Feed-Forward 3D Reconstruction

Ask about this topic

Latest papers 284

41 papers in the last four weeks, up 95% on the four weeks before. 0.2% of all new papers.

All topics
CardsList

  1. Benchmarking Efficient & Effective Camera Pose Estimation Strategies for Novel View Synthesis

    Mar 20, 2026Jhacson Meza, Martin R. Oswald, Torsten SattlerCamera Pose EstimationStructure from Motion

    Faculty of Electrical Engineering, Czech Technical University in Prague · Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague · University of Amsterdam

  2. SegVGGT: Joint 3D Reconstruction and Instance Segmentation from Multi-View Images

    Mar 20, 2026Jinyuan Qu, Hongyang Li, Lei Zhang3D Instance SegmentationMulti-View 3D Reconstruction

    Tsinghua University · International Digital Economy Academy (IDEA) · South China University of Technology

  3. StreetForward: Perceiving Dynamic Street with Feedforward Causal Attention

    Mar 20, 2026Zhongrui Yu, Zhao Wang, Yijia Xie +4Dynamic Scene ReconstructionFeed-Forward 3D Reconstruction

    Li Auto Inc. · Zhejiang University

  4. SwiftGS: Episodic Priors for Immediate Satellite Surface Recovery

    Mar 19, 2026Rong Fu, Jiekai Wu, Xiaowen Ma +43D ReconstructionFeed-Forward 3D Reconstruction

    Independent Researcher

  5. S-VGGT: Structure-Aware Subscene Decomposition for Scalable 3D Foundation Models

    Mar 18, 2026Xinze Li, Pengxu Chen, Yiyuan Wang +23D Foundation ModelsEfficient Attention

    Beijing Normal-Hong Kong Baptist University · Jilin University · Hong Kong Baptist University +1

  6. PanoVGGT: Feed-Forward 3D Reconstruction from Panoramic Imagery

    Mar 18, 2026Yijing Guo, Mengjun Chao, Luo Wang +5Panoramic 3D ReconstructionFeed-Forward 3D Reconstruction

    ShanghaiTech University · Sudo

  7. Leveling3D: Leveling Up 3D Reconstruction with Feed-Forward 3D Gaussian Splatting and Geometry-Aware Generation

    Mar 17, 2026Yiming Huang, Baixiang Huang, Beilei Cui +3Novel View Synthesis3D Gaussian Splatting

    The Chinese University of Hong Kong

  8. ILV: Iterative Latent Volumes for Fast and Accurate Sparse-View CT Reconstruction

    Mar 16, 2026Seungryong Lee, Woojeong Baek, Joosang Lee +1Cone-Beam CTImage Reconstruction

    Sungkyunkwan University · Yonsei University

  9. Zero-Shot Reconstruction of Animatable 3D Avatars with Cloth Dynamics from a Single Image

    Mar 16, 2026Joohyun Kwon, Geonhee Sim, Gyeongsik Moon3D Avatar GenerationHuman Avatar Animation

    Korea University

  10. HARMONI: Aligning Human and Scene Priors for Multi-View 4D Reconstruction

    Mar 13, 2026Sangmin Kim, Minhyuk Hwang, Geonho Cha +23D ReconstructionMulti-View 3D Reconstruction

    Seoul National University · NAVER Cloud

  11. InstantHDR: Single-forward Gaussian Splatting Initialization for HDR 3D Reconstruction

    Mar 11, 2026Dingqiang Ye, Jiacong Xu, Jianglu Ping +3HDR ImagingNeural Rendering

    Johns Hopkins University, USA · Shenzhen University, China

  12. GGPT: Geometry Grounded Point Transformer

    Mar 11, 2026Yutong Chen, Yiming Wang, Xucong Zhang +2Sparse-View 3D ReconstructionFeed-Forward 3D Reconstruction

    ETH Zurich · Delft University of Technology

  13. ReCoSplat: Online Feed-Forward Gaussian Splatting via Render-and-Compare

    Mar 10, 2026Freeman Cheng, Botao Ye, Xueting Li +33D Gaussian SplattingStreaming 3D Reconstruction

    University of California, Merced · ETH Zürich · NVIDIA +2

  14. DenoiseSplat: Feed-Forward Gaussian Splatting for Noisy 3D Scene Reconstruction

    Mar 10, 2026Fuzhen Jiang, Zhuoran Li, Yinlin Zhang3D ReconstructionMulti-View 3D Reconstruction

    Hangzhou Dianzi University, Hangzhou, Zhejiang, China

  15. DynamicVGGT: Learning Dynamic Point Maps for 4D Scene Reconstruction in Autonomous Driving

    Mar 9, 2026Zhuolin He, Jing Li, Guanghao Li +9Dynamic Scene ReconstructionAutonomous Driving Perception

    Fudan University · Yinwang Intelligent Technology · Huawei +2

  16. Speed3R: Sparse Feed-forward 3D Reconstruction Models

    Mar 9, 2026Weining Ren, Xiao Tan, Kai Han3D ReconstructionFeed-Forward 3D Reconstruction

    The University of Hong Kong · Baidu AMU

  17. ReconDrive: Fast Feed-Forward 4D Gaussian Splatting for Autonomous Driving Scene Reconstruction

    Mar 8, 2026Haibao Yu, Kuntao Xiao, Jiahang Wang +7Dynamic Scene Reconstruction3D Gaussian Splatting

    The University of Hong Kong · Tuojing Intelligence · King’s College London +2

  18. FTSplat: Feed-forward Triangle Splatting Network

    Mar 6, 2026Xiong Jinlin, Li Can, Shen Jiawei +3Feed-Forward 3D ReconstructionMulti-View 3D Reconstruction

    Jinlin Xiong, Can Li, Jiawei Shen and Lei Sun are with Tianjin Key Laboratory of Intelligent Robotics, Nankai University, Tianjin 300350, China (tjKLIR). · Dongyang Zhao and Zhigang Qi are with Beijing Institute of Computer Application, Beijing 100081, China.

  19. CylinderSplat: 3D Gaussian Splatting with Cylindrical Triplanes for Panoramic Novel View Synthesis

    Mar 6, 2026Qiwei Wang, Xianghui Ze, Jingyi Yu +1Novel View Synthesis3D Gaussian Splatting

    Shanghaitech University · Nanjing University of Science and Technology

  20. ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Training

    Mar 4, 2026Haian Jin, Rundi Wu, Tianyuan Zhang +43D ReconstructionMulti-View 3D Reconstruction

    Google DeepMind · Cornell University · Massachusetts Institute of Technology

  21. EmbodiedSplat: Online Feed-Forward Semantic 3DGS for Open-Vocabulary 3D Scene Understanding

    Mar 4, 2026Seungjun Lee, Zihan Wang, Yunsong Wang +13D Scene UnderstandingLanguage-Embedded 3DGS

    National University of Singapore

  22. NOVA3R: Non-pixel-aligned Visual Transformer for Amodal 3D Reconstruction

    Mar 4, 2026Weirong Chen, Chuanxia Zheng, Ganlin Zhang +23D ReconstructionMulti-View 3D Reconstruction

    Technical University of Munich · Munich Center for Machine Learning · University of Oxford +1

  23. LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory

    Mar 3, 2026Junyi Zhang, Charles Herrmann, Junhwa Hur +53D ReconstructionStreaming 3D Reconstruction

    Google DeepMind · UC Berkeley

  24. SemGS: Feed-Forward Semantic 3D Gaussian Splatting from Sparse Views for Generalizable Scene Understanding

    Mar 3, 2026Sheng Ye, Zhen-Hui Dong, Ruoyu Fan +23D Scene Understanding3D Gaussian Splatting

    Department of Computer Science, Tsinghua University, Beijing, China

  25. OnlineX: Unified Online 3D Reconstruction and Understanding with Active-to-Stable State Evolution

    Mar 2, 2026Chong Xia, Fangfu Liu, Yule Wang +23D ReconstructionStreaming 3D Reconstruction

    Tsinghua University

  26. RnG: A Unified Transformer for Complete 3D Modeling from Partial Observations

    Mar 1, 2026Mochu Xiang, Zhelun Shen, Xuesong Li +7Feed-Forward 3D Reconstruction3D ViTs

    Northwestern Polytechnical University, China · Baidu Inc., China · Australian National University, Australia +1

  27. TokenSplat: Token-aligned 3D Gaussian Splatting for Feed-forward Pose-free Reconstruction

    Feb 28, 2026Yihui Li, Chengxin Lv, Zichen Tang +23D ReconstructionMulti-View 3D Reconstruction

    State Key Laboratory of Complex and Critical Software Environment, Beijing, China · School of Computer Science and Engineering, Beihang University, China · School of Artificial Intelligence, Beihang University, China

  28. SR3R: Rethinking Super-Resolution 3D Reconstruction With Feed-Forward Gaussian Splatting

    Feb 27, 2026Xiang Feng, Xiangbo Wang, Tieshi Zhong +73D Reconstruction3D Gaussian Splatting

    Hangzhou Dianzi University · ShanghaiTech University · Peking University +1

  29. AHAP: Reconstructing Arbitrary Humans from Arbitrary Perspectives with Geometric Priors

    Feb 27, 2026Xiaozhen Qiao, Wenjia Wang, Zhiyuan Zhao +43D Human ReconstructionFeed-Forward 3D Reconstruction

    Institute of Artificial Intelligence (TeleAI), China Telecom, P. R. China. · University of Science and Technology of China. · University of Hong Kong. +1

  30. VGG-T3^3: Offline Feed-Forward 3D Reconstruction at Scale

    Feb 26, 2026Sven Elflein, Ruilong Li, Sérgio Agostinho +43D ReconstructionFeed-Forward 3D Reconstruction

    NVIDIA · Vector Institute · University of Toronto