REVIEW 32 cited by
VGGT: Visual Geometry Grounded Transformer
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
VGGT: Visual Geometry Grounded Transformer
read the original abstract
We present VGGT, a feed-forward neural network that directly infers all key 3D attributes of a scene, including camera parameters, point maps, depth maps, and 3D point tracks, from one, a few, or hundreds of its views. This approach is a step forward in 3D computer vision, where models have typically been constrained to and specialized for single tasks. It is also simple and efficient, reconstructing images in under one second, and still outperforming alternatives that require post-processing with visual geometry optimization techniques. The network achieves state-of-the-art results in multiple 3D tasks, including camera parameter estimation, multi-view depth estimation, dense point cloud reconstruction, and 3D point tracking. We also show that using pretrained VGGT as a feature backbone significantly enhances downstream tasks, such as non-rigid point tracking and feed-forward novel view synthesis. Code and models are publicly available at https://github.com/facebookresearch/vggt.
Forward citations
Cited by 32 Pith papers
-
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.
-
Stream3D: Sequential Multi-View 3D Generation via Evidential Memory
Stream3D is a training-free method that maintains temporal consistency in 3D generation from monocular streams by dynamically caching a fixed number of informative historical frames using an evidence score.
-
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.
-
OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulation
OA-WAM uses persistent address vectors and dynamic content vectors in object slots to enable addressable world-action prediction, improving robustness on manipulation benchmarks under scene changes.
-
Towards Realistic and Consistent Orbital Video Generation via 3D Foundation Priors
A video generation approach conditions a base model with multi-scale 3D latent features and a cross-attention adapter to produce geometrically realistic and consistent orbital videos from one image.
-
$\pi^3$: 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 d...
-
VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold
VGGT-SLAM aligns VGGT submaps via SL(4) manifold optimization of 15-DoF homographies to enable consistent dense RGB SLAM on long uncalibrated monocular videos.
-
RayOcc: Occlusion-Aware Ray Occupancy Estimation via Gaussian Mixture Intensity
RayOcc models each camera ray as a non-normalized Gaussian mixture with Poisson-based occupancy probabilities, allowing multiple depth hypotheses per ray and improving Gaussian-initialized 3D occupancy prediction on nuScenes.
-
PACE: Polar Axis-Conditioned Estimation for PairUAV Relative Localization
A shared image-pair network beats a single-head baseline by giving heading and range their own decoder readouts—PACE's raw model scores 0.002460 on the PairUAV hidden test.
-
X-Lens: Real-Time Metric Depth Estimation with Heterogeneous Cameras
X-Lens fuses arbitrary calibrated fisheye and pinhole views into real-time metric depth at 41 FPS with a 0.04B-parameter model and a new 266K-frame synthetic dataset.
-
X-Lens: Real-Time Metric Depth Estimation with Heterogeneous Cameras
A 0.04B-parameter feed-forward model estimates metric depth from variable calibrated fisheye and pinhole views using calibration tokens and Jacobian distortion bias, with a new multi-view synthetic dataset.
-
HandsOnWorld: Unconstrained Egocentric Video Generation with Camera-Disentangled Hand Control
HandsOnWorld creates a hand-controlled egocentric video generator from unconstrained monocular video via a new EgoVid-Pro dataset from monocular reconstruction and a Plücker Hand Map that disentangles camera and hand motion.
-
Error-Conditioned Neural Solvers
Error-Conditioned Neural Solvers improve PDE prediction accuracy by using the residual field as network input for learned corrections, outperforming residual-minimization methods by up to 10x on turbulent flows and ge...
-
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.
-
S-Agent: Spatial Tool-Use Elicits Reasoning for Spatial Intelligence
S-Agent augments VLMs with spatial tools, scene and agent memory for evidence accumulation on multi-view and video tasks, and produces an 8B model via SFT on its own trajectories that beats same-scale baselines.
-
Unpaired RGB-Thermal Gaussian-Splatting Using Visual Geometric Transformers
Framework for unpaired RGB-thermal novel view synthesis via VGGT-based independent pose estimation, Procrustes alignment with cross-modal matcher, multi-modal 3D Gaussian Splatting, and a new benchmarking framework fo...
-
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.
-
Stabilizing Streaming Video Geometry via Dynamic Feature Normalization
DyFN is a lightweight recurrent module that dynamically normalizes latent feature statistics to remove scale-shift drift and achieve state-of-the-art temporal consistency in streaming monocular geometry estimation whi...
-
Stream3D: Sequential Multi-View 3D Generation via Evidential Memory
Stream3D is a training-free method that maintains a fixed-size evidential memory of past frames to convert frozen view-conditioned 3D generators into consistent streaming generators.
-
ROAR-3D: Routing Arbitrary Views for High-Fidelity 3D Generation
ROAR-3D adds a token-wise view router and dual-stream attention to pretrained single-view 3D generators so they can use arbitrary unposed images for higher-fidelity output.
-
Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective
The paper proposes a problem-driven taxonomy for feed-forward 3D scene modeling that groups methods by five core challenges: feature enhancement, geometry awareness, model efficiency, augmentation strategies, and temp...
-
WARPED: Wrist-Aligned Rendering for Robot Policy Learning from Egocentric Human Demonstrations
WARPED synthesizes realistic wrist-view observations from monocular egocentric human videos via foundation models, hand-object tracking, retargeting, and Gaussian Splatting to train visuomotor policies that match tele...
-
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.
-
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.
-
SalientGS: Unified SfM-to-3DGS with Importance-Guided MCMC Gaussian Allocation
Importance-guided MCMC reallocates 3D Gaussians toward multi-view underfit regions, enabling a unified SfM-to-3DGS pipeline that finishes in ~15 minutes with SOTA perceptual quality.
-
VIGOR: VIdeo Geometry-Oriented Reward for Temporal Generative Alignment
A VGGT-based pointwise reprojection reward with geometry-aware sampling improves video geometric consistency via SFT/DPO and causal test-time search.
-
SalientGS: Unified SfM-to-3DGS with Importance-Guided MCMC Gaussian Allocation
SalientGS integrates fast first-order SfM, joint pose refinement, and importance-guided MCMC Gaussian birth/relocation to reach 27.65 dB macro-average PSNR at 1.5M Gaussians in about 10 minutes end-to-end.
-
S-Agent: Spatial Tool-Use Elicits Reasoning for Spatial Intelligence
S-Agent improves VLMs on spatial reasoning benchmarks via tool-based 3D evidence accumulation and dual memory, and fine-tuning on its generated trajectories produces an 8B model that surpasses similar-scale baselines ...
-
EigeNet: Geometry-Informed Multi-Modal Learning for Few-shot Novel View RIR Prediction
EigeNet applies a cross-view alternate-attention transformer with geometry modulation for few-shot novel-view RIR prediction, reporting SOTA results on simulated and real data.
-
StemVLA:An Open-Source Vision-Language-Action Model with Future 3D Spatial Geometry Knowledge and 4D Historical Representation
StemVLA supervises a GPT-2-based VLA with predicted future 3D-geometry features (VGGT) and temporally aggregated history, reporting 86.0% on LIBERO-Long - but its CALVIN results and equations are placeholders.
-
Understanding the Impact of Geometric Foundation Models on Vision-Language-Action Models
The paper quantifies the geometric gap in current VLAs via linear probing and compares three architectures for injecting geometry from GFMs while analyzing impacts of data, cameras, and reconstruction quality.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.