paper-with-me

3D Reconstruction

10개 벤치마크 · 논문 3,177편 · 이 태스크의 논문 보기 →

Benchmarks

DTU

결과 48개

ShapeNet

결과 16개

Data3D−R2N2

결과 8개

Scan2CAD

결과 4개

300W

결과 2개

3DPeople

결과 2개

ApolloCar3D

결과 2개

ScanNet

결과 2개

Most implemented

The Double Sphere Camera Model

2018-07-24 · 구현 9개

Papers

Shape-guided Gaussian Splatting for Sparse-View X-ray 3D Reconstruction

2026-09-09 · Pranav Poudel, Florence Dell'Aniello Picard, Nairouz Shehata, Frédéric Lavoie 외 arxiv

Sparse-view X-ray 3D reconstruction is essential for reducing radiation exposure, but recovering a density field from a handful of X-ray projections is severely ill-posed. Recently, 3D Gaussian Splatting has achieved sta…

3D Reconstruction

KODAMA: Multimodal Digital Twin Reconstruction for Urban RF Propagation Modelling

2026-09-07 · Maximiliano Wardle, A. Ryo Koblitz arxiv

3D reconstruction typically strives for geometric fidelity or visual plausibility. Radio frequency digital twins (RFDT) are instead judged by whether communication channels behave in them as they do in the real world. RF…

3D Reconstruction

BLASt3R: Bundle Adjustment of Any Image Set with Multi-View Matching and Monocular Priors

2026-09-04 · Vincent Leroy, Philippe Weinzaepfel, Lojze Zust, Yohann Cabon 외 arxiv

Recent hybrid Structure-from-Motion (SfM) systems combine the robustness of feed-forward 3D reconstruction with the accuracy of traditional bundle adjustment (BA) with pixel matching. They are usually the best performing…

3D Reconstruction

HiSfM: Disambiguating Structure-from-Motion via Scaffold-Anchored Hierarchical Reconstruction

2026-09-04 · Ziding Zhao, Hainan Cui, Peilin Tao, Shuhan Shen arxiv

Structure-from-Motion (SfM) is a fundamental tool for sparse 3D reconstruction with broad impact in robotics and vision, supporting mapping, localization, and large-scale scene modeling. However, conventional pipelines o…

3D Reconstruction

Scal3R: Learning Efficient Multi-Relative Pose Query for Scalable Online 3D Reconstruction

2026-09-03 · Chin-Yang Lin, Yang-Che Sun, Cheng Sun, Fu-En Yang 외 hf

Online 3D reconstruction models perform poorly on long videos. This happens because regressing poses relative to a fixed first-frame anchor forces extrapolation far beyond the training distribution. Small drifts accumula…

3D Reconstruction

ENEAS: Embedding-guided Neural Ensemble for Adaptive Segmentation

2026-09-03 · Javier del Pino, Salvador Rodríguez, Alejandro Garabito, Javier Álvarez 외 hf

We present ENEAS, a unified, text-promptable method for instance tracking and semantic discovery. Text-promptable segmentation models, including the latest foundation models such as SAM 3, still suffer from temporal hall…

3D Reconstruction

전체 3,177편 보기 →