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

SCOPE: Scale-Consistent One-Pass Estimation of 3D Geometry
Jun 19, 2026Zheng Zhang, Lihe Yang, Tianyu Yang +6Streaming 3D Reconstruction 3D Reconstruction
The University of Hong Kong, Hong Kong · Alibaba Group, Hong Kong · Alibaba Group, China +2
Hand-4DGS: Feed-Forward 3D Gaussian Splatting for 4D Hand Reconstruction from Egocentric Videos
Jun 17, 2026Jeongmin Bae, Seoha Kim, Marc Pollefeys +33D Gaussian Splatting 4D Reconstruction
Yonsei University · Electronics and Telecommunications Research Institute · ETH Zurich +2
MVM-IOD: An Industrial Object-Centric Benchmark Dataset for the Evaluation of 3D Reconstruction Methods
Jun 15, 2026Robert Langendörfer, Markus Hillemann, Markus Ulrich3D Reconstruction Camera Pose Estimation
Machine Vision Metrology, Institute of Photogrammetry and Remote Sensing, Karlsruhe Institute of Technology, Germany
Uncertainty Quality of VGGT: An Analysis on the DTU Benchmark Dataset
Jun 15, 2026Markus Hillemann, Robert Langendörfer, Steven Landgraf +13D ViTs 3D Reconstruction
Institute of Photogrammetry and Remote Sensing, Karlsruhe Institute of Technology, Germany
SpatialAvatar-0: High-Quality 4D Head Avatar with Multi-Stage Reconstruction
Jun 14, 2026Yiran Wang, Zeyu Zhang, Yuanming Li +23D Gaussian Splatting 4D Reconstruction
1USYD · 2SpatialReal · 3ZJU +1
Pano3D: Unified 3D Reconstruction and Panoptic Segmentation
Jun 12, 2026Victor Barberteguy, Ahmet Iscen, Mathilde Caron +3Panoptic Segmentation 3D Semantic Segmentation
Google DeepMind · LIGM, École des Ponts, IP Paris, Univ Gustave Eiffel, CNRS
Surflo: Consistent 3D Surface Flow Model with Global State
Jun 11, 2026Antoine Guédon, Shu Nakamura, Nicolas Dufour +33D Reconstruction Multi-View 3D Reconstruction
LIX, École polytechnique · Kyoto University · Kyutai +1
CD-RCM: Generalizable Continuous-Depth Novel View Synthesis for Reflectance Confocal Microscopy
Jun 10, 2026Tooba Imtiaz, Milind Rajadhyaksha, Kivanc Kose +1Novel View Synthesis Sparse-View 3D Reconstruction
Northeastern University · Memorial Sloan Kettering Cancer Center
Wild3R: Feed-Forward 3D Gaussian Splatting from Unconstrained Sparse Photo Collection
Jun 10, 2026Yuto Furutani, Takashi Otonari, Kaede Shiohara +13D Gaussian Splatting Sparse-View 3D Reconstruction
The University of Tokyo
DarkVGGT: Seeing Through Darkness Using Thermal Geometry
Jun 9, 2026Minseong Kweon, Wenyuan Zhao, Nuo Chen +6Thermal Imaging 3D Reconstruction
University of Minnesota · Texas A&M University · Stanford University
Empowering Feed-Forward Reconstruction Models with Metric Scale via Satellite Images
Jun 6, 2026Xianghui Ze, Yongjian Luo, Mengjun Chao +3Metric Depth Estimation 3D Reconstruction
Nanjing University of Science and Technology · ShanghaiTech University
ZipSplat: Fewer Gaussians, Better Splats
Jun 3, 2026Alexander Veicht, Sunghwan Hong, Dániel Baráth +13D Gaussian Splatting Multi-View 3D Reconstruction
ETH Zürich · Microsoft
Anchor3R: Streaming 3D Reconstruction with Transient Anchors for Long-Horizon Visual Mapping
Jun 3, 2026Peilin Tao, Chong Cheng, Yuansen Du +8Relative Pose Estimation Streaming 3D Reconstruction
1CASIA · 2UCAS · 3Horizon Robotics +1
BA-T: An Iterative Transformer for Two-View Bundle Adjustment
Jun 2, 2026Ganlin Zhang, Weirong Chen, Daniel Cremers +1Multi-View Consistency 3D ViTs
TU Munich · MCML · ETH Zurich
FreeStreamGS: Online Feed-forward 3D Gaussian Splatting from Unposed Streaming Inputs
Jun 2, 2026Ruiyang Chen, Feiran Li, Chu Zhou +33D Gaussian Splatting Streaming 3D Reconstruction
Beijing University of Posts and Telecommunications, China · Independent Researcher · National Institute of Informatics, Japan
HumanNOVA: Photorealistic, Universal and Rapid 3D Human Avatar Modeling from a Single Image
Jun 1, 2026Hezhen Hu, Wangbo Zhao, Lanqing Guo +63D Avatar Generation 3D Shape Generation
University of Texas at Austin · National University of Singapore · Texas A&M University
$\text{VG}^2$ GT: Voxel-Gaussian Splatting Visual Geometry Grounded Transformer
Jun 1, 2026Yibin Zhao, Yihan Pan, Jun Nan +33D Gaussian Splatting Novel 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
ScaRF-SLAM: Scale-Consistent Reconstruction with Feed-Forward Models and Classical Visual SLAM
May 29, 2026Yuhao Zhang, Yifu Tao, Frank Dellaert +13D Reconstruction Visual SLAM
Oxford Robotics Institute, University of Oxford, UK · School of Interactive Computing, Georgia Institute of Technology, USA
Learning Global Motion with Compact Gaussians for Feed-Forward 4D Reconstruction
May 29, 2026Mungyeom Kim, Minkyeong Jeon, Honggyu An +10Point Tracking 3D Gaussian Splatting
KAIST AI · ETH Zürich, ETH AI Center · Sony AI +1
SurGe: Improved Surface Geometry in Point Maps
May 29, 2026Karim Knaebel, Gonzalo Martin Garcia, Christian Schmidt +43D Reconstruction Monocular 3D Reconstruction
RWTH Aachen University · Eindhoven University of Technology
Topologically Consistent Multi-view 3D Head Reconstruction via Coarse-Guided Layered Surface Sampling
May 29, 2026Timo Bolkart, Daoye Wang, Prashanth ChandranMulti-View 3D Reconstruction 3D Mesh Reconstruction
Google, Switzerland
QVGGT: Post-Training Quantized Visual Geometry Grounded Transformer
May 29, 2026Zhizhen Pan, Hesong Wang, Huan WangMixed-Precision Quantization 3D ViTs
Westlake University · Beijing University of Posts and Telecommunications
Déjà View: Looping Transformers for Multi-View 3D Reconstruction
May 28, 2026Alessandro Burzio, Tobias Fischer, Sven Elflein +9Multi-View 3D Reconstruction Recurrent Transformers
NVIDIA · University of Modena and Reggio Emilia, AImageLab · ETH Zürich +1
FRUC: Feedforward Dynamic Scene Reconstruction from Uncalibrated Collaborative Driving Views
May 28, 2026Yihang Tao, Yu Guo, Zhengru Fang +23D Gaussian Splatting 3D Reconstruction
Hong Kong JC STEM Lab of Smart City, City University of Hong Kong
G3T Up! Gravity Aligned Coordinate Frames Simplify Pointmap Processing
May 26, 2026Bharath Raj Nagoor Kani, Noah Snavely3D Reconstruction Camera Pose Estimation
Cornell University
DelowlightSplat: Feed-Forward Gaussian Splatting for Lowlight 3D Scene Reconstruction
May 26, 2026Fuzhen Jiang, Zengtian Xie, Zhuoran Li3D Gaussian Splatting 3D Reconstruction
Hangzhou Dianzi University · Hangzhou, China · Zhuhai College of Science and Technology +1
$R^3$ : 3D Reconstruction via Relative Regression
May 26, 2026Congrong Xu, Huachen Gao, Xingyu Chen +3Relative Pose Estimation Streaming 3D Reconstruction
University of Michigan · Westlake University · NVIDIA
Geometry-Aware Representation Denoising for Robust Multi-view 3D Reconstruction
May 25, 2026Jin Hyeon Kim, Jaeeun Lee, Claire Kim +8Diffusion Models for Image Restoration 3D Reconstruction
1KAIST AI · 2Samsung Electronics
TriSplat: Simulation-Ready Feed-Forward 3D Scene Reconstruction
May 25, 2026Weijie Wang, Zimu Li, Jinchuan Shi +53D Reconstruction Sparse-View 3D Reconstruction
Zhejiang University · ETH Zurich · ETH AI Center +2
Global Structure-from-Motion Meets Feedforward Reconstruction
May 25, 2026Linfei Pan, Johannes Schönberger, Marc PollefeysMulti-View 3D Reconstruction Camera Pose Estimation
ETH Zurich · Meta Reality Labs · ETH Zurich, Microsoft

Jun 19, 2026J/K move · Enter open · S save

SCOPE: Scale-Consistent One-Pass Estimation of 3D Geometry

Zheng Zhang, Lihe Yang, Tianyu Yang, Chaohui Yu+5

The University of Hong Kong, Hong Kong · Alibaba Group, Hong Kong · Alibaba Group, China+2

Streaming 3D Reconstruction 3D Reconstruction Monocular 3D Reconstruction 3D Scene Representation Feed-Forward 3D Reconstruction

Open paper AskPDF arXiv

We present SCOPE (Scale-Consistent One-Pass Estimation of 3D Geometry), a novel approach for estimating 3D geometry from extended monocular video sequences, where existing methods struggle to maintain both geometric accuracy and temporal consistency across hundreds of frames. Our approach generates affine-invariant 3D point maps with shared parameters across entire sequences, enabling consistent scale-invariant representations. We introduce three key innovations: viewpoint-invariant geometry aligning multi-perspective points in a unified reference frame; appearance-invariant learning enforcing consistency across exponential timescales; and frequency-modulated positioning enabling extrapolation to sequences vastly exceeding training length. Experiments across diverse datasets demonstrate significant improvements, reducing relative point map error by 24.2% and temporal alignment error by 34.9% on ScanNet compared to state-of-the-art methods. Our approach handles challenging scenarios with complex camera trajectories and lighting variations while efficiently processing extended sequences in a single pass. Project page: https://scope3d.github.io/.