CasaMaestro predicts metric depth and poses from sparse multi-view panoramas to enable fast house-scale 3D reconstruction.
In: Proceedings of the IEEE/CVF Confer- ence on Computer Vision and Pattern Recognition (2025)
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 2
method 2
citation-polarity summary
fields
cs.CV 9verdicts
UNVERDICTED 9representative citing papers
AsyncEvGS reconstructs high-fidelity 3D scenes from motion-blurred images by first deblurring via event data then using VGGT-based pose estimation and structure-driven losses inside Gaussian Splatting.
Free Geometry enables test-time self-improvement of 3D reconstruction models via cross-view consistency between full and masked observations, yielding average gains of 3.73% in pose accuracy and 2.88% in point maps.
ReplicateAnyScene performs fully automated zero-shot video-to-compositional-3D reconstruction by cascading alignments of generic priors from vision foundation models across textual, visual, and spatial dimensions.
SpectralSplat disentangles appearance from geometry in feed-forward 3D Gaussian Splatting by factoring color into base and adapted streams conditioned on DINOv2 embeddings, trained on paired data from a hybrid relighting pipeline.
Distillation of a 688M-parameter MASt3R teacher yields up to 7x smaller students that retain most lunar reconstruction accuracy and outperform sparse-supervised baselines.
SyncFix improves 3D reconstructions by synchronizing multi-view latent representations in a diffusion refinement process, generalizing from pair-wise training to arbitrary view counts at inference.
MAG-3D is a training-free multi-agent framework that coordinates planning, grounding, and coding agents with off-the-shelf VLMs to achieve grounded 3D reasoning and state-of-the-art benchmark results.
ProBA replaces rigid point tracks with a probabilistic pose graph and 3D Gaussian landmarks, optimizing via negative log-likelihood with the Bhattacharyya coefficient to expand the basin of attraction in prior-free SfM.
citing papers explorer
-
CasaMaestro: Multi-View Panoramas for House-Scale 3D Reconstruction
CasaMaestro predicts metric depth and poses from sparse multi-view panoramas to enable fast house-scale 3D reconstruction.
-
AsyncEvGS: Asynchronous Event-Assisted Gaussian Splatting for Handheld Motion-Blurred Scenes
AsyncEvGS reconstructs high-fidelity 3D scenes from motion-blurred images by first deblurring via event data then using VGGT-based pose estimation and structure-driven losses inside Gaussian Splatting.
-
Free Geometry: Refining 3D Reconstruction from Longer Versions of Itself
Free Geometry enables test-time self-improvement of 3D reconstruction models via cross-view consistency between full and masked observations, yielding average gains of 3.73% in pose accuracy and 2.88% in point maps.
-
ReplicateAnyScene: Zero-Shot Video-to-3D Composition via Textual-Visual-Spatial Alignment
ReplicateAnyScene performs fully automated zero-shot video-to-compositional-3D reconstruction by cascading alignments of generic priors from vision foundation models across textual, visual, and spatial dimensions.
-
SpectralSplat: Appearance-Disentangled Feed-Forward Gaussian Splatting for Driving Scenes
SpectralSplat disentangles appearance from geometry in feed-forward 3D Gaussian Splatting by factoring color into base and adapted streams conditioned on DINOv2 embeddings, trained on paired data from a hybrid relighting pipeline.
-
Geometric Foundation Model Distillation for Efficient Lunar 3D Reconstruction
Distillation of a 688M-parameter MASt3R teacher yields up to 7x smaller students that retain most lunar reconstruction accuracy and outperform sparse-supervised baselines.
-
SyncFix: Fixing 3D Reconstructions via Multi-View Synchronization
SyncFix improves 3D reconstructions by synchronizing multi-view latent representations in a diffusion refinement process, generalizing from pair-wise training to arbitrary view counts at inference.
-
MAG-3D: Multi-Agent Grounded Reasoning for 3D Understanding
MAG-3D is a training-free multi-agent framework that coordinates planning, grounding, and coding agents with off-the-shelf VLMs to achieve grounded 3D reasoning and state-of-the-art benchmark results.
-
ProBA: Probabilistic Bundle Adjustment with the Bhattacharyya Coefficient
ProBA replaces rigid point tracks with a probabilistic pose graph and 3D Gaussian landmarks, optimizing via negative log-likelihood with the Bhattacharyya coefficient to expand the basin of attraction in prior-free SfM.