3D Priors

Follow this topic Ask about this topic

Momentum

5 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 37

All topics

DecomVoxel: Harnessing 3D-Native Priors with Guided In-situ Denoising Optimization for Decompositional Scene Reconstruction
Oct 1, 2026Junfeng Ni, Zirui Zhou, Yixin Chen +5Scene Reconstruction Voxel
Tsinghua University, State Key Laboratory of General Artificial Intelligence, BIGAI, China · Peking University, China
Pow3R-SLAM: Real-Time RGB-D SLAM with 3D Reconstruction Priors
Sep 29, 2026Christopher Kolios, Ishaan Mehta, Sasa Janjic +2Orb-Slam2 Simultaneous Localization And Mapping
Toronto Metropolitan University, Toronto, Canada. · University of Windsor, Windsor, Canada. · University College London, London, United Kingdom.
LEGAU: Learning Semantic Gaussian Priors for Scalable Category-level Pose Estimation
Sep 28, 2026Hongli Xu, Zhaowei Lu, Junwen Huang +5Category-Level Object Pose Estimation 3D Priors
Technical University of Munich Munich, Germany · Munich Center for Machine Learning Munich, Germany · Siemens AG Munich, Germany +1
FAMOS: Feed-Forward 3D Articulation Modeling from Sparse Observations
Sep 17, 2026Kevin Qu, Tao Sun, Massimiliano Viola +53D Models Motion Model
Stanford University · ETH Zürich
PriorPose: Reference-Guided Joint Deformation and Alignment for Category-Level Object Pose Estimation
Sep 15, 2026Yihan Chen, Huan Ren, Wenfei Yang +3Category-Level Object Pose Estimation 3D Priors
School of Information Science and Technology / National Key Laboratory of Deep Space Exploration, University of Science and Technology of China · Beijing Institute of Control Engineering
Evaluating 2D and 3D-Aware Vision Foundation Models for Vehicle Attribute Recognition
Aug 30, 2026Alexandre V. Delazeri, Gabriel E. Lima, Eduil Nascimento +2Automotive Detection Vision Foundation Models
Department of Informatics, Federal University of Paraná, Curitiba, Brazil · Department of Technological Development and Quality, Paraná Military Police, Curitiba, Brazil · Graduate Program in Informatics, Pontifical Catholic University of Paraná, Curitiba, Brazil
RayLift: Lifting Complementary Ray-Wise Evidence with 3D Geometry Priors for Semantic Scene Completion
Aug 9, 2026Meng Wang, Hongxia Yu, Wenzhe He +43D Priors Voxel
College of Computer Science and Electronic Engineering,Hunan University,Changsha,China
VR3D: View-Robust 3D Representation Learning for Aerial-Ground Person Re-Identification
Aug 3, 2026Chao Ji, Shiyu Xuan, Zechao Li3D Priors 3D Generation
School of Computer Science and Engineering, Nanjing University of Science and Technology
QuerySplat: Decoupling Geometry and Appearance Representations in 3DGS Prediction
Aug 2, 2026Yinglong Li, Donghui Shen, Xiaoyu Zhang +5Feed-Forward 3D Gaussian Splatting 3D Priors
State Key Laboratory of Virtual Reality Technology and Systems, Beihang University · InSpatio Research · State Key Lab of CAD&CG, Zhejiang University
Learning to Predict Contact Force Distributions from Vision Leveraging Object Geometry Priors
Aug 1, 2026Ryo Hanai, Yukiyasu Domaea, Ixchel G. Ramirez-Alpizar +3Force Rigid-Body Dynamics
Artificial Intelligence Research Center, National Institute of Advanced Industrial Science and Technology (AIST), Tokyo, Japan · Intelligent Systems Research Institute, National Institute of Advanced Industrial Science and Technology (AIST), Tokyo, Japan · Institute of AI and Robotics, Graduate School of Fundamental Science and Engineering, Waseda University, Tokyo, Japan
SAM3D-Guided Object-Centric Representation Alignment for Vision-Language-Action Models
Jul 28, 2026Zonghe Liu, Shanyuan Jie, Xiaoquan Sun +4Diffusion-Based Vision-Language-Actions Robotic Manipulation
University of Hong Kong · Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences · Huazhong University of Science and Technology +2
Latent Riemannian Flow Matching for Geometry-Grounded 3D Foundation Models
Jul 21, 2026Lisa Weijler, Irene Ballester, Guofeng Mei +23D Foundation Models Riemannian Flow Matching
TU Wien · Fondazione Bruno Kessler · Imperial College London
Repairing Shape-Prior Shortcuts in Long-Range Single-Shot Fringe Projection Profilometry
Jul 10, 2026Adam Haroon, Cody Fleming, Beiwen LiPixel-Level Prediction 3D Priors
Department of Mechanical Engineering, Iowa State University, 2529 Union Drive, Ames, 50011, Iowa, USA · College of Engineering, University of Georgia, 597 D. W. Brooks Drive, Athens, 30602, Georgia, USA
Vitality-Aware Compression for Efficient Image-to-Shape Diffusion Transformers
Jul 1, 2026Jaeah Lee, Hyunjin Kim, Jaewoong Cho +13D Generative Models Diffusion Transformers
KRAFTON AI, Republic of Korea · Amazon, Australia
WarpHammer: Densifying Scene Warps with 3D Object Priors for Extreme View Synthesis
Jun 30, 2026Michael Green, Gavriel Habib, Dvir Samuel +4Novel View Synthesis 3D Reconstruction
1OriginAI, Israel · 2NVIDIA · 3Technion
Articulating then Matching: Zero-Shot Shape Matching for Uncurated Data
Jun 28, 2026Qilong Liu, Qinfeng Xiao, Chenyuan Yi +2Shape Correspondence 3D Priors
Hong Kong Polytechnic University, HK SAR · Artificial Intelligence in Design, HK SAR
PSP: Harnessing Position and Shape Priors for Cross-Domain Few-Shot Medical Image Segmentation
Jun 27, 2026Bin Xu, Yazhou Zhu, Haofeng ZhangSemi-Supervised Medical Image Segmentation Medical Imaging Datasets
School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, China.
Scene-Level Heterogeneous Physics Simulation with 3D Gaussian Splats
Jun 19, 2026Xiaoyang Liu, Shangzhe Wu, Kai Han3D Assets Physics Simulation
1The University of Hong Kong · University of Cambridge
Diagnosing Shape-Prior Shortcuts in Long-Range Single-Shot Fringe Projection Profilometry
Jun 13, 2026Adam Haroon, Anush Lakshman, Cody Fleming +1Vision-Language Reprojection Consistency 3D Priors
Department of Mechanical Engineering, Iowa State University, 2529 Union Drive, Ames, 50011, Iowa, USA · College of Engineering, University of Georgia, 597 D. W. Brooks Drive, Athens, 30602, Georgia, USA
GraspFoM: Towards Reconstruction-Driven Robotic Grasping with 3D Foundation Priors
Jun 7, 2026Dongli Wu, Xiaobao Wei, Hao Wang +5Robotic Grasping 3D Priors
1The Hong Kong University of Science and Technology (Guangzhou) · 2Peking University · 3The Hong Kong University of Science and Technology
3DThinkVLA: Endowing Vision-Language-Action Models with Latent 3D Priors via 3D-Thinking-Guided Co-training
Jun 3, 2026Jiaxin Shi, Xidong Zhang, Fucai Zhu +33D Spatial Reasoning 3D Priors
Shanghai Jiao Tong University · Daimon Robotics · Harbin Institute of Technology +4
Generative Diffusion Priors for 3D Mapping of the Dark Universe
May 30, 2026Brandon Zhao, Diana Scognamiglio, Olivier Doré +1Cosmology Diffusion Priors
Department of Computing and Mathematical Sciences, California Institute of Technology · Jet Propulsion Laboratory, California Institute of Technology · Department of Physics, Duke University +1
CoMo3R-SLAM: Collaborative Monocular Dense SLAM with Learned 3D Reconstruction Priors for Outdoor Multi-Agent Systems
May 28, 2026Zhihao Cao, Qi Shao, Shuhao Zhai +4Orb-Slam2 Simultaneous Localization And Mapping
ETH Zurich, Switzerland · Harbin Engineering University, China · University of Liverpool, United Kingdom +4
Beyond 3D VQAs: Injecting 3D Spatial Priors into Vision-Language Models for Enhanced Geometric Reasoning
May 28, 2026Chun-Hsiao Yeh, Shengyi Qian, Manchen Wang +33D Spatial Reasoning Spatial Reasoning
FAIR at Meta · UC Berkeley · HKU
Geometry Matters: 3D Foundation Priors for Learning Semantic Correspondence
May 28, 2026Artur Jesslen, Olaf Dünkel, Adam Kortylewski3D Priors 3D Foundation Models
University of Freiburg, Germany · Max Planck Institute for Informatics, Saarland Informatics Campus, Germany · CISPA Helmholtz Center for Information Security, Germany
ParCo-SDF: Learning Prior-Free Partial-to-Complete Signed Distance Fields of Deformable Objects
May 28, 2026Deokmin Hwang, Minseok Song, Daehyung ParkGeometric Reconstruction Continuous Distance Field
School of Computing, Korea Advanced Institute of Science and Technology, Korea
Category-Level 3D Correspondence in Camera Space via Morphable Object Priors
May 27, 2026Leonhard Sommer, Artur Jesslen, Basavaraj Sunagad +13D Scene Understanding Shape Correspondence
University of Freiburg, Germany · CISPA Helmholtz Center for Information Security, Germany
DinoComplete: 3D Shape Completion with Distilled Semantic Priors and State Space Models
May 26, 2026Furkan Mert Algan, Eckehard Steinbach3D Priors Dino
Chair of Media Technology · Munich Institute of Robotics and Machine Intelligence · School of Computation Information and Technology, Technical University of Munich
ComPose: A Unified Completion-Pose Framework for Robust Category-Level Object Pose Estimation
May 25, 2026Huan Ren, Yihan Chen, Chuxin Wang +3Category-Level Object Pose Estimation Object Geometry
University of Science and Technology of China · 2National Key Laboratory of Deep Space Exploration, Deep Space Exploration Laboratory · 3Beijing Institute of Control Engineering
Echo4DIR: 4D Implicit Heart Reconstruction from 2D Echocardiography Videos
May 21, 2026Yanan Liu, Qinya Li, Hao Zhang +5End-To-End 4D Heart Mesh Recovery Across Full-Stack Echocardiography
Department of Biomedical Engineering, National University of Singapore, Singapore · School of Information Science and Engineering, Yunnan University, Kunming, China
Evaluation of Anatomical Shape Priors in Deep Learning-Based Cardiac Multi-Compartment Segmentation
May 15, 2026Michael Hudler, Franz Thaler, Martin UrschlerEchocardiography Anatomical Priors
Institute for Medical Informatics, Statistics and Documentation Medical University of Graz
Reconstruction by Generation: 3D Multi-Object Scene Reconstruction from Sparse Observations
Apr 29, 2026Andrii Zadaianchuk, Leonardo Barcellona, Lennard Schuenemann +73D Reconstruction 3D Priors
University of Amsterdam · KU Leuven · Toyota Research Institute +1
Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding
Mar 19, 2026Xianjin Wu, Dingkang Liang, Tianrui Feng +5Generative Video Models 3D Priors
Huazhong University of Science and Technology, China · Baidu Inc., China
Beyond Inpainting: Unleash 3D Understanding for Stable Camera-Controlled Video Generation
Jan 15, 2026Dong-Yu Chen, Yixin Guo, Shuojin Yang +2Camera Control Video Generation
BNRist, Department of Computer Science and Technology, Tsinghua University Beijing 100084, China
Higher order PCA-like rotation-invariant features for detailed shape descriptors modulo rotation
Jan 6, 2026Jarek DudaStatistical Shape Model Principal Component Analysis
Jagiellonian University, Krakow, Poland
DisCo3D: Distilling Multi-View Consistency for 3D Scene Editing
Aug 3, 2025Yufeng Chi, Huimin Ma, Kafeng Wang +13D Editing Diffusion-Based Image Editing
Institute for Artificial Intelligence, Beijing National Research Center for Information Science and Technology, Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China · College of Computer, National University of Defense Technology, Changsha 410073, China
SEGA: Drivable 3D Gaussian Head Avatar from a Single Image
Apr 19, 2025Chen Guo, Zhuo Su, Liao Wang +8Animatable 3D Human Avatars 3D Gaussian
Tsinghua Shenzhen International Graduate School, China · ByteDance and Pengcheng Lab, China · ByteDance, China +1

Oct 1, 2026, cs.CVJ/K move · Enter open · S save

DecomVoxel: Harnessing 3D-Native Priors with Guided In-situ Denoising Optimization for Decompositional Scene Reconstruction

Junfeng Ni, Zirui Zhou, Yixin Chen, Yu Liu+4

Tsinghua University, State Key Laboratory of General Artificial Intelligence, BIGAI, China · Peking University, China

Scene Reconstruction Voxel 3D Priors Completion Dataset Distillation Guidance

Open paper AskPDF arXiv

Decompositional scene reconstruction aims to reconstruct high-quality objects and background, yet existing methods still struggle with the level of quality under heavy occlusions. While generative priors offer a potential solution, 2D image-based priors often suffer from multi-view inconsistency due to a lack of 3D awareness. Conversely, 3D-native priors provide stronger structural inductive biases but frequently lead to spatial drift and misalignment within complex scenes. To address these issues, we propose DecomVoxel, formulating object completion as a guided in-situ denoising optimization that bridges 3D-native priors with neural scene reconstruction. Our framework introduces a reformulated epsilon-based distillation loss to ensure stable latent refinement, alongside adaptive spatial guidance that utilizes occupied and vacant anchors with temporal annealing to suppress generative hallucinations and mitigate spatial drift. Experiments on Replica and ScanNet++ show that DecomVoxel significantly outperforms state-of-the-art methods while faithfully preserving the original spatial layout, structural fidelity, and style-consistent texture. Our method pushes the boundary of decompositional reconstruction by delivering high-quality textured meshes with clean topology, geometry, and appearance, providing a robust solution for the decompositional reconstruction of complex real-world scenes. Code is available at https://github.com/DecomVoxel/DecomVoxel.

Momentum

Related topics

Latest papers 37