RoMa v2: Harder Better Faster Denser Feature Matching
read the original abstract
Dense feature matching aims to estimate all correspondences between two images of a 3D scene and has recently been established as the gold standard due to its high accuracy and robustness. However, existing dense matchers still fail or perform poorly for many hard real-world scenarios, and high-precision models are often slow, limiting their applicability. In this paper, we attack these weaknesses on a wide front through a series of systematic improvements that together yield a significantly better model. In particular, we construct a novel matching architecture and loss, which, combined with a curated diverse training distribution, enables our model to solve many complex matching tasks. We further make training faster through a decoupled two-stage matching-then-refinement pipeline, and at the same time, significantly reduce refinement memory usage through a custom CUDA kernel. Finally, we leverage the recent DINOv3 foundation model along with multiple other insights to make the model more robust and unbiased. In our extensive set of experiments, we show that the resulting novel matcher sets a new state-of-the-art, being significantly more accurate than its predecessors. Code is available at https://github.com/Parskatt/romav2
This paper has not been read by Pith yet.
Forward citations
Cited by 15 Pith papers
-
One Video, One World: Turning Monocular Video into Physical 4D Scenes
OVOW reconstructs instance-level, simulation-ready 4D mesh scenes from monocular video via a four-stage training-free pipeline and introduces a new benchmark for structured Video-to-4D evaluation.
-
REDI-Match: Rotation-Equivariant Distillation for Efficient and Robust Dense Matching
REDI-Match proposes rotation-equivariant distillation to transfer VFM semantics into a strictly equivariant encoder plus an entropy-driven alignment decoder, reporting SOTA accuracy and 1.9x speed on dense matching be...
-
REDI-Match: Rotation-Equivariant Distillation for Efficient and Robust Dense Matching
REDI-Match uses rotation-equivariant distillation to transfer VFM semantics into a strictly equivariant encoder plus an entropy-driven alignment module, claiming SOTA accuracy and 1.9x speed on rotation-heavy benchmarks.
-
OrthoTrack: Continuous 6-DoF UAV Trajectory Estimation Anchored in Public Orthophotos
OrthoTrack is a training-free system for continuous 6-DoF UAV pose estimation anchored in public orthophotos and surface models, with a new MovingDrone benchmark dataset.
-
OrthoTrack: Continuous 6-DoF UAV Trajectory Estimation Anchored in Public Orthophotos
OrthoTrack is a training-free system for continuous metric 6-DoF UAV pose estimation anchored in public orthophotos and surface models, with a new MovingDrone benchmark dataset.
-
Unified Motion-Action Modeling for Heterogeneous Robot Learning
UMA treats object motion and robot actions as co-evolving variables under a masked generative objective with hindsight relabeling and contrastive disentanglement to support multi-task pretraining and deployment across...
-
SG2Loc: Sequential Visual Localization on 3D Scene Graphs
A particle-filter sequential localization method that matches per-patch semantic features from images to objects in a compact 3D scene graph via mesh projection and visibility.
-
G2G: Exploiting Intra-Group Geometry for Inter-Group Pose Estimation
G2G attaches three small trainable modules to frozen backbones and reports state-of-the-art inter-group pose accuracy on four datasets spanning simulation, real cross-season, and sim-to-real transfer using only relati...
-
Privacy-Preserving Structureless Visual Localization via Image Obfuscation
Simple image obfuscation enables privacy-preserving structureless visual localization with standard feature matchers and no pipeline changes, achieving state-of-the-art accuracy among privacy methods.
-
LoMa: Local Feature Matching Revisited
Scaling data, model size, and compute for local feature matching produces large performance gains on challenging benchmarks and a new manually annotated HardMatch dataset.
-
TerraSky3D: Multi-View Reconstructions of European Landmarks in 4K
TerraSky3D is a new high-resolution multi-view dataset with 50,000 images in 150 scenes of European landmarks, supplied with poses and depth maps to support 3D reconstruction research.
-
FreeTimeGS++: Secrets of Dynamic Gaussian Splatting and Their Principles
FreeTimeGS++ improves 4D Gaussian Splatting by using gated marginalization and neural velocity fields to achieve more stable dynamic scene representations with lower run-to-run variance.
-
FreeTimeGS++: Secrets of Dynamic Gaussian Splatting and Their Principles
FreeTimeGS++ improves dynamic scene reconstruction by identifying emergent temporal partitioning and photometric-motion decoupling in 4DGS, then applying targeted techniques for reduced run-to-run variance.
-
FreeTimeGS++: Secrets of Dynamic Gaussian Splatting and Their Principles
Analysis of 4DGS reveals temporal partitioning from Gaussian durations and a photometric-spatiotemporal discrepancy, leading to FreeTimeGS++ with gated marginalization and neural velocity fields for superior stability...
-
Who Handles Orientation? Investigating Invariance in Feature Matching
Learning rotation invariance in descriptors matches the performance of matcher-level invariance but allows earlier invariance, faster matchers, and no loss in upright performance when trained at scale.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.