Geo-Align applies RL with a perceptual reward derived from 3D camera trajectory estimation to improve controllability and fidelity in video generation without paired training data.
hub
arXiv preprint arXiv:2501.13928 (2025)
17 Pith papers cite this work. Polarity classification is still indexing.
17
Pith papers citing it
hub tools
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative 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.
3DReflecNet is a 22 TB+ dataset of over 120,000 synthetic and 1,000 real objects with millions of multi-view frames for benchmarking 3D reconstruction on reflective, transparent, and low-texture surfaces.
PaceVGGT reduces VGGT inference latency by up to 5.1x on ScanNet-50 via pre-AA token pruning with a distilled Token Scorer, per-frame keep budgets, adaptive merge/prune, and feature-guided restoration, while preserving reconstruction quality on ScanNet-50 and 7-Scenes.
FastForward represents scenes as collections of 3D-anchored image features and performs camera pose estimation via feed-forward correspondence prediction, achieving competitive accuracy with minimal mapping time.
π³ is a feed-forward network with full permutation equivariance that outputs affine-invariant poses and scale-invariant local point maps without reference frames, reaching state-of-the-art on camera pose, depth, and dense reconstruction benchmarks.
TriSplat predicts oriented triangle primitives from images in one forward pass to produce simulation-ready 3D meshes with competitive rendering quality.
GEM-4D improves video world models for robot manipulation by distilling 4D geometric correspondences into training and adding an inverse dynamics module, achieving SOTA geometric consistency and 81% real-world success.
A feed-forward video latent transformer that predicts time-varying 3D Gaussian primitives from one image to produce controllable 4D scenes with appearance, geometry, and motion.
A causal transformer with key-value caching and distillation from a bidirectional VGGT model enables efficient online 4D geometry reconstruction from videos.
Geometry Forcing aligns video diffusion representations with geometric foundation model features via angular cosine and scale regression objectives to improve 3D consistency in generated videos.
VLM-3R augments VLMs with implicit 3D tokens from monocular video via geometry encoding and 200K+ 3D reconstructive QA pairs, plus a new 138K-pair temporal benchmark, to support spatial and embodied reasoning.
Introduces an eager-mode PyTorch BA library with GPU-accelerated sparse ops claiming 18.5-23x speedups over GTSAM, g2o, and Ceres.
Presents Instant3D for rapid text/image-to-3D generation via multi-view diffusion plus feed-forward reconstruction, and FastMap for 10x faster structure-from-motion with comparable accuracy.
IVGT implicitly models continuous neural scene representations from pose-free multi-view images to enable coherent surface extraction, novel view synthesis, and related 3D tasks via SDF and color prediction.
ViPE estimates camera intrinsics, motion, and dense near-metric depth from uncalibrated videos, outperforming baselines on TUM and KITTI while releasing annotations for 96M frames across real and generated videos.
VGGT-Long extends VGGT with chunking, overlap alignment, and loop closure to produce consistent kilometer-scale 3D reconstructions from monocular RGB sequences without retraining or extra supervision.
citing papers explorer
-
Geo-Align: Video Generation Alignment via Metric Geometry Reward
Geo-Align applies RL with a perceptual reward derived from 3D camera trajectory estimation to improve controllability and fidelity in video generation without paired training data.
-
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.
-
3DReflecNet: A Large-Scale Dataset for 3D Reconstruction of Reflective, Transparent, and Low-Texture Objects
3DReflecNet is a 22 TB+ dataset of over 120,000 synthetic and 1,000 real objects with millions of multi-view frames for benchmarking 3D reconstruction on reflective, transparent, and low-texture surfaces.
-
PaceVGGT: Pre-Alternating-Attention Token Pruning for Visual Geometry Transformers
PaceVGGT reduces VGGT inference latency by up to 5.1x on ScanNet-50 via pre-AA token pruning with a distilled Token Scorer, per-frame keep budgets, adaptive merge/prune, and feature-guided restoration, while preserving reconstruction quality on ScanNet-50 and 7-Scenes.
-
A Scene is Worth a Thousand Features: Feed-Forward Camera Localization from a Collection of Image Features
FastForward represents scenes as collections of 3D-anchored image features and performs camera pose estimation via feed-forward correspondence prediction, achieving competitive accuracy with minimal mapping time.
-
$\pi^3$: Permutation-Equivariant Visual Geometry Learning
π³ is a feed-forward network with full permutation equivariance that outputs affine-invariant poses and scale-invariant local point maps without reference frames, reaching state-of-the-art on camera pose, depth, and dense reconstruction benchmarks.
-
TriSplat: Simulation-Ready Feed-Forward 3D Scene Reconstruction
TriSplat predicts oriented triangle primitives from images in one forward pass to produce simulation-ready 3D meshes with competitive rendering quality.
-
GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation
GEM-4D improves video world models for robot manipulation by distilling 4D geometric correspondences into training and adding an inverse dynamics module, achieving SOTA geometric consistency and 81% real-world success.
-
Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Models
A feed-forward video latent transformer that predicts time-varying 3D Gaussian primitives from one image to produce controllable 4D scenes with appearance, geometry, and motion.
-
Streaming 4D Visual Geometry Transformer
A causal transformer with key-value caching and distillation from a bidirectional VGGT model enables efficient online 4D geometry reconstruction from videos.
-
Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling
Geometry Forcing aligns video diffusion representations with geometric foundation model features via angular cosine and scale regression objectives to improve 3D consistency in generated videos.
-
VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction
VLM-3R augments VLMs with implicit 3D tokens from monocular video via geometry encoding and 200K+ 3D reconstructive QA pairs, plus a new 138K-pair temporal benchmark, to support spatial and embodied reasoning.
-
Bundle Adjustment in the Eager Mode
Introduces an eager-mode PyTorch BA library with GPU-accelerated sparse ops claiming 18.5-23x speedups over GTSAM, g2o, and Ceres.
-
Efficient 3D Content Reconstruction and Generation
Presents Instant3D for rapid text/image-to-3D generation via multi-view diffusion plus feed-forward reconstruction, and FastMap for 10x faster structure-from-motion with comparable accuracy.
-
IVGT: Implicit Visual Geometry Transformer for Neural Scene Representation
IVGT implicitly models continuous neural scene representations from pose-free multi-view images to enable coherent surface extraction, novel view synthesis, and related 3D tasks via SDF and color prediction.
-
ViPE: Video Pose Engine for 3D Geometric Perception
ViPE estimates camera intrinsics, motion, and dense near-metric depth from uncalibrated videos, outperforming baselines on TUM and KITTI while releasing annotations for 96M frames across real and generated videos.
-
VGGT-Long: Chunk it, Loop it, Align it -- Pushing VGGT's Limits on Kilometer-scale Long RGB Sequences
VGGT-Long extends VGGT with chunking, overlap alignment, and loop closure to produce consistent kilometer-scale 3D reconstructions from monocular RGB sequences without retraining or extra supervision.