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.
Metric3d v2: A versatile monocular geometric foundation model for zero-shot metric depth and surface normal estima- tion
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
abstract
We introduce Metric3D v2, a geometric foundation model for zero-shot metric depth and surface normal estimation from a single image, which is crucial for metric 3D recovery. While depth and normal are geometrically related and highly complimentary, they present distinct challenges. SoTA monocular depth methods achieve zero-shot generalization by learning affine-invariant depths, which cannot recover real-world metrics. Meanwhile, SoTA normal estimation methods have limited zero-shot performance due to the lack of large-scale labeled data. To tackle these issues, we propose solutions for both metric depth estimation and surface normal estimation. For metric depth estimation, we show that the key to a zero-shot single-view model lies in resolving the metric ambiguity from various camera models and large-scale data training. We propose a canonical camera space transformation module, which explicitly addresses the ambiguity problem and can be effortlessly plugged into existing monocular models. For surface normal estimation, we propose a joint depth-normal optimization module to distill diverse data knowledge from metric depth, enabling normal estimators to learn beyond normal labels. Equipped with these modules, our depth-normal models can be stably trained with over 16 million of images from thousands of camera models with different-type annotations, resulting in zero-shot generalization to in-the-wild images with unseen camera settings. Our method enables the accurate recovery of metric 3D structures on randomly collected internet images, paving the way for plausible single-image metrology. Our project page is at https://JUGGHM.github.io/Metric3Dv2.
citation-role summary
background 1
baseline 1
citation-polarity summary
representative citing papers
Qwen-RobotWorld is a language-conditioned video world model using Double-Stream MMDiT, an 8.6M-frame embodied corpus, and progressive curriculum training that ranks first on EWMBench and DreamGen Bench.
One transformer, trained with random-sized temporal attention chunks, unifies offline, streaming, and long-video depth, normal, and point-map estimation and reports new best numbers on five public benchmarks.
PRISM-SLAM adds a Plücker Ray-Distance Factor and dynamic uncertainty gating to a VFM-augmented factor graph to deliver scale-consistent metric SLAM at 30 FPS from monocular RGB.
Depth Anything V2 delivers finer, more robust monocular depth predictions by replacing real labeled images with synthetic data, scaling the teacher model, and using large-scale pseudo-labeled real images for student training.
Qwen-Image is a foundation model that reaches state-of-the-art results in image generation and editing by combining a large-scale text-focused data pipeline with curriculum learning and dual semantic-reconstructive encoding for editing consistency.
MoGe-2 recovers metric-scale 3D point maps with fine details from single images via data refinement and extension of affine-invariant predictions.
UniDepthV2 predicts metric 3D points directly from single images using a self-promptable camera module, pseudo-spherical representation, and new losses for improved cross-domain generalization.
A ray-tracing pipeline aligns ground-level image pixels to outdated DEM rasters for real-time 3D terrain reconstruction in wildfire zones, validated primarily through a custom simulator.
citing papers explorer
-
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.
-
Qwen-RobotWorld Technical Report: Unifying Embodied World Modeling through Language-Conditioned Video Generation
Qwen-RobotWorld is a language-conditioned video world model using Double-Stream MMDiT, an 8.6M-frame embodied corpus, and progressive curriculum training that ranks first on EWMBench and DreamGen Bench.
-
Towards Consistent Video Geometry Estimation
One transformer, trained with random-sized temporal attention chunks, unifies offline, streaming, and long-video depth, normal, and point-map estimation and reports new best numbers on five public benchmarks.
-
PRISM-SLAM: Probabilistic Ray-Grounded Inference for Scale-aware Metric SLAM
PRISM-SLAM adds a Plücker Ray-Distance Factor and dynamic uncertainty gating to a VFM-augmented factor graph to deliver scale-consistent metric SLAM at 30 FPS from monocular RGB.
-
Depth Anything V2
Depth Anything V2 delivers finer, more robust monocular depth predictions by replacing real labeled images with synthetic data, scaling the teacher model, and using large-scale pseudo-labeled real images for student training.
-
Qwen-Image Technical Report
Qwen-Image is a foundation model that reaches state-of-the-art results in image generation and editing by combining a large-scale text-focused data pipeline with curriculum learning and dual semantic-reconstructive encoding for editing consistency.
-
MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details
MoGe-2 recovers metric-scale 3D point maps with fine details from single images via data refinement and extension of affine-invariant predictions.
-
UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler
UniDepthV2 predicts metric 3D points directly from single images using a self-promptable camera module, pseudo-spherical representation, and new losses for improved cross-domain generalization.
-
LTM: Large-scale Terrain Model for Wildfire-prone Landscapes
A ray-tracing pipeline aligns ground-level image pixels to outdated DEM rasters for real-time 3D terrain reconstruction in wildfire zones, validated primarily through a custom simulator.