paper-with-me

Papers Multi-View 3D Reconstruction

“Multi-View 3D Reconstruction” 태그가 달린 논문 89편 · 필터 해제

Learning Spherical Occupancy Profiles for Multi-View 3D Reconstruction and Generation

2026-08-24 · YiHsuan Tsai arxiv

We study spherical occupancy profiles-the ray-wise occupancy probability profiles P(r) = T(r) o(r) distilled from multi-view 3D Gaussian reconstructions-as a unified intermediate representation for both discriminative an…

Multi-View 3D Reconstruction

InvSplat: Inverse Feed-Forward Scene Splatting

2026-07-02 · Polina Karpikova, Wenjing Bian, Haofei Xu, Hendrik Lensch 외 arxiv

Inverse rendering aims to recover both 3D geometry and physically meaningful material properties from images, enabling applications such as relighting and novel view synthesis. Optimization-based methods achieve high fid…

Multi-View 3D ReconstructionNovel View SynthesisInverse Rendering

Visual Geometry Transformer in the Wild: Distractor-Free 3D Reconstruction

2026-06-22 · Tianbo Pan, Xingyi Yang, Shizun Wang, Xinchao Wang arxiv

Current end-to-end multi-view 3D reconstruction methods achieve impressive results, but rely on a restrictive static assumption: the scenes is entire distractor-free with perfect cross-view geometry. This reliance on ide…

Multi-View 3D ReconstructionPoint Clouds

G-MASt3R-SfM: Graph-based View Pruning and Multi-stage Optimization for Robust SfM

2026-06-22 · Toshiki Watanabe, Shintaro Ito, Natsuki Takama, Koichi Ito 외 arxiv

Structure from Motion (SfM) is essential for multi-view 3D reconstruction, however, its accuracy heavily relies on the accuracy of image matching. While the recent correspondence matching method, MASt3R, enables robust m…

Multi-View 3D ReconstructionCamera Pose EstimationImage Matching

3D Consistency Optimization for Self-Supervised Monocular Video Depth Estimation

2026-06-14 · Yuanye Liu, Ke Zhang, Junzhe Jiang, Li Zhang 외 arxiv

Reliable monocular video depth estimation is crucial for downstream 3D reasoning and embodied AI in endoscopic navigation. However, existing self-supervised approaches typically treat video frames independently or rely o…

Multi-View 3D ReconstructionDepth Estimation

Déjà View: Looping Transformers for Multi-View 3D Reconstruction

2026-05-28 · Alessandro Burzio, Tobias Fischer, Sven Elflein, Qunjie Zhou 외 arxiv

Recent feed-forward 3D reconstruction transformers have scaled to over a billion parameters, following the broader trend of increasing model capacity in computer vision. Yet emerging evidence suggests that contiguous tra…

Multi-View 3D Reconstruction

Geometry-Aware Representation Denoising for Robust Multi-view 3D Reconstruction

2026-05-25 · Jin Hyeon Kim, Jaeeun Lee, Claire Kim, Kyoungjin Oh 외 arxiv

Multi-view 3D reconstruction has achieved remarkable progress with the advent of feed-forward 3D reconstruction models. However, these models are typically trained and evaluated under ideal, degradation-free imaging cond…

Multi-View 3D Reconstruction

Good Token Hunting: A Hitchhiker's Guide to Token Selection for Visual Geometry Transformers

2026-05-22 · Shuhong Zheng, Michael Oechsle, Erik Sandström, Marie-Julie Rakotosaona 외 arxiv

Visual geometry transformers have become powerful architectures for multi-view 3D reconstruction, enabling joint prediction of multiple 3D attributes in a feed-forward manner. However, their computational cost grows quad…

Multi-View 3D Reconstruction

TurboVGGT: Fast Visual Geometry Reconstruction with Adaptive Alternating Attention

2026-05-14 · David Huang, Guile Wu, Chengjie Huang, Bingbing Liu 외 arxiv

Recent feed-forward 3D reconstruction methods, such as visual geometry transformers, have substantially advanced the traditional per-scene optimization paradigm by enabling effective multi-view reconstruction in a single…

Multi-View 3D ReconstructionComputational Efficiency

DP-SfM: Dual-Pixel Structure-from-Motion without Scale Ambiguity

2026-05-03 · Lilika Makabe, Kohei Ashida, Hiroaki Santo, Fumio Okura 외 arxiv

Multi-view 3D reconstruction, namely, structure-from-motion followed by multi-view stereo, is a fundamental component of 3D computer vision. In general, multi-view 3D reconstruction suffers from an unknown scale ambiguit…

Multi-View 3D Reconstruction

AirZoo: A Unified Large-Scale Dataset for Grounding Aerial Geometric 3D Vision

2026-04-29 · Xiaoya Cheng, Rouwan Wu, Xinyi Liu, Zeyu Cui 외 arxiv

Despite the rapid progress in data-driven 3D vision, aerial geometric 3D vision remains a formidable challenge due to the severe scarcity of large-scale, high-fidelity training data. Existing benchmarks, predominantly bi…

Multi-View 3D ReconstructionImage Retrieval

RecGen3D: Reconstruction-Guided 3D Generation in a Shared Canonical Space

2026-04-01 · Zhisheng Huang, Jiahao Chen, Cheng Lin, Chenyu Hu 외 arxiv

Sparse-view 3D modeling represents a fundamental tension between reconstruction fidelity and generative plausibility. While feed-forward reconstruction excels in efficiency and input alignment, it often lacks the global …

Multi-View 3D Reconstruction

Fisheye3R: Adapting Unified 3D Feed-Forward Foundation Models to Fisheye Lenses

2026-03-30 · Ruxiao Duan, Erin Hong, Dongxu Zhao, Eric Turner 외 arxiv

Feed-forward foundation models for multi-view 3-dimensional (3D) reconstruction have been trained on large-scale datasets of perspective images; when tested on wide field-of-view images, e.g., from a fisheye camera, thei…

Multi-View 3D Reconstruction

ReLi3D: Relightable Multi-view 3D Reconstruction with Disentangled Illumination

2026-03-20 · Jan-Niklas Dihlmann, Mark Boss, Simon Donne, Andreas Engelhardt 외 arxiv

Reconstructing 3D assets from images has long required separate pipelines for geometry reconstruction, material estimation, and illumination recovery, each with distinct limitations and computational overhead. We present…

Multi-View 3D Reconstruction

SegVGGT: Joint 3D Reconstruction and Instance Segmentation from Multi-View Images

2026-03-20 · Jinyuan Qu, Hongyang Li, Lei Zhang arxiv

3D instance segmentation methods typically rely on high-quality point clouds or posed RGB-D scans, requiring complex multi-stage processing pipelines, and are highly sensitive to reconstruction noise. While recent feed-f…

Multi-View 3D Reconstruction3D Instance SegmentationPoint Clouds

UniScale: Unified Scale-Aware 3D Reconstruction for Multi-View Understanding via Prior Injection for Robotic Perception

2026-02-26 · Mohammad Mahdavian, Gordon Tan, Binbin Xu, Yuan Ren 외 arxiv

We present UniScale, a unified, scale-aware multi-view 3D reconstruction framework for robotic applications that flexibly integrates geometric priors through a modular, semantically informed design. In vision-based robot…

Multi-View 3D Reconstruction

S-MUSt3R: Sliding Multi-view 3D Reconstruction

2026-02-04 · Leonid Antsfeld, Boris Chidlovskii, Yohann Cabon, Vincent Leroy 외 arxiv

The recent paradigm shift in 3D vision led to the rise of foundation models with remarkable capabilities in 3D perception from uncalibrated images. However, extending these models to large-scale RGB stream 3D reconstruct…

Multi-View 3D ReconstructionRobot Navigation

Distill3R: A Pipeline for Democratizing 3D Foundation Models on Commodity Hardware

2026-01-31 · Brandon Leblanc, Charalambos Poullis arxiv

While multi-view 3D reconstruction has shifted toward large-scale foundation models capable of inferring globally consistent geometry, their reliance on massive computational clusters for training has created a significa…

Multi-View 3D Reconstruction

PPISP: Physically-Plausible Compensation and Control of Photometric Variations in Radiance Field Reconstruction

2026-01-26 · Isaac Deutsch, Nicolas Moënne-Loccoz, Gavriel State, Zan Gojcic arxiv

Multi-view 3D reconstruction methods remain highly sensitive to photometric inconsistencies arising from camera optical characteristics and variations in image signal processing (ISP). Existing mitigation strategies such…

Multi-View 3D Reconstruction

Agreement-Driven Multi-View 3D Reconstruction for Live Cattle Weight Estimation

2026-01-25 · Rabin Dulal, Wenfeng Jia, Lihong Zheng, Jane Quinn arxiv

Accurate cattle live weight estimation is vital for livestock management, welfare, and productivity. Traditional methods, such as manual weighing using a walk-over weighing system or proximate measurements using body con…

Multi-View 3D Reconstruction3D Generation
1–20 / 89 다음 →