Novel View Synthesis

Ask about this topic

Overview

Novel view synthesis studies how to render a scene from camera positions that were not observed, supporting applications such as 3D reconstruction, virtual reality, robotics, and medical imaging. Common approaches include neural radiance fields, 3D Gaussian Splatting, and feed-forward multi-view transformers; diffusion and video-generation models are increasingly used to fill unseen regions or handle large viewpoint changes. Methods are tested on benchmarks such as LLFF, Mip-NeRF 360, DTU, and RealEstate10K, with growing attention to sparse, unposed, dynamic, and multimodal inputs. A central challenge is balancing photorealistic completion of unseen content with geometrically consistent views, especially when extrapolating beyond the training cameras, while keeping models efficient and robust to real-world conditions.

Latest papers

CardsList

289 papers33 papers in the last four weeks, up 14% on the four weeks before. 0.2% of all new papers.

  1. Rectifying Mask via Entropy for Distractor-Free 3DGS in Ambiguous Scenarios

    Jun 28, 2026Wongi Park, Jiyeon Lim, Minjae Lee +63D Gaussian SplattingDynamic Scene Reconstruction

    1Ajou Univerity · 2Samsung Electronics · 3Georgia Institute of Technology +5

  2. Meshtryoshka: Differentiable Rendering of Real-World Scenes via Mesh Rasterization

    Jun 26, 2026David Charatan, Daniel Xu, Richard Szeliski +2Differentiable RenderingNovel View Synthesis

    Massachusetts Institute of Technology, United States · University of Washington, United States · Google DeepMind, United States

  3. PanoImager: Geometry-Guided Novel View Synthesis and Reconstruction from Sparse Panoramic Views

    Jun 25, 2026Zhisong Xu, Takeshi OishiMulti-View Consistency3D Gaussian Splatting

    Institute of Industrial Science, The University of Tokyo, Tokyo, Japan

  4. Rendering Novel Views of MRI Using 3D Gaussian Splatting

    Jun 24, 2026Robin Y. Park, Mark C. Eid, Rhydian Windsor +43D Gaussian SplattingNovel View Synthesis

    Visual Geometry Group, University of Oxford · Oxford Machine Learning in NeuroImaging Lab, University of Oxford

  5. PRISM: Feed-Forward Single-Image 3D Reconstruction via Geometric Warp-Residual Modeling

    Jun 24, 2026Zhijie Zheng, Xinhao Xiang, Jiawei ZhangNovel View SynthesisSingle-View 3D Reconstruction

    University of California, Davis CA 95616, USA

  6. Gastroendoscopy View Synthesis: A New Real Dataset and Evaluation

    Jun 24, 2026Masaki Minai, Yusuke Monno, Masatoshi Okutomi +13D Gaussian SplattingEndoscopy

    Department of Systems and Control Engineering, School of Engineering, Institute of Science Tokyo, Meguro-ku, Tokyo 152-8550, Japan · Department of Gastroenterology, International University of Health and Welfare Ichikawa Hospital, Ichikawa-shi, Chiba 272-0827, Japan

  7. DrivingVoxels: Compositional Sparse Voxel Rasterization for Dynamic Driving Scene Reconstruction

    Jun 22, 2026Tania Aguirre, Luis Roldão, Moussab Bennehar +4Autonomous DrivingDynamic Scene Reconstruction

    Noah’s Ark, Huawei Paris Research Center, France · EURECOM, France

  8. Learning Stable Canonical Worlds for Novel View Synthesis and Beyond

    Jun 22, 2026Xiaoyu Xu, Jian Zou, Sheyang Tang +3Multi-View ConsistencyNovel View Synthesis

    Department of Computer Science, City University of Hong Kong · Department of Electrical and Computer Engineering, University of Waterloo

  9. ACE-GS: Acing the Trade-off with Accurate, Compact and Efficient 3D Gaussian Splatting

    Jun 19, 2026Jijian Zhao3DGS Compression3D Gaussian Splatting

    Huazhong University of Science and Technology, Wuhan, China

  10. From Uncertainty to Stability and Fidelity: Guiding Sparse-View 3D Gaussian Splatting with Fisher Information

    Jun 18, 2026Junbao Zhou, Qingshan Xu, Yuan Zhou +73D Gaussian SplattingNovel View Synthesis

    Nanyang Technological University, Singapore · University of Science and Technology of China, China · Zhejiang University, China +1

  11. VisDom: Sparse Novel View Synthesis with Visible Domain Constraint

    Jun 18, 2026Mariia Gladkova*, Tarun Yenamandra*, Edmond Boyer +3Multi-View 3D ReconstructionNovel View Synthesis

    1TU Munich · 2MCML

  12. One-Shot Novel View and Pose Human Image Synthesis via 3D Prior Guided Diffusion Model

    Jun 18, 2026Shenjian Gong, Kangkan Wang, Shanshan Zhang +1Image GenerationNovel View Synthesis

    PCA Lab, Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education, and Jiangsu Key Lab of Image and Video Understanding for Social Security, School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, 210094 China

  13. CD-RCM: Generalizable Continuous-Depth Novel View Synthesis for Reflectance Confocal Microscopy

    Jun 10, 2026Tooba Imtiaz, Milind Rajadhyaksha, Kivanc Kose +1Novel View SynthesisSparse-View 3D Reconstruction

    Northeastern University · Memorial Sloan Kettering Cancer Center

  14. Scene-Adaptive Nonlinear Tone Curves for Pseudo Ground-Truth Generation in Low-Light 3D Gaussian Splatting

    Jun 10, 2026Mingzhe Lyu, Jinqiang Cui, Hong Zhang3D Gaussian SplattingImage Enhancement

    Shenzhen Key Laboratory of Robotics and Computer Vision, Southern University of Science and Technology, Shenzhen, 518055, China. · Pengcheng Laboratory, Shenzhen, 518108, China.

  15. Beyond Spherical Harmonics: Rethinking Appearance Models for Radiance Reconstruction

    Jun 8, 2026Ewa Miazga, Jorge Condor, Piotr DidykNovel View Synthesis3D Scene Representation

    1École Polytechnique Fédérale de Lausanne, Switzerland · 2Università della Svizzera Italiana, Lugano, Switzerland

  16. Leveraging NeRF-Rendered Images for 3D Gaussian Splatting

    Jun 8, 2026Mizuki Morikawa, Yuta Shimizu, Chunyu Li +23D Gaussian SplattingNovel View Synthesis

    Institute of Science Tokyo, Tokyo, Japan

  17. LEGS: Laplacian-Enhanced Gaussian Splatting with a Nonlinear Weighted Loss

    Jun 6, 2026Yongfei Guo, Qizhou Huo, Xuan Sun +13D Gaussian Splatting3D Reconstruction

    Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun, China · University of Chinese Academy of Sciences, Beijing, China

  18. UniSHARP: Universal Sharp Monocular View Synthesis

    Jun 5, 2026Meixi Song, Dizhe Zhang, Hao Ren +43D Gaussian SplattingNeural Rendering

    Insta360 Research · Sun Yat-sen University · Beihang University +2

  19. Unpaired RGB-Thermal Gaussian-Splatting Using Visual Geometric Transformers

    Jun 3, 2026Jean Cordonnier, Chenghao Xu, Olga Fink +1Thermal Imaging3D Gaussian Splatting

    Ecole Polytechnique Federale de Lausanne, Lausanne, Switzerland · Schindler EPFL Lab, Lausanne, Switzerland

  20. FreeStreamGS: Online Feed-forward 3D Gaussian Splatting from Unposed Streaming Inputs

    Jun 2, 2026Ruiyang Chen, Feiran Li, Chu Zhou +33D Gaussian SplattingStreaming 3D Reconstruction

    Beijing University of Posts and Telecommunications, China · Independent Researcher · National Institute of Informatics, Japan

  21. KC-3DGS: Kurtosis-Constrained Gaussian Splatting for High-Fidelity View Synthesis

    Jun 2, 2026Vivekjyoti Banerjee, Abhay Yadav, Rama Chellappa +13D Gaussian SplattingNovel View Synthesis

    Johns Hopkins University · NEC Labs America

  22. The Road Ahead in Autonomous Driving: The KITScenes Multimodal Dataset

    Jun 1, 2026Richard Schwarzkopf, Fabian Immel, Alexander Blumberg +21Autonomous Driving DatasetsAutonomous Driving Benchmarks

    FZI Research Center for Information Technology · Karlsruhe Institute of Technology · University Charles III of Madrid +1

  23. Fast and Lightweight Novel View Synthesis with Differentiable Multiplane Image

    Jun 1, 2026Kaidi Zhang, Guanxu ZhuNeural RenderingNovel View Synthesis

    Universiti Malaya · Wuhan University

  24. Effective Multi-sensor Conditioning for Street-view Novel-view Synthesis

    Jun 1, 2026Zhengfei Kuang, Adam Sun, Liyuan Zhu +7Camera-Conditioned Video GenerationVideo Diffusion Models

    1Stanford Univerity · 2NVIDIA

  25. VG2\text{VG}^2GT: Voxel-Gaussian Splatting Visual Geometry Grounded Transformer

    Jun 1, 2026Yibin Zhao, Yihan Pan, Jun Nan +33D Gaussian SplattingNovel View Synthesis

    East China University of Science and Technology, 130 Meilong Road, Shanghai, 200237, China · Shanghai Open University, 288 Guoshun Road, 200433, Shanghai, China · Shanghai Xiaoyuan Innovation Center, 599 Xingmei Road, 200237, Shanghai, China

  26. DENSER: Depth-Guided Ensemble with Staged EFA-GS Reconstruction for Soccer Novel View Synthesis

    May 31, 2026Parthsarthi Rawat3D Gaussian SplattingNovel View Synthesis

    GameChanger by Dick’s Sporting Goods

  27. DeblurNVS: Geometric Latent Diffusion for Novel View Synthesis from Sparse Motion-Blurred Images

    May 31, 2026Changyue Shi, Wangbo Yu, Chaoran Feng +1Latent Diffusion Models3D Reconstruction

    School of AI for Science, Peking University Shenzhen Graduate School, Shenzhen, 518055 China · School of Electronic and Computer Engineering, Peking University Shenzhen Graduate School, Shenzhen, 518055 China

  28. RayDer: Scalable Self-Supervised Novel View Synthesis from Real-World Video

    May 29, 2026Ulrich Prestel, Stefan Andreas Baumann, Nick Stracke +13D ViTsNovel View Synthesis

  29. Equivariant Latent Alignment via Flow Matching under Group Symmetries

    May 29, 2026Sunghyun Kim, Jaehoon Hahm, Jeongwoo Shin +1Flow MatchingEquivariant Neural Networks

    1Seoul National University, Seoul, Korea · University of Illinois Urbana-Champaign, Illinois, USA

  30. Supercharging Thermal Gaussian Splatting with Depth Estimation

    May 28, 2026Manoj Biswanath, Chenxin Cai, Hannah Schieber +2Thermal Imaging3D Gaussian Splatting

    Photogrammetry and Remote Sensing, Munich Center for Machine Learning (MCML), Technical University of Munich, Munich, Germany · Technical University of Munich, Munich, Germany · Human-Centered Computing and Extended Reality Lab, TUM University Hospital, Clinic for Orthopedics and Sports Orthopedics, Munich Institute of Robotics and Machine Intelligence (MIRMI), Technical University of Munich, Munich, Germany