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.
hub Contested
Depth Pro: Sharp Monocular Metric Depth in Less Than a Second
Contested. 1 Pith paper cite this work to dispute or refute its claims.
56
Pith papers citing it
Contested
1 dispute or refute
abstract
We present a foundation model for zero-shot metric monocular depth estimation. Our model, Depth Pro, synthesizes high-resolution depth maps with unparalleled sharpness and high-frequency details. The predictions are metric, with absolute scale, without relying on the availability of metadata such as camera intrinsics. And the model is fast, producing a 2.25-megapixel depth map in 0.3 seconds on a standard GPU. These characteristics are enabled by a number of technical contributions, including an efficient multi-scale vision transformer for dense prediction, a training protocol that combines real and synthetic datasets to achieve high metric accuracy alongside fine boundary tracing, dedicated evaluation metrics for boundary accuracy in estimated depth maps, and state-of-the-art focal length estimation from a single image. Extensive experiments analyze specific design choices and demonstrate that Depth Pro outperforms prior work along multiple dimensions. We release code and weights at https://github.com/apple/ml-depth-pro
hub tools
citation-role summary
background 4
baseline 2
method 2
citation-polarity summary
representative citing papers
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.
Authors create ReasonMatch-Bench and DCRL training to boost MLLM performance on wide-baseline matching, reporting gains over baselines while preserving general capabilities.
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.
WideDepth supplies the first millimeter-accurate indoor fisheye depth benchmark together with a stereo generation pipeline and model adaptation technique.
H-Flow learns dense human scene flow from monocular video via joint pose and depth prediction in a multi-head transformer, using physics-inspired geometric and biomechanical priors for self-supervision, and introduces the DynAct4D synthetic benchmark.
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.
AmbiSuR adds intrinsic photometric disambiguation and a self-indication module to Gaussian Splatting to resolve ambiguities and improve surface reconstruction accuracy.
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.
LAGRNet embeds learnable algebraic group, ring, and sheaf structures into a neural network to improve accuracy and generalization in 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.
A search-based algorithm achieves globally optimal pose estimation from silhouettes alone by querying precomputed area response surfaces and auxiliary ellipse aspect ratios for any shape.
3D-Fixer performs in-place 3D asset completion from single-view partial point clouds via coarse-to-fine generation with ORFA conditioning, plus a new ARSG-110K dataset, to achieve higher geometric accuracy than MIDI and Gen3DSR while keeping diffusion efficiency.
A semi-supervised framework distills vision foundation models into compact instance segmentation experts that outperform their teachers by up to 11.9 AP on Cityscapes and 8.6 AP on ADE20K while being 11 times smaller.
HairOrbit leverages video generation priors and a neural orientation extractor to achieve state-of-the-art strand-level 3D hair reconstruction from single-view portraits in visible and invisible regions.
Low-rank decoder adaptation enables efficient test-time optimization for zero-shot depth completion by updating only the subspace containing depth-relevant information.
Introduces the first publicly accessible native 4K resolution endoscopic video dataset for robotic-assisted minimally invasive procedures.
GuideDog supplies 22K egocentric image-description pairs from 46 countries and an 818-sample QA benchmark showing that current multimodal models still struggle with depth perception and BLV-specific guidance rules.
WaterGen decouples scene generation from medium degradation in a two-stage latent diffusion process to produce controllable realistic underwater images that improve downstream restoration and segmentation.
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.
Modality Forcing lets a single DiT produce image and depth outputs in any order after training on sparse real-world depth, with larger image-pretrained models yielding better depth accuracy and a 57% AbsRel reduction versus prior joint generative baselines.
A city-blind 3D isovist prediction model trained on Manhattan and Paris yields city identity linearly decodable from temporal latents above single-frame baselines.
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.
A depth estimation method using event camera with coded optics and IR projection, trained only on synthetic planar data, achieves 7cm accuracy up to 2.5m in real dark scenes for robot navigation.
citing papers explorer
-
Target-depth sensing with metasurface-encoder integrated optoelectronic neural network
A metasurface optical encoder compresses depth into 2D images for a shadow ResNet to achieve high accuracy in both target classification and depth estimation on MNIST and vehicle datasets.