method · first seen 5 Oct 2026
feed-forward 3D reconstruction
Also: feed-forward reconstruction
Predicting 3D scene geometry such as point maps directly in one forward pass without optimization.
Feed-forward 3D reconstruction trains a network across many scenes so that it outputs geometry, such as point maps or pixel-aligned 3D Gaussians, in a single pass instead of running per-scene optimization or classical structure-from-motion. The sources are almost all arXiv papers, and they treat the large pre-trained reconstruction models as a base to build on. Some adapt them to new domains: lunar rover imagery, thermal cameras, ultrasound, non-perspective cameras and hand avatars. Others address their weak points, including uncertainty estimation, sparse-view holes, scale normalization, interactive correction from user clicks and parameter-efficient adaptation. A Google-affiliated paper calls it a prominent research direction, and one GitHub repo implements a variant of the feed-forward Gaussian splatting approach.
If these models stay reliable across domains, they could replace slow optimization-based pipelines in robotics, medical imaging and VLM spatial reasoning, where geometry is needed in near real time. The current work on uncertainty and correction suggests the field is moving from benchmark results toward deployment.
Analyst note (emerging), 17 Nov 2026.
Mentions per week
PapersCodeDiscussion
Rank 19 on 16 Nov 2026 · 21 mentions in 28 days · 21 independent groups · papers → code · first seen 6 weeks ago · acceleration +0.16
Earliest sources
- MoonGS: High-quality Representation of the Lunar Surface via Gaussian Splatting Using Robust Depth Features from Image PairsPapers · 5 Oct 2026 · Yun Jiang, Bo Zheng, Yingying Zhang, Xueming Xiao, Tao Hu, Hutao Cui, Zhiguo Men…
- ReVar3R: Gauge-Aware Perturbation Uncertainty for Feed-Forward 3D ReconstructionPapers · 6 Oct 2026 · Sammam Mahdi, Fariha Binta Salim, Rakin Bin Rabbani, Aniqua Nusrat Zereen
- DensiTok: Making Feed-Forward 3D Gaussian Splatting See More Views Than It Is GivenPapers · 6 Oct 2026 · Minhyeok Lee, Jungho Lee, Minseok Kang, Heeseung Choi, Ig-Jae Kim, Sangyoun Lee
- MvFFN: Multi-view Floor plan Feed-forward Network for Unposed Wide-Baseline Panorama Layout ReconstructionPapers · 9 Oct 2026 · Yuguang Li, Yichuan Deng, Zixuan Liu, Ivaylo Boyadzhiev, Xiuyuan Wu, Xinyu Zou,…
- PURE: Refining Feed-forward 3D Reconstruction with Unlabeled Post-trainingPapers · 10 Oct 2026 · Yaolong Zhu, Peng Li, Jiahao Lu, Chengfeng Zhao, Mengfei Li, Chao Wang, Wenyue C…
- Sharper Frames, Worse Rooms: Viewpoint Coverage Dominates Image Quality in Feed-Forward 3D ReconstructionPapers · 11 Oct 2026 · Alibek Dadajonov, Hikmatillo Umarhojiyev
Latest sources
- Déjà-Events: Multi-view 3D Geometry with Event Cameras via Sparsity-Aware Adaptive GatingPapers · 16 Nov 2026 · Arda Cinar Demirtas, Pablo Varela Bernal, Marc Pollefeys, Sunghwan Hong
- SpaceMCP: Vision Language Model Spatial Reasoning via Model Context ProtocolPapers · 11 Nov 2026 · Ameen Izhac, Nobuko Yoshida, Ronald Clark
- ThermalSplat: Generalizable Pose-Free Gaussian Splatting for Sparse-View Thermal 3D ReconstructionPapers · 11 Nov 2026 · Prasanna S, Gopi Raju Matta, Divya Madhuri Vemunuri, Kaushik Mitra
- Camera3R: Feed-Forward 3D Reconstruction from Heterogeneous Camera ModelsPapers · 10 Nov 2026 · Ruxiao Duan, Yunwen Zhou, Erin Hong, Dongxu Zhao, Eric Turner, Federico Tombari,…
- Click3R: Interactive Stereo 3D Reconstruction with Sparse Correspondence ClicksPapers · 9 Nov 2026 · Hao Gu, Jin Yao, Zezhou Cheng
- 3R-Adapter: Retrieval, Rewiring, and Refinement for Efficient Adaptation of 3D Reconstruction ModelPapers · 9 Nov 2026 · Zixiang Ai, Zhenyu Cui, Xu Zou, Jiahuan Zhou
- UltraVoxelGS: Voxel-First Feed-Forward Gaussian Splatting for 3D Ultrasound ReconstructionPapers · 9 Nov 2026 · Yue Wang, Haoxin Chen, Xiaoqing Guo
- OfficeTwin: Realizing 3D Reconstruction of Redundant Scenes through Partial Viewpoint PerceptionPapers · 6 Nov 2026 · Quanyun Wu, Kyle Gao, Daisy Li, Kshitij Goyal, Dayou Mao, David A. Clausi, Jonat…
- InstantHand: Feed-Forward 3D Gaussian Splatting for Animatable Hand Avatar Reconstruction from a Single ImagePapers · 5 Nov 2026 · Chanho Kim, Muhammad Salman Ali, Kyeonghwan Gwak, Muhammad Shaheryar, Incheol Pa…
- SplatAnything: Gaussian Spacing Normalization for Feed-forward 3DGS across Arbitrary ScenesPapers · 5 Nov 2026 · Hao Yu, Zhenwei Wang, Yongzhen Hu, Yuning Gong, Junta Wu, Xiaowei Zhou, Hujun Ba…
- Georeferenced Cross-View 3D Reconstruction from Ground and Satellite ImagesPapers · 5 Nov 2026 · David G. Shatwell, Mubarak Shah
- CrossPressor: Scalable Cross-View Fusion for Feed-Forward 3D Gaussian SplattingPapers · 4 Nov 2026 · Yuxi Hu, Wenhao Dong, Jun Zhang, Friedrich Fraundorfer