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
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 ReconstructionInvSplat: Inverse Feed-Forward Scene Splatting
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 RenderingVisual Geometry Transformer in the Wild: Distractor-Free 3D Reconstruction
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 CloudsG-MASt3R-SfM: Graph-based View Pruning and Multi-stage Optimization for Robust SfM
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 Matching3D Consistency Optimization for Self-Supervised Monocular Video Depth Estimation
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 EstimationDéjà View: Looping Transformers for Multi-View 3D Reconstruction
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 ReconstructionGeometry-Aware Representation Denoising for Robust Multi-view 3D Reconstruction
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 ReconstructionGood Token Hunting: A Hitchhiker's Guide to Token Selection for Visual Geometry Transformers
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 ReconstructionTurboVGGT: Fast Visual Geometry Reconstruction with Adaptive Alternating Attention
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 EfficiencyDP-SfM: Dual-Pixel Structure-from-Motion without Scale Ambiguity
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 ReconstructionAirZoo: A Unified Large-Scale Dataset for Grounding Aerial Geometric 3D Vision
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 RetrievalRecGen3D: Reconstruction-Guided 3D Generation in a Shared Canonical Space
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 ReconstructionFisheye3R: Adapting Unified 3D Feed-Forward Foundation Models to Fisheye Lenses
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 ReconstructionReLi3D: Relightable Multi-view 3D Reconstruction with Disentangled Illumination
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 ReconstructionSegVGGT: Joint 3D Reconstruction and Instance Segmentation from Multi-View Images
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 CloudsUniScale: Unified Scale-Aware 3D Reconstruction for Multi-View Understanding via Prior Injection for Robotic Perception
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 ReconstructionS-MUSt3R: Sliding Multi-view 3D Reconstruction
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 NavigationDistill3R: A Pipeline for Democratizing 3D Foundation Models on Commodity Hardware
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 ReconstructionPPISP: Physically-Plausible Compensation and Control of Photometric Variations in Radiance Field Reconstruction
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 ReconstructionAgreement-Driven Multi-View 3D Reconstruction for Live Cattle Weight Estimation
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