TrackCraft3R is the first method to repurpose a video diffusion transformer as a feed-forward dense 3D tracker via dual-latent representations and temporal RoPE alignment, achieving SOTA performance with lower compute.
hub Mixed citations
MapAnything: Universal Feed-Forward Metric 3D Reconstruction
Mixed citation behavior. Most common role is background (62%).
79
Pith papers citing it
Background
62% of classified citations
abstract
We introduce MapAnything, a unified transformer-based feed-forward model that ingests one or more images along with optional geometric inputs such as camera intrinsics, poses, depth, or partial reconstructions, and then directly regresses the metric 3D scene geometry and cameras. MapAnything leverages a factored representation of multi-view scene geometry, i.e., a collection of depth maps, local ray maps, camera poses, and a metric scale factor that effectively upgrades local reconstructions into a globally consistent metric frame. Standardizing the supervision and training across diverse datasets, along with flexible input augmentation, enables MapAnything to address a broad range of 3D vision tasks in a single feed-forward pass, including uncalibrated structure-from-motion, calibrated multi-view stereo, monocular depth estimation, camera localization, depth completion, and more. We provide extensive experimental analyses and model ablations demonstrating that MapAnything outperforms or matches specialist feed-forward models while offering more efficient joint training behavior, thus paving the way toward a universal 3D reconstruction backbone.
hub tools
citation-role summary
background 8
baseline 3
dataset 1
method 1
citation-polarity summary
representative citing papers
CasaMaestro predicts metric depth and poses from sparse multi-view panoramas to enable fast house-scale 3D reconstruction.
None of ten tested video-generation models reliably remembers objects after occlusion in dynamic scenes; static-camera videos inflate consistency scores.
FLAT maps compressed video diffusion latents to explicit triangle splats via ray-centered rotation parameterization and a product window function, reporting better geometric accuracy than 3D Gaussian baselines under identical training.
GeoT2V-Bench is a reconstruction-based benchmark that reveals disagreements among multiple metrics for 3D consistency in text-to-video models.
ZipSplat uses multi-view token extraction followed by k-means clustering and attention to decode compact scene tokens into unconstrained 3D Gaussians, achieving SOTA pose-free results with ~6x fewer primitives.
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.
Depth2Pose is a new evaluation framework for monocular depth estimators that uses relative camera pose accuracy as a task-driven proxy and introduces the D2P dataset of challenging out-of-distribution scenes.
UAVFF3D introduces a geometry-aware real-synthetic benchmark and evaluation protocol for feed-forward UAV 3D reconstruction that supports domain adaptation and reduces errors in camera pose and scene geometry.
A feature-free monocular VINS initialization method that uses feed-forward 3D model point cloud predictions achieves over 90% success rate with under 1.2 seconds of data and performs robustly in degraded environments.
Cross3R performs feed-forward 3D reconstruction and 6-DoF pose estimation from any combination of satellite, UAV, and ground images, outperforming baselines on a new 278K-image tri-view dataset.
Mix3R mixes feed-forward reconstruction and generative 3D priors via Mixture-of-Transformers and overlap-based attention bias to achieve better-aligned 3D shapes and more accurate poses than either approach alone.
AirZoo is a new dataset covering 378 regions across 22 countries with pixel-level metric depth and 6-DoF poses, shown via benchmarks to improve SoTA models on aerial image retrieval, cross-view matching, and multi-view 3D reconstruction.
A three-stage optimization pipeline for multi-camera extrinsic self-calibration that refines camera poses, reconstructs human and stick trajectories, and resolves global scale using the known stick length constraint.
GlobalSplat achieves competitive novel-view synthesis on RealEstate10K and ACID using only 16K Gaussians via global scene tokens and coarse-to-fine training, with a 4MB footprint and under 78ms inference.
CAL2M achieves calibration-free kilometer-level SLAM by using an assistant eye for scale, epipolar-guided intrinsic correction, and anchor propagation for nonlinear sub-map alignment.
The first survey on Attention Sink in Transformers structures the literature around fundamental utilization, mechanistic interpretation, and strategic mitigation.
EgoTL provides a new egocentric dataset with think-aloud chains and metric labels that benchmarks VLMs on long-horizon tasks and improves their planning, reasoning, and spatial grounding after finetuning.
Encoding cameras as pixel-aligned raxels lets one video diffusion model jointly denoise video and trajectories, supporting pose estimation, controlled generation, and joint synthesis.
A new benchmark with real lunar stereo ground truth and analog data shows that sim-to-real fine-tuned monocular depth models achieve large in-domain gains but minimal generalization to actual lunar images.
AnchorSplat uses anchor-aligned 3D Gaussians guided by geometric priors for feed-forward scene reconstruction, achieving SOTA novel view synthesis on ScanNet++ with fewer primitives and better view consistency.
Test-time constrained optimization incorporates priors into pre-trained multiview transformers via self-supervised losses and penalty terms to improve 3D reconstruction accuracy.
MoonSeg3R is the first method for online monocular 3D instance segmentation, achieving performance competitive with RGB-D systems by using CUT3R priors for geometric consistency and temporal query memory.
CrashTwin recovers metric-scale crash dynamics from monocular rollouts and shows that strong visual scores routinely mask large momentum, energy, and identity violations in world models.
citing papers explorer
-
TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking
TrackCraft3R is the first method to repurpose a video diffusion transformer as a feed-forward dense 3D tracker via dual-latent representations and temporal RoPE alignment, achieving SOTA performance with lower compute.
-
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.
-
MemoBench: Benchmarking World Modeling in Dynamically Changing Environments
None of ten tested video-generation models reliably remembers objects after occlusion in dynamic scenes; static-camera videos inflate consistency scores.
-
FLAT: Feedforward Latent Triangle Splatting for Geometrically Accurate Scene Generation
FLAT maps compressed video diffusion latents to explicit triangle splats via ray-centered rotation parameterization and a product window function, reporting better geometric accuracy than 3D Gaussian baselines under identical training.
-
GeoT2V-Bench: Benchmarking 3D Consistency in Text-to-Video Models via 3D Reconstruction
GeoT2V-Bench is a reconstruction-based benchmark that reveals disagreements among multiple metrics for 3D consistency in text-to-video models.
-
ZipSplat: Fewer Gaussians, Better Splats
ZipSplat uses multi-view token extraction followed by k-means clustering and attention to decode compact scene tokens into unconstrained 3D Gaussians, achieving SOTA pose-free results with ~6x fewer primitives.
-
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.
-
Depth2Pose: A Pose-Based Benchmark for Monocular Depth Estimation without Ground-Truth Depth
Depth2Pose is a new evaluation framework for monocular depth estimators that uses relative camera pose accuracy as a task-driven proxy and introduces the D2P dataset of challenging out-of-distribution scenes.
-
UAVFF3D: A Geometry-Aware Benchmark for Feed-Forward UAV 3D Reconstruction
UAVFF3D introduces a geometry-aware real-synthetic benchmark and evaluation protocol for feed-forward UAV 3D reconstruction that supports domain adaptation and reduces errors in camera pose and scene geometry.
-
Efficient Feature-Free Initialization for Monocular Visual-Inertial Systems Using a Feed-Forward 3D Model
A feature-free monocular VINS initialization method that uses feed-forward 3D model point cloud predictions achieves over 90% success rate with under 1.2 seconds of data and performs robustly in degraded environments.
-
Seeing Across Skies and Streets: Feedforward 3D Reconstruction from Satellite, Drone, and Ground Images
Cross3R performs feed-forward 3D reconstruction and 6-DoF pose estimation from any combination of satellite, UAV, and ground images, outperforming baselines on a new 278K-image tri-view dataset.
-
Mix3R: Mixing Feed-forward Reconstruction and Generative 3D Priors for Joint Multi-view Aligned 3D Reconstruction and Pose Estimation
Mix3R mixes feed-forward reconstruction and generative 3D priors via Mixture-of-Transformers and overlap-based attention bias to achieve better-aligned 3D shapes and more accurate poses than either approach alone.
-
AirZoo: A Unified Large-Scale Dataset for Grounding Aerial Geometric 3D Vision
AirZoo is a new dataset covering 378 regions across 22 countries with pixel-level metric depth and 6-DoF poses, shown via benchmarks to improve SoTA models on aerial image retrieval, cross-view matching, and multi-view 3D reconstruction.
-
Multi-Camera Self-Calibration in Sports Motion Capture: Leveraging Human and Stick Poses
A three-stage optimization pipeline for multi-camera extrinsic self-calibration that refines camera poses, reconstructs human and stick trajectories, and resolves global scale using the known stick length constraint.
-
GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens
GlobalSplat achieves competitive novel-view synthesis on RealEstate10K and ACID using only 16K Gaussians via global scene tokens and coarse-to-fine training, with a 4MB footprint and under 78ms inference.
-
Keep It CALM: Toward Calibration-Free Kilometer-Level SLAM with Visual Geometry Foundation Models via an Assistant Eye
CAL2M achieves calibration-free kilometer-level SLAM by using an assistant eye for scale, epipolar-guided intrinsic correction, and anchor propagation for nonlinear sub-map alignment.
-
Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation
The first survey on Attention Sink in Transformers structures the literature around fundamental utilization, mechanistic interpretation, and strategic mitigation.
-
EgoTL: Egocentric Think-Aloud Chains for Long-Horizon Tasks
EgoTL provides a new egocentric dataset with think-aloud chains and metric labels that benchmarks VLMs on long-horizon tasks and improves their planning, reasoning, and spatial grounding after finetuning.
-
Rays as Pixels: Learning A Joint Distribution of Videos and Camera Trajectories
Encoding cameras as pixel-aligned raxels lets one video diffusion model jointly denoise video and trajectories, supporting pose estimation, controlled generation, and joint synthesis.
-
LuMon: A Comprehensive Benchmark and Development Suite with Novel Datasets for Lunar Monocular Depth Estimation
A new benchmark with real lunar stereo ground truth and analog data shows that sim-to-real fine-tuned monocular depth models achieve large in-domain gains but minimal generalization to actual lunar images.
-
AnchorSplat: Feed-Forward 3D Gaussian Splatting with 3D Geometric Priors
AnchorSplat uses anchor-aligned 3D Gaussians guided by geometric priors for feed-forward scene reconstruction, achieving SOTA novel view synthesis on ScanNet++ with fewer primitives and better view consistency.
-
Learning 3D Reconstruction with Priors in Test Time
Test-time constrained optimization incorporates priors into pre-trained multiview transformers via self-supervised losses and penalty terms to improve 3D reconstruction accuracy.
-
MoonSeg3R: Monocular Online Zero-Shot Segment Anything in 3D with Reconstructive Foundation Priors
MoonSeg3R is the first method for online monocular 3D instance segmentation, achieving performance competitive with RGB-D systems by using CUT3R priors for geometric consistency and temporal query memory.
-
A Physics-Grounded Benchmark for Multi-Agent Dynamics in World Models
CrashTwin recovers metric-scale crash dynamics from monocular rollouts and shows that strong visual scores routinely mask large momentum, energy, and identity violations in world models.
-
NoDrift3R: Raymap-Guided Coupling for Drift-Robust Unposed Feed-Forward 3D Reconstruction
Anchoring Gaussian centers to predicted raymaps and jointly optimizing RGB, raymap, and camera losses with a dual-frequency curriculum suppresses pose drift and improves pose-free 3D reconstruction on long sequences.
-
DPPE: Rethinking Camera-Based Positional Encoding for Scaling Multi-View Transformers
DPPE decouples rotation and translation in camera positional encodings for multi-view transformers to resolve late-stage training stagnation and improve generalization in novel view synthesis.
-
Argus: Metric Panoramic 3D Reconstruction for Indoor Scenes
Argus plus Realsee3D deliver state-of-the-art metric camera pose, depth, and point-cloud reconstruction from unordered indoor panoramas via learned covisibility anchoring and geometric factorization.
-
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.
-
Geometric Action Model for Robot Policy Learning
GAM splits a geometric foundation model to enable language-conditioned future geometry prediction and action decoding for robot policies, claiming superior performance on manipulation benchmarks.
-
Latent Spatial Memory for Video World Models
Mirage stores and queries 3D scene information in diffusion latent space via depth-guided lifting and warping, yielding 10.57× faster generation and 55× smaller memory than explicit RGB point-cloud baselines while reaching SOTA on WorldScore.
-
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 relative-pose supervision.
-
Anchor3R: Streaming 3D Reconstruction with Transient Anchors for Long-Horizon Visual Mapping
Anchor3R reframes feed-forward 3D reconstruction as current-centric local measurement prediction, using loop-closure and motion averaging to produce coherent global maps from visual streams.
-
Modeling Depth Ambiguity: A Mixture-Density Representation for Flying-Point-Free Depth Estimation
MDA represents per-pixel depth as a mixture of distributions so that boundary pixels can align hypotheses with distinct surfaces instead of averaging into empty space.
-
ScaRF-SLAM: Scale-Consistent Reconstruction with Feed-Forward Models and Classical Visual SLAM
ScaRF-SLAM decouples classical visual SLAM tracking from GFM mapping and adds lightweight scale optimization across submaps to achieve higher trajectory accuracy and 10-20% better reconstruction precision on building-scale indoor and outdoor datasets.
-
RayDer: Scalable Self-Supervised Novel View Synthesis from Real-World Video
RayDer is a unified transformer backbone for self-supervised static-scene novel view synthesis that absorbs dynamic content as a nuisance factor and shows power-law scaling with data and compute while matching supervised methods in zero-shot settings.
-
VLM3: Vision Language Models Are Native 3D Learners
Standard VLMs achieve expert-level 3D performance on depth estimation, pose estimation, and object understanding via three simple techniques without architecture changes or regression losses.
-
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.
-
FOUND-IT: Foundation-model-first Task-driven 3D Scene Graphs with Granularity on Demand
FOUND-IT constructs evolving task-driven 3D scene graphs with on-demand granularity from monocular cameras by augmenting foundation models, reporting 79% higher accuracy on a grounding benchmark and real-time Jetson deployment.
-
Cambrian-P: Pose-Grounded Video Understanding
Adding per-frame camera-pose supervision to a video MLLM improves spatial and general video question answering by 2–6% and yields SOTA streaming pose estimates on ScanNet.
-
UniT: Unified Geometry Learning with Group Autoregressive Transformer
UniT unifies online and offline 3D geometry perception via a Group Autoregressive Transformer that processes observation groups with anchor-free point map prediction and a scale-adaptive loss.
-
Cross-View Splatter: Feed-Forward View Synthesis with Georeferenced Images
A feed-forward model aligns ground and satellite features to predict Gaussian splats for improved novel-view synthesis on georeferenced outdoor scenes.
-
RGB-only Active 3D Scene Graph Generation for Indoor Mobile Robots
RGB-only active 3D scene graph generation unifies perception and planning to achieve depth-baseline parity and more than double object detection in active indoor exploration.
-
Fixed External Cameras as Common Prior Maps for Active 3D Scene Graph Generation
Fixed external cameras as Common Prior Maps boost initial object recall in 3D scene graph generation by up to 79% and improve active exploration efficiency.
-
LongDPM: Overlap-Aware 4D Reconstruction from Long Monocular Videos
LongDPM introduces an overlap-aware chunk-based framework that registers and fuses local dynamic reconstructions to achieve coherent long-range 4D geometry and tracking from monocular video.
-
GemDepth: Geometry-Embedded Features for 3D-Consistent Video Depth
GemDepth adds explicit camera-pose geometry embeddings and an alternating spatio-temporal transformer to produce sharper, more temporally consistent video depth maps than prior smoothing-based methods.
-
Syn4D: A Multiview Synthetic 4D Dataset
Syn4D supplies multiview synthetic dynamic scenes with dense geometric, tracking and pose ground truth that lets any pixel be unprojected to any time and camera.
-
MeshReGen: A Unified 3D Geometry Regeneration Framework
MeshReGen introduces a conditioned 3D geometry regenerator with VecSet that learns a regeneration prior via self-supervision and reports state-of-the-art results on controllable generation tasks.
-
LA-Pose: Latent Action Pretraining Meets Pose Estimation
LA-Pose achieves over 10% higher pose accuracy than recent feed-forward methods on Waymo and PandaSet benchmarks by repurposing latent actions from self-supervised inverse-dynamics pretraining while using orders of magnitude less labeled 3D data.
-
SS3D: End2End Self-Supervised 3D from Web Videos
SS3D pretrains an end-to-end feed-forward 3D estimator on filtered YouTube-8M videos via SfM self-supervision, MVS filtering, and expert distillation, delivering stronger zero-shot transfer and fine-tuning than prior self-supervised baselines.
-
Vista4D: Video Reshooting with 4D Point Clouds
Vista4D re-synthesizes dynamic videos from new viewpoints by grounding them in a 4D point cloud built with static segmentation and multiview training.