GenRecon lifts object-level generative priors to scene-scale reconstruction by chunking scenes and using projection-based conditioning on multi-view features, claiming 16% better results than prior methods.
Dust3r: Geometric 3d vision made easy
12 Pith papers cite this work, alongside 3 external citations. Polarity classification is still indexing.
12
Pith papers citing it
3
external citations · external index
citation-role summary
background 1
citation-polarity summary
years
2026 12verdicts
UNVERDICTED 12roles
background 1polarities
background 1representative citing papers
NoPo4D is the first feed-forward system for dynamic 4D Gaussian splatting from unposed multi-view videos, using velocity decomposition supervised by optical flow and a bidirectional motion encoder.
CRePE supplies depth-aware positional distributions along curved rays for stable unified-camera control in frozen video DiT models.
PointSplat infers compact Gaussian splats directly in 3D space from input point sets via ray casting and Point-Image Transformer to reduce inter-view redundancy and improve novel-view quality for humans.
Diffusion-based per-view harmonization for lighting-consistent object transfer between 3DGS scenes, using heterogeneous training data and final 3D consolidation.
A LightGBM classifier trained on NWAY Bayesian matches identifies true Chandra-Gaia counterparts for 113k X-ray sources, flags 7k ambiguous cases, and attributes half of 20k separation-only matches to chance coincidences, validated at 95% on COUP without positional features.
Modality Forcing lets a single DiT produce image and depth outputs in any order after training on sparse real-world depth, with larger image-pretrained models yielding better depth accuracy and a 57% AbsRel reduction versus prior joint generative baselines.
Finetuning 3D foundation models on simulated sparse subsets from MegaDepth-X produces robust reconstructions from extremely sparse, noisy internet photos while preserving performance on dense benchmarks.
TrianguLang achieves state-of-the-art feed-forward text-guided 3D localization and segmentation by using predicted geometry to gate cross-view semantic correspondences without ground-truth poses.
SAVMap extracts semantic structure points from panoramic video, tracks them across rectified views, and recovers 3D wireframe maps via Manhattan-constrained SfM, reporting 4.8 cm aggregate MAE over 5000 shelf elements in a 46-row warehouse.
Tests linear, triangular, spline, MLS, Voronoi upsampling plus depth-guided lifting for better 3DGS on Mip-NeRF360 and Replica datasets, with scene-type guidelines.
StereoPolicy fuses left-right image features via cross-attention to deliver consistent gains over RGB, RGB-D, point cloud, and multi-view baselines in simulation and real-robot manipulation tasks.
citing papers explorer
-
GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction
GenRecon lifts object-level generative priors to scene-scale reconstruction by chunking scenes and using projection-based conditioning on multi-view features, claiming 16% better results than prior methods.
-
No Pose, No Problem in 4D: Feed-Forward Dynamic Gaussians from Unposed Multi-View Videos
NoPo4D is the first feed-forward system for dynamic 4D Gaussian splatting from unposed multi-view videos, using velocity decomposition supervised by optical flow and a bidirectional motion encoder.
-
CRePE: Curved Ray Expectation Positional Encoding for Unified-Camera-Controlled Video Generation
CRePE supplies depth-aware positional distributions along curved rays for stable unified-camera control in frozen video DiT models.
-
PointSplat: Compact Gaussian Splatting via Human-Centric Prediction
PointSplat infers compact Gaussian splats directly in 3D space from input point sets via ray casting and Point-Image Transformer to reduce inter-view redundancy and improve novel-view quality for humans.
-
Lighting-Consistent Object Transfer Across Radiance Fields
Diffusion-based per-view harmonization for lighting-consistent object transfer between 3DGS scenes, using heterogeneous training data and final 3D consolidation.
-
The Chandra-Gaia Catalog of Counterparts: Resolving ambiguous Gaia matches to X-ray sources in the Chandra Source Catalog using Machine Learning
A LightGBM classifier trained on NWAY Bayesian matches identifies true Chandra-Gaia counterparts for 113k X-ray sources, flags 7k ambiguous cases, and attributes half of 20k separation-only matches to chance coincidences, validated at 95% on COUP without positional features.
-
Modality Forcing for Scalable Spatial Generation
Modality Forcing lets a single DiT produce image and depth outputs in any order after training on sparse real-world depth, with larger image-pretrained models yielding better depth accuracy and a 57% AbsRel reduction versus prior joint generative baselines.
-
Long-tail Internet photo reconstruction
Finetuning 3D foundation models on simulated sparse subsets from MegaDepth-X produces robust reconstructions from extremely sparse, noisy internet photos while preserving performance on dense benchmarks.
-
TrianguLang: Geometry-Aware Semantic Consensus for Pose-Free 3D Localization
TrianguLang achieves state-of-the-art feed-forward text-guided 3D localization and segmentation by using predicted geometry to gate cross-view semantic correspondences without ground-truth poses.
-
SAVMap: Structure-Aided Visual Mapping of Large-Scale 2.5D Manhattan Wireframes from Panoramic Video
SAVMap extracts semantic structure points from panoramic video, tracks them across rectified views, and recovers 3D wireframe maps via Manhattan-constrained SfM, reporting 4.8 cm aggregate MAE over 5000 shelf elements in a 46-row warehouse.
-
Optimizing 3D Gaussian Splatting via Point Cloud Upsampling
Tests linear, triangular, spline, MLS, Voronoi upsampling plus depth-guided lifting for better 3DGS on Mip-NeRF360 and Replica datasets, with scene-type guidelines.
-
StereoPolicy: Improving Robotic Manipulation Policies via Stereo Perception
StereoPolicy fuses left-right image features via cross-attention to deliver consistent gains over RGB, RGB-D, point cloud, and multi-view baselines in simulation and real-robot manipulation tasks.