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

F-RNG: Feed-Forward Relightable Neural Gaussians
May 25, 2026Guangming Fu, Jiahui Fan, Jian Yang +23D Gaussian Splatting 3D Reconstruction
Nankai University, China · Nanjing University, China · NVIDIA, USA
CodecSplat: Ultra-Compact Latent Coding for Feed-Forward 3D Gaussian Splatting
May 25, 2026Pengpeng Yu, Runqing Jiang, Qi Zhang +33DGS Compression 3D Gaussian Splatting
Sun Yat-sen University, China · Pengcheng Laboratory, China · Peking University, China
ArtSplat: Feed-Forward Articulated 3D Gaussian Splatting from Sparse Multi-State Uncalibrated Views
May 23, 2026Inseo Lee, Yoonji Kim, Eugene Sohn +4Articulated Object Reconstruction 3D Gaussian Splatting
1Seoul National University · 2Sogang University · 3NAVER AI Lab
LangFlash: Feed-forward 3D Language Gaussian Splatting from Sparse Unposed Images
May 22, 2026Yilong Liu, Wanhua Li, Chen Zhu-Tian +13D Gaussian Splatting Language-Embedded 3DGS
Harvard University · Tsinghua University · Nanyang Technological University +1
Diffusion-guided Generalizable Enhancer for Urban Scene Reconstruction
May 21, 2026Henry Che, Jingkang Wang, Yun Chen +33D Gaussian Splatting Diffusion Model Guidance
1Waabi · University of Illinois Urbana-Champaign · University of Toronto
No Pose, No Problem in 4D: Feed-Forward Dynamic Gaussians from Unposed Multi-View Videos
May 21, 2026Matteo Balice, Yanik Kunzi, Chenyangguang Zhang +33D Gaussian Splatting 4D Reconstruction
1Politecnico di Milano · 2ETH Zürich · 3ETH AI Center
ForeSplat: Optimization-Aware Foresight for Feed-Forward 3D Gaussian Splatting
May 21, 2026Yuke Li, Weihang Liu, Cheng Zhang +83D Gaussian Splatting Meta-Learning
ShanghaiTech University · GGU Technology Co., Ltd · Stereye
UniT: Unified Geometry Learning with Group Autoregressive Transformer
May 20, 2026Haotian Wang, Yusong Huang, Zhaonian Kuang +4Transformer Depth Estimation
Intelligent Transportation Thrust of the Systems Hub, The Hong Kong University of Science and Technology (GZ), Guangzhou, P.R.China. · The National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi’an Jiaotong University, Xi’an, P.R.China. · Applied Science, Amazon.com, Inc., USA.
Feed-Forward Gaussian Splatting from Sparse Aerial Views
May 19, 2026Dongli Wu, Zhuoxiao Li, Tongyan Hua +43D Gaussian Splatting 3D Reconstruction
1The Hong Kong University of Science and Technology (Guangzhou) · 2Peking University · 3The Ohio State University
Cross-View Splatter: Feed-Forward View Synthesis with Georeferenced Images
May 19, 2026Matias Turkulainen, Akshay Krishnan, Filippo Aleotti +63D Gaussian Splatting Novel View Synthesis
Aalto University · Niantic Spatial · Georgia Tech +3
Trust It or Not: Evidential Uncertainty for Feed-Forward 3D Reconstruction with Trust3R
May 19, 2026Zihao Zhu, Wenyuan Zhao, Nuo Chen +2Evidential Deep Learning 3D Reconstruction
Department of Electrical and Computer Engineering, Texas A&M University, College Station, TX, USA
Resolving Representation Ambiguity in Feedforward Novel View Synthesis Transformer via Semantic-Spatial Decoupling
May 18, 2026Yihang Wu, Yihang Sun, Shaofeng Zhang +4Disentangled Representation Learning Vision Transformer
Institute of Trustworthy Embodied Artificial Intelligence (TEAI), Fudan University · 3Sch. of Artificial Intelligence & Sch. of Computer Science, Shanghai Jiao Tong University · University of Science and Technology of China +1
UAVFF3D: A Geometry-Aware Benchmark for Feed-Forward UAV 3D Reconstruction
May 18, 2026Xiang Yang, Yongli Wang, HaiFeng Li +1Domain Adaptation 3D Reconstruction
aSchool of Geosciences and Info-Physics, Central South University, Changsha, China
Mamba-VGGT: Persistent Long-Sequence Video Geometry Grounded Transformer via External Sliding Window Mamba Memory
May 17, 2026Tianchen Deng, Zhenxiang Xiong, Nailin Wang +43D ViTs 3D Reconstruction
Shanghai Jiao Tong University · Nanyang Technological University · ETH Zurich +1
HAD: Hallucination-Aware Diffusion Priors for 3D Reconstruction
May 16, 2026Xi Liu, Weiwei Sun, Zhou Ren +33D Reconstruction Novel View Synthesis
1Amazon AWS · 2Clemson University
Not All Tasks Quantize Equally: Fisher-Guided Quantization for Visual Geometry Transformer
May 15, 2026Yipu Zhang, Jintao Cheng, Weilun Feng +5Feed-Forward 3D Reconstruction Post-Training Quantization
Department of Electronic and Computer Engineering, HKUST · State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences · University of Chinese Academy of Sciences +2
FFAvatar: Few-Shot, Feed-Forward, and Generalizable Avatar Reconstruction
May 14, 2026Thuan Hoang Nguyen, Jiahao Luo, Yinyu Nie +33D Gaussian Splatting 3D Reconstruction
Snap Inc. · MBZUAI · University of California, Santa Cruz
VGGT- $Ω$
May 14, 2026Jianyuan Wang, Minghao Chen, Shangzhan Zhang +7Multi-View 3D Reconstruction Dynamic Scene Reconstruction
1Visual Geometry Group, University of Oxford · 2Meta AI
VGGT-Edit: Feed-forward Native 3D Scene Editing with Residual Field Prediction
May 14, 2026Kaixin Zhu, Yiwen Tang, Yifan Yang +93D Shape Editing 3D Scene Editing
1Peking University · 2Tencent · 3The Chinese University of Hong Kong +4
Sat3DGen: Comprehensive Street-Level 3D Scene Generation from Single Satellite Image
May 14, 2026Ming Qian, Zimin Xia, Changkun Liu +6Remote Sensing 3D Scene Generation
LIESMARS & School of Artificial Intelligence, Wuhan University · EPFL · HKUST +4
TurboVGGT: Fast Visual Geometry Reconstruction with Adaptive Alternating Attention
May 14, 2026David Huang, Guile Wu, Chengjie Huang +23D ViTs Multi-View 3D Reconstruction
Huawei Noah’s Ark Lab · University of Toronto · Foundation Model Department, Huawei
LEXI-SG: Monocular 3D Scene Graph Mapping with Room-Guided Feed-Forward Reconstruction
May 13, 2026Christina Kassab, Hyeonjae Gil, Matías Mattamala +2Simultaneous Localization and Mapping Monocular 3D Reconstruction
Department of Engineering Science, University of Oxford, UK · Department of Mechanical Engineering, Seoul National University, South Korea · School of Informatics, University of Edinburgh, UK
RoSplat: Robust Feed-Forward Pixel-wise Gaussian Splatting for Varying Input Views and High-Resolution Rendering
May 13, 2026Hoang Chuong Nguyen, Renjie Wu, Jose M. Alvarez +13D Gaussian Splatting Novel View Synthesis
Australian National University · NVIDIA
OCH3R: Object-Centric Holistic 3D Reconstruction
May 13, 2026Yi Du, Yang You, Xiang Wan +13D ViTs 3D Reconstruction
Stanford University
PointForward: Feedforward Driving Reconstruction through Point-Aligned Representations
May 12, 2026Cheng Chi, Xianqi Wang, Hongcheng Luo +93D Reconstruction Multi-View 3D Reconstruction
Xiaomi EV · Huazhong University of Science and Technology · Zhejiang University
Lite3R: A Model-Agnostic Framework for Efficient Feed-Forward 3D Reconstruction
May 12, 2026Haoyu Zhang, Zeyu Zhang, Zedong Zhou +2Quantization-Aware Training 3D Reconstruction
1Peking University · 2La Trobe University
AdaptSplat: Adapting Vision Foundation Models for Feed-Forward 3D Gaussian Splatting
May 11, 2026Mingwei Xing, Xinliang Wang, Yifeng Shi3D Gaussian Splatting Vision Foundation Model Adaptation
Ke Holdings Inc.
ConFixGS: Learning to Fix Feedforward 3D Gaussian Splatting with Confidence-Aware Diffusion Priors in Driving Scenes
May 10, 2026Rui Song, Tianhui Cai, Markus Gross +53D Gaussian Splatting Diffusion Guidance
University of California, Los Angeles · Technical University of Munich · University of Cambridge
PrePARE: Pre-AA Token Pruning for Frozen Multi-View Geometry Transformers
May 8, 2026Haotang Li, Zhenyu Qi, Shaohan Henry Wang +5Multi-View Geometry Efficient ViTs
University of Arizona · East Carolina University · Augusta University +1
Seeing Across Skies and Streets: Feedforward 3D Reconstruction from Satellite, Drone, and Ground Images
May 8, 2026Qiwei Wang, Zhongyao Tuo, Xianghui Ze +1Relative Pose Estimation Cross-View Geo-Localization
ShanghaiTech University Shanghai, China · Nanjing University of Science and Technology Nanjing, China

May 25, 2026J/K move · Enter open · S save

F-RNG: Feed-Forward Relightable Neural Gaussians

Guangming Fu, Jiahui Fan, Jian Yang, Miloš Hašan+1

Nankai University, China · Nanjing University, China · NVIDIA, USA

3D Gaussian Splatting 3D Reconstruction Neural Rendering Sparse-View 3D Reconstruction Image Relighting Feed-Forward 3D Reconstruction

Open paper AskPDF arXiv

Capturing relightable 3D assets from real-world objects is a widely researched problem. Several per-scene optimization-based methods, based on 3D Gaussian splatting (3DGS), support relighting; however, they usually require dense input views, and their overfitting nature makes it difficult to generalize across scenes. Unlike per-scene optimization methods, generalized feed-forward models can directly reconstruct Gaussians from sparse input views. However, the resulting assets have baked-in illumination and cannot be easily used for relighting. In this paper, we present F-RNG, a feed-forward framework that directly generates relightable 3DGS assets from sparse-view inputs. Training such a model from scratch can require massive data and computing resources, and it is especially challenging to generate relightable assets in a feed-forward manner with acceptable cost. We develop F-RNG upon an existing large reconstruction model (LRM) to extract relightable representations, while also utilizing priors from an intrinsic decomposition model (IDM). Specifically, we first introduce a latent-interpolated fine-grained geometry synthesis to enhance the LRM's geometry representation. Second, we propose a prior-guided relightable appearance distillation to extract relightable neural representations by incorporating IDM priors. Finally, a universal neural renderer enables flexible and high-fidelity relighting. F-RNG requires neither re-training nor fine-tuning of the underlying LRMs, thus can automatically benefit from better LRMs and IDMs in the future. With only small networks that can be trained with affordable data and computational resources, F-RNG avoids the repetitive inference of large models under different light conditions. By comparison to the state-of-the-art LRM-based relighting method, F-RNG achieves ~~25x faster relighting, as well as superior quality (~~+2.0 dB).