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.
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.
39
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
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.
Decouples semantic and spatial tokens in NVS transformers to resolve representation ambiguity, yielding consistent gains with near-zero added latency.
DepthVLM converts a standard VLM into a dense metric depth predictor by attaching a lightweight head and training under unified vision-text supervision, outperforming prior VLMs and some pure vision models on a new indoor-outdoor benchmark.
MS-DePro achieves state-of-the-art performance on multi-source domain adaptation benchmarks for object detection by using depth-guided region proposals and multi-modal alignment of learnable text embeddings.
Clear2Fog generates realistic synthetic fog from clear scenes, enabling mixed-density training that outperforms full fixed-density data and improves real-world performance by 1.67 mAP after learning-rate adjustment.
GeoQuery replaces corrupted rendering features with geometry-aligned proxy queries and restricts cross-view attention to local windows, enabling robust diffusion-based refinement under extreme view sparsity.
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.
MLG-Stereo adds multi-granularity feature extraction, local-global cost volumes, and guided recurrent refinement to ViT stereo matching, yielding competitive results on Middlebury, KITTI-2015, and strong results on KITTI-2012.
A selective regularization framework lets scale-ambiguous monocular depth priors improve Gaussian Splatting geometry and rendering by isolating and supervising only ill-posed regions.
Marigold-SSD delivers zero-shot depth completion via single-step diffusion with late fusion, achieving fast inference after only 4.5 GPU days of training while showing strong cross-domain results on indoor and outdoor benchmarks.
Pixel-to-4D builds a dynamic 3D Gaussian representation from one image and samples object motion in a single forward pass to produce camera-controlled videos with claimed state-of-the-art quality and speed on KITTI, Waymo, RealEstate10K and DL3DV-10K.
DA3 recovers consistent visual geometry from arbitrary views via a vanilla DINO transformer and depth-ray target, setting new SOTA on a visual geometry benchmark while outperforming DA2 on monocular depth.
citing papers explorer
-
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.
-
Genie Sim PanoRecon: Fast Immersive Scene Generation from Single-View Panorama
A feed-forward Gaussian-splatting system reconstructs photo-realistic 3D scenes from single-view panoramas in seconds via cube-map decomposition and depth-aware fusion for robotic simulation use.