A fine-tuned video diffusion model translates monocular video into a synthetic proxy video of a moving cube, enabling 6-DoF pose tracking via classical solvers without 3D models, depth, or masks.
super hub Mixed citations
Depth Anything 3: Recovering the Visual Space from Any Views
Mixed citation behavior. Most common role is method (42%).
217
Pith papers citing it
Method
42% of classified citations
abstract
We present Depth Anything 3 (DA3), a model that predicts spatially consistent geometry from an arbitrary number of visual inputs, with or without known camera poses. In pursuit of minimal modeling, DA3 yields two key insights: a single plain transformer (e.g., vanilla DINO encoder) is sufficient as a backbone without architectural specialization, and a singular depth-ray prediction target obviates the need for complex multi-task learning. Through our teacher-student training paradigm, the model achieves a level of detail and generalization on par with Depth Anything 2 (DA2). We establish a new visual geometry benchmark covering camera pose estimation, any-view geometry and visual rendering. On this benchmark, DA3 sets a new state-of-the-art across all tasks, surpassing prior SOTA VGGT by an average of 44.3% in camera pose accuracy and 25.1% in geometric accuracy. Moreover, it outperforms DA2 in monocular depth estimation. All models are trained exclusively on public academic datasets.
hub tools
citation-role summary
background 13
method 13
baseline 4
dataset 1
citation-polarity summary
claims ledger
- abstract We present Depth Anything 3 (DA3), a model that predicts spatially consistent geometry from an arbitrary number of visual inputs, with or without known camera poses. In pursuit of minimal modeling, DA3 yields two key insights: a single plain transformer (e.g., vanilla DINO encoder) is sufficient as a backbone without architectural specialization, and a singular depth-ray prediction target obviates the need for complex multi-task learning. Through our teacher-student training paradigm, the model achieves a level of detail and generalization on par with Depth Anything 2 (DA2). We establish a new
authors
co-cited works
representative citing papers
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.
Every9D-21M supplies 21.8M real-world 9D pose annotations for 700 everyday categories by propagating manual canonical poses through cross-instance alignment in object-centric videos and verifying them multiview.
SpatialBench evaluates 41 spatial foundation models across 6 paradigms and 5 task suites, finds they are not all-round players, and introduces the DA-Next-5M dataset plus DA-Next baseline model.
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.
The Geometric Reciprocity Theorem proves that DIBR disocclusion masks for stereo synthesis equal the pixels lost during reverse warping, enabling self-supervised stereo inpainting training from monocular images alone.
LIME formulates language-conditioned camera motion as predicting SE(3) target poses from RGB and intent text, using mined multi-intent supervision from egocentric video and a flow-matching pose head.
InvSplat is a feed-forward multi-view model that predicts 3D Gaussians augmented with intrinsic material attributes for inverse rendering and relighting.
QWERTY enables training-free motion control in pretrained image-to-video DiTs by warping the frame-invariant semantic subspace of queries in 3D full attention and using the predicted noise as self-guidance for latent optimization.
MindEdit-Bench introduces six spatial reasoning tasks from 120 private indoor photo triplets, with two new counterfactual editing tasks where VLMs score 8-31% against 81-97% human accuracy.
WarpHammer densifies scene warps with 3D object priors from generative models and fuses pose-unknown auxiliary views via multi-view geometry to enable stable extreme novel view synthesis.
CasaMaestro predicts metric depth and poses from sparse multi-view panoramas to enable fast house-scale 3D reconstruction.
NeuWorld uses a transformer VAE to learn compact Neural Implicit Scenes from sparse posed frames and a diffusion transformer to evolve them conditioned on camera trajectories for consistent interactive exploration.
SWAM jointly generates intermediate RGB-D sequences and action trajectories from monocular RGB start/goal observations for embodied navigation.
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.
SATURN reconstructs approximate 3D scenes, derives soft perspective-aware predicates, and executes them symbolically to achieve stable performance on complex multi-perspective spatial grounding tasks where VLMs degrade.
Introduces Fisher Information-guided stereo augmentation and uncertainty-aware regularization to mitigate overfitting in sparse-view 3D Gaussian Splatting.
OR3 converts OR clips to action-driven digital twins, uses LLM imagination for hypothetical ActDTs, and achieves 57.6 R@1 and 77.3 R@5 on 276 implicit queries from 386 robotic knee procedure clips, outperforming baselines.
World Tracing introduces a multi-layer pixel-aligned 3D point representation instantiated via a diffusion transformer (WT-DiT) trained with pixel-space flow matching to jointly reconstruct visible surfaces and generate occluded geometry.
DepthMaster unifies metric monocular depth estimation for perspective and panoramic images by patching panoramas into perspective views, adding a consistency loss and virtual cameras, and training mostly on perspective data to reach SOTA zero-shot results on 13 datasets.
PhysAgent is a simulator-in-the-loop multi-agent system that automates physically grounded 4D synthesis from multimodal prompts by using trajectory feedback from vision models and LLM reasoning to optimize force fields.
ExMesh introduces a framework for explicit mesh reconstruction from images that integrates adaptive topology updates into differentiable optimization while maintaining UV coordinates.
RigPAPR auto-rigs static PAPR point clouds and drives them via direct LBS from monocular fixed-view video, matching baselines at supervised views and exceeding them by 3+dB PSNR at novel views with cleaner joints.
A transformer model predicts in vivo hip and knee contact forces from uncalibrated monocular video at accuracy matching subject-specific musculoskeletal simulations under leave-one-subject-out validation.
citing papers explorer
-
ProxyPose: 6-DoF Pose Tracking via Video-to-Video Translation
A fine-tuned video diffusion model translates monocular video into a synthetic proxy video of a moving cube, enabling 6-DoF pose tracking via classical solvers without 3D models, depth, or masks.
-
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.
-
Every9D-21M: Large-Scale Real-World 9D Canonicalization of Everyday Objects
Every9D-21M supplies 21.8M real-world 9D pose annotations for 700 everyday categories by propagating manual canonical poses through cross-instance alignment in object-centric videos and verifying them multiview.
-
SpatialBench: Is Your Spatial Foundation Model an All-Round Player?
SpatialBench evaluates 41 spatial foundation models across 6 paradigms and 5 task suites, finds they are not all-round players, and introduces the DA-Next-5M dataset plus DA-Next baseline model.
-
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.
-
Geometric Reciprocity: Unlocking Self-Supervision for Stereoscopic Video Generation
The Geometric Reciprocity Theorem proves that DIBR disocclusion masks for stereo synthesis equal the pixels lost during reverse warping, enabling self-supervised stereo inpainting training from monocular images alone.
-
LIME: Learning Intent-aware Camera Motion from Egocentric Video
LIME formulates language-conditioned camera motion as predicting SE(3) target poses from RGB and intent text, using mined multi-intent supervision from egocentric video and a flow-matching pose head.
-
InvSplat: Inverse Feed-Forward Scene Splatting
InvSplat is a feed-forward multi-view model that predicts 3D Gaussians augmented with intrinsic material attributes for inverse rendering and relighting.
-
QWERTY: Training-Free Motion Control via Query-Warped Video Diffusion Transformers
QWERTY enables training-free motion control in pretrained image-to-video DiTs by warping the frame-invariant semantic subspace of queries in 3D full attention and using the predicted noise as self-guidance for latent optimization.
-
MindEdit-Bench: Benchmarking Object-Level Counterfactual Spatial Reasoning in VLMs from In-the-Wild Photos
MindEdit-Bench introduces six spatial reasoning tasks from 120 private indoor photo triplets, with two new counterfactual editing tasks where VLMs score 8-31% against 81-97% human accuracy.
-
WarpHammer: Densifying Scene Warps with 3D Object Priors for Extreme View Synthesis
WarpHammer densifies scene warps with 3D object priors from generative models and fuses pose-unknown auxiliary views via multi-view geometry to enable stable extreme novel view synthesis.
-
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.
-
Walking in the Implicit: Interactive World Exploration via Neural Scene Representation
NeuWorld uses a transformer VAE to learn compact Neural Implicit Scenes from sparse posed frames and a diffusion transformer to evolve them conditioned on camera trajectories for consistent interactive exploration.
-
Pondering the Way: Spatial-perceiving World Action Model for Embodied Navigation
SWAM jointly generates intermediate RGB-D sequences and action trajectories from monocular RGB start/goal observations for embodied navigation.
-
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.
-
SATURN: Symbolic Spatial Reasoning for Multi-Perspective Grounding
SATURN reconstructs approximate 3D scenes, derives soft perspective-aware predicates, and executes them symbolically to achieve stable performance on complex multi-perspective spatial grounding tasks where VLMs degrade.
-
From Uncertainty to Stability and Fidelity: Guiding Sparse-View 3D Gaussian Splatting with Fisher Information
Introduces Fisher Information-guided stereo augmentation and uncertainty-aware regularization to mitigate overfitting in sparse-view 3D Gaussian Splatting.
-
Reasoning Text-to-Video Retrieval for Operating Room Clips via Action-Driven Digital Twins
OR3 converts OR clips to action-driven digital twins, uses LLM imagination for hypothetical ActDTs, and achieves 57.6 R@1 and 77.3 R@5 on 276 implicit queries from 386 robotic knee procedure clips, outperforming baselines.
-
World Tracing: Generative Pixel-Aligned Geometry Beyond the Visible
World Tracing introduces a multi-layer pixel-aligned 3D point representation instantiated via a diffusion transformer (WT-DiT) trained with pixel-space flow matching to jointly reconstruct visible surfaces and generate occluded geometry.
-
DepthMaster: Unified Monocular Depth Estimation for Perspective and Panoramic Images
DepthMaster unifies metric monocular depth estimation for perspective and panoramic images by patching panoramas into perspective views, adding a consistency loss and virtual cameras, and training mostly on perspective data to reach SOTA zero-shot results on 13 datasets.
-
PhysAgent: Automating Physics-Based 4D Synthesis via Trajectory-Grounded Multi-Agent Feedback
PhysAgent is a simulator-in-the-loop multi-agent system that automates physically grounded 4D synthesis from multimodal prompts by using trajectory feedback from vision models and LLM reasoning to optimize force fields.
-
ExMesh: EXplicit Mesh Reconstruction with Topology Adaptation
ExMesh introduces a framework for explicit mesh reconstruction from images that integrates adaptive topology updates into differentiable optimization while maintaining UV coordinates.
-
RigPAPR: Rig-Based Animation of Static Neural Point Clouds from a Fixed-Viewpoint Video
RigPAPR auto-rigs static PAPR point clouds and drives them via direct LBS from monocular fixed-view video, matching baselines at supervised views and exceeding them by 3+dB PSNR at novel views with cleaner joints.
-
From Pixels to Newtons: Predicting In Vivo Joint Contact Forces from Monocular Video
A transformer model predicts in vivo hip and knee contact forces from uncalibrated monocular video at accuracy matching subject-specific musculoskeletal simulations under leave-one-subject-out validation.
-
Geometry Gaussians: Decoupling Appearance and Geometry in Gaussian Splatting
A dedicated geometry opacity parameter per 3D Gaussian decouples appearance from geometry and yields better novel-view rendering plus surface reconstruction on varied datasets.
-
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.
-
Z-FLoc: Zero-Shot Floorplan Localization via Geometric Primitives
Z-FLoc performs zero-shot floorplan localization by matching geometric primitives from BEV projections of monocular 3D reconstructions to floorplans using dedicated minimal solvers in a robust framework.
-
Honey, I Shrunk the Arc de Triomphe!
MetricScenes dataset from web photos and stereo imagery, plus a two-stage Poisson depth completion method, allows fine-tuning MoGe-2 to mitigate scale-collapse in metric monocular geometry while preserving benchmark performance.
-
MBench: A Comprehensive Benchmark on Memory Capability for Video World Models
MBench is a new benchmark that quantifies long-term memory in video world models via three hierarchical consistency dimensions evaluated on curated real videos.
-
WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluation
WBench is a benchmark with 289 test cases and 1,058 turns for evaluating interactive world models using 22 automated metrics validated against human judgments.
-
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.
-
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.
-
SpaceDG: Benchmarking Spatial Intelligence under Visual Degradation
SpaceDG is the first large-scale benchmark dataset (~1M QA pairs) simulating nine visual degradations in 3DGS-rendered scenes to measure and improve spatial intelligence robustness in MLLMs.
-
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.
-
Goodbye Drift: Anchored Tree Sampling for Long-Horizon Video-to-Video Generation
Anchored Tree Sampling converts horizon-compounding drift into anchor-bounded drift by organizing video generation as a sparse-to-dense tree of imputations instead of left-to-right autoregressive rollout.
-
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.
-
StableHand: Quality-Aware Flow Matching for World-Space Dual-Hand Motion Estimation from Egocentric Video
StableHand introduces a quality-aware flow matching framework conditioned on predicted four-channel per-frame hand observation quality to estimate dual-hand world-space motion from egocentric video, achieving SOTA results with 20-25% W-MPJPE reduction on HOT3D and ARCTIC benchmarks.
-
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.
-
Probing into Camera Control of Video Models
A training-free method reformulates camera control as geometric displacement fields applied via differentiable latent resampling, enabling control and bias probing in video diffusion models.
-
Revisiting Photometric Ambiguity for Accurate Gaussian-Splatting Surface Reconstruction
AmbiSuR adds intrinsic photometric disambiguation and a self-indication module to Gaussian Splatting to resolve ambiguities and improve surface reconstruction accuracy.
-
PointForward: Feedforward Driving Reconstruction through Point-Aligned Representations
PointForward uses sparse world-space 3D queries and scene graphs to deliver consistent single-pass reconstruction of dynamic driving scenes via point-aligned representations.
-
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.
-
Image Generators are Generalist Vision Learners
An image generator is instruction-tuned to perform diverse vision tasks by representing task outputs as RGB images, achieving SOTA on segmentation and depth estimation.
-
View-Consistent 3D Scene Editing via Dual-Path Structural Correspondense and Semantic Continuity
A dual-path consistency framework for text-driven 3D scene editing that models cross-view dependencies via structural correspondence and semantic continuity, trained on a newly constructed paired multi-view dataset.
-
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.
-
Any 3D Scene is Worth 1K Tokens: 3D-Grounded Representation for Scene Generation at Scale
A 3D-grounded autoencoder and diffusion transformer allow direct generation of 3D scenes in an implicit latent space using a fixed 1K-token representation for arbitrary views and resolutions.
-
EgoFun3D: Modeling Interactive Objects from Egocentric Videos using Function Templates
EgoFun3D creates a new task, 271-video dataset, and pipeline using function templates to model interactive 3D objects from egocentric videos for simulation.
-
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.