Feed-Forward 3D Reconstruction

Follow this topic 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

SurfelSplat: Learning Efficient and Generalizable Gaussian Surfel Representations for Sparse-View Surface Reconstruction
Apr 9, 2026Chensheng Dai, Shengjun Zhang, Min Chen +1Sparse-View 3D Reconstruction 3D Gaussian Splatting
Tsinghua University
ReconPhys: Reconstruct Appearance and Physical Attributes from Single Video
Apr 9, 2026Boyuan Wang, Xiaofeng Wang, Yongkang Li +9Deformable Shape Reconstruction Feed-Forward 3D Reconstruction
GigaAI · Institute of Automation, Chinese Academy of Sciences · Tsinghua University
Genie Sim PanoRecon: Fast Immersive Scene Generation from Single-View Panorama
Apr 8, 2026Zhijun Li, Yongxin Su, Di Yang +43D Scene Generation Panoramic 3D Reconstruction
AnchorSplat: Feed-Forward 3D Gaussian Splatting with 3D Geometric Priors
Apr 8, 2026Xiaoxue Zhang, Xiaoxu Zheng, Yixuan Yin +53D Gaussian Splatting 3D Reconstruction
LSRM: High-Fidelity Object-Centric Reconstruction via Scaled Context Windows
Apr 6, 2026Zhengqin Li, Cheng Zhang, Jakob Engel +1Inverse Rendering 3D ViTs
Meta Reality Labs Research
SpectralSplat: Appearance-Disentangled Feed-Forward Gaussian Splatting for Driving Scenes
Apr 3, 2026Quentin Herau, Tianshuo Xu, Depu Meng +53D Gaussian Splatting Representation Disentanglement
Applied Intuition · The Hong Kong University of Science and Technology · University of California, Berkeley
Flash-Mono: Feed-Forward Accelerated Gaussian Splatting Monocular SLAM
Apr 3, 2026Zicheng Zhang, Ke Wu, Xiangting Meng +33DGS SLAM 3D Gaussian Splatting
Fudan University · ShanghaiTech University · Shanghai Jiao Tong University
SparseSplat: Towards Applicable Feed-Forward 3D Gaussian Splatting with Pixel-Unaligned Prediction
Apr 3, 2026Zicheng Zhang, Xiangting Meng, Ke Wu +13D Gaussian Splatting Feed-Forward 3D Reconstruction
Fudan University · ShanghaiTech University
Large-scale Codec Avatars: The Unreasonable Effectiveness of Large-scale Avatar Pretraining
Apr 2, 2026Junxuan Li, Rawal Khirodkar, Chengan He +373D Avatar Generation 3D Human Reconstruction
Codec Avatars Lab, Meta
HyVGGT-VO: Tightly Coupled Hybrid Dense Visual Odometry with Feed-Forward Models
Apr 2, 2026Junxiang Pan, Lipu Zhou, Baojie ChenVisual Odometry Feed-Forward 3D Reconstruction
The authors are with the School of Instrument Science and Opto-electronics Engineering, Beihang University, Beijing 100191, China
RecGen3D: Reconstruction-Guided 3D Generation in a Shared Canonical Space
Apr 1, 2026Zhisheng Huang, Jiahao Chen, Cheng Lin +103D Asset Generation 3D Scene Generation
Texas A&M University, College Station, USA · Macau University of Science and Technology, Macau, Macau · HKUST, Hong Kong, Hong Kong +2
Diff3R: Feed-forward 3D Gaussian Splatting with Uncertainty-aware Differentiable Optimization
Apr 1, 2026Yueh-Cheng Liu, Jozef Hladký, Matthias Nießner +13D Gaussian Splatting Feed-Forward 3D Reconstruction
Technical University of Munich · Computing Systems Lab, Huawei Technologies, Switzerland
Reliev3R: Relieving Feed-forward Reconstruction from Multi-View Geometric Annotations
Apr 1, 2026Youyu Chen, Junjun Jiang, Yueru Luo +43D Reconstruction Feed-Forward 3D Reconstruction
Harbin Institute of Technology · The Chinese University of Hong Kong, Shenzhen · Huawei
AA-Splat: Anti-Aliased Feed-forward Gaussian Splatting
Mar 31, 2026Taewoo Suh, Sungpyo Kim, Jongmin Park +13D Gaussian Splatting Feed-Forward 3D Reconstruction
Korea Advanced Institute of Science and Technology
GenFusion: Feed-forward Human Performance Capture via Progressive Canonical Space Updates
Mar 30, 2026Youngjoong Kwon, Yao He, Heejung Choi +43D Human Reconstruction Novel View Synthesis
Stanford University
From None to All: Self-Supervised 3D Reconstruction via Novel View Synthesis
Mar 29, 2026Ranran Huang, Weixun Luo, Ye Mao +13D Reconstruction Multi-View 3D Reconstruction
Imperial College London
HD-VGGT: High-Resolution Visual Geometry Transformer
Mar 28, 2026Tianrun Chen, Yuanqi Hu, Yidong Han +113D Reconstruction 3D ViTs
KOKONI 3D, Moxin Technology · Zhejiang University · Huzhou University +4
SceneExpander: Text-Guided 3D Scene Expansion via Free-Form View Insertion
Mar 28, 2026Zijian He, Renjie Liu, Yihao Wang +5Multi-View 3D Reconstruction Feed-Forward 3D Reconstruction
Sun Yat-sen University · KlingAI Research, Kuaishou Technology
Fus3D: Decoding Consolidated 3D Geometry from Feed-forward Geometry Transformer Latents
Mar 26, 2026Laura Fink, Linus Franke, George Kopanas +2Feed-Forward 3D Reconstruction Multi-View 3D Reconstruction
Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany · Inria, Université Côte d’Azur, France · Google DeepMind, UK
Less Gaussians, Texture More: 4K Feed-Forward Textured Splatting
Mar 26, 2026Yixing Lao, Xuyang Bai, Xiaoyang Wu +73D Gaussian Splatting Novel View Synthesis
HKU · Apple
ViewSplat: View-Adaptive 3D Gaussian Splatting for Feed-Forward Synthesis
Mar 26, 2026Moonyeon Jeong, Seunggi Min, Suhyeon Lee +13D Gaussian Splatting Novel View Synthesis
University of Seoul · Korea Electronics Technology Institute
AirSplat: Alignment and Rating for Robust Feed-Forward 3D Gaussian Splatting
Mar 26, 2026Minh-Quan Viet Bui, Jaeho Moon, Munchurl KimNovel View Synthesis 3D Gaussian Splatting
KAIST, Republic of Korea
HGGT: Robust and Flexible 3D Hand Mesh Reconstruction from Uncalibrated Images
Mar 25, 2026Yumeng Liu, Xiao-Xiao Long, Marc Habermann +53D Mesh Reconstruction 3D Reconstruction
University of Science and Technology of China · Nanjing University · Max-Planck-Institut für Informatik +3
AdvSplat: Adversarial Attacks on Feed-Forward Gaussian Splatting Models
Mar 24, 2026Yiran Qiao, Yiren Lu, Yunlai Zhou +4Adversarial Perturbations 3D Gaussian Splatting
Case Western Reserve University, Cleveland OH 44106, USA
SLARM: Streaming and Language-Aligned Reconstruction Model for Dynamic Scenes
Mar 24, 2026Zhicheng Qiu, Jiarui Meng, Tong-an Luo +4Dynamic Scene Reconstruction Streaming 3D Reconstruction
Huawei Technologies Ltd.
UniQueR: Unified Query-based Feedforward 3D Reconstruction
Mar 24, 2026Chensheng Peng, Quentin Herau, Jiezhi Yang +63D Gaussian Splatting 3D Reconstruction
Applied Intuition · UC Berkeley · Stanford University
CAM3R: Camera-Agnostic Model for 3D Reconstruction
Mar 23, 2026Namitha Guruprasad, Abhay Yadav, Cheng Peng +13D Reconstruction Multi-View 3D Reconstruction
Johns Hopkins University, Baltimore, MD 21218, USA · University of Virginia, Charlottesville, VA 22904, USA
F4Splat: Feed-Forward Predictive Densification for Feed-Forward 3D Gaussian Splatting
Mar 22, 2026Injae Kim, Chaehyeon Kim, Minseong Bae +23D Gaussian Splatting Adaptive Gaussian Densification
KAIST, Daejeon, Republic of Korea · Korea University, Seoul, Republic of Korea
2Xplat: Decoupling Geometry and Appearance Modeling for Feed-Forward 3D Gaussian Splatting
Mar 22, 2026Hwasik Jeong, Seungryong Lee, Gyeongjin Kang +43D Gaussian Splatting 3D Reconstruction
Yonsei University · Sungkyunkwan University
RayMap3R: Inference-Time RayMap for Dynamic 3D Reconstruction
Mar 21, 2026Feiran Wang, Zezhou Shang, Gaowen Liu +1Dynamic Scene Reconstruction Streaming 3D Reconstruction
University of Illinois Chicago · Cisco Research

Apr 9, 2026J/K move · Enter open · S save

SurfelSplat: Learning Efficient and Generalizable Gaussian Surfel Representations for Sparse-View Surface Reconstruction

Chensheng Dai, Shengjun Zhang, Min Chen, Yueqi Duan

Tsinghua University

Sparse-View 3D Reconstruction 3D Gaussian Splatting Feed-Forward 3D Reconstruction

Open paper AskPDF arXiv

3D Gaussian Splatting (3DGS) has demonstrated impressive performance in 3D scene reconstruction. Beyond novel view synthesis, it shows great potential for multi-view surface reconstruction. Existing methods employ optimization-based reconstruction pipelines that achieve precise and complete surface extractions. However, these approaches typically require dense input views and high time consumption for per-scene optimization. To address these limitations, we propose SurfelSplat, a feed-forward framework that generates efficient and generalizable pixel-aligned Gaussian surfel representations from sparse-view images. We observe that conventional feed-forward structures struggle to recover accurate geometric attributes of Gaussian surfels because the spatial frequency of pixel-aligned primitives exceeds Nyquist sampling rates. Therefore, we propose a cross-view feature aggregation module based on the Nyquist sampling theorem. Specifically, we first adapt the geometric forms of Gaussian surfels with spatial sampling rate-guided low-pass filters. We then project the filtered surfels across all input views to obtain cross-view feature correlations. By processing these correlations through a specially designed feature fusion network, we can finally regress Gaussian surfels with precise geometry. Extensive experiments on DTU reconstruction benchmarks demonstrate that our model achieves comparable results with state-of-the-art methods, and predict Gaussian surfels within 1 second, offering a 100x speedup without costly per-scene training.