角合成 ：novel view synthesis(abstract)；分类 cs.CV、cs.GR

Comments Accepted at 3DV 2024, Oral presentation. For the project page see https://github.com/isl-org/objects-with-lighting

City-on-Web: Real-time Neural Rendering of Large-scale Scenes on the Web

Kaiwen Song, Xiaoyi Zeng, Chenqu Ren, Juyong Zhang

专题命中 新视角合成 ：novel view synthesis(abstract)；分类 cs.CV、cs.GR

Comments Project page: https://ustc3dv.github.io/City-on-Web/