REVIEW 11 cited by
DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos
read the original abstract
Estimating video depth in open-world scenarios is challenging due to the diversity of videos in appearance, content motion, camera movement, and length. We present DepthCrafter, an innovative method for generating temporally consistent long depth sequences with intricate details for open-world videos, without requiring any supplementary information such as camera poses or optical flow. The generalization ability to open-world videos is achieved by training the video-to-depth model from a pre-trained image-to-video diffusion model, through our meticulously designed three-stage training strategy. Our training approach enables the model to generate depth sequences with variable lengths at one time, up to 110 frames, and harvest both precise depth details and rich content diversity from realistic and synthetic datasets. We also propose an inference strategy that can process extremely long videos through segment-wise estimation and seamless stitching. Comprehensive evaluations on multiple datasets reveal that DepthCrafter achieves state-of-the-art performance in open-world video depth estimation under zero-shot settings. Furthermore, DepthCrafter facilitates various downstream applications, including depth-based visual effects and conditional video generation.
Forward citations
Cited by 11 Pith papers
-
Forget, Anticipate and Adapt: Test Time Training for Long Videos
FFN enables efficient TTT for long videos by operating on three frames and using a surprise-based adaptive window, shown on a new dataset of up to 3-hour videos for segmentation and classification tasks.
-
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.
-
Forget, Anticipate and Adapt: Test Time Training for Long Videos
FFN performs TTT on multi-hour videos by restricting updates to three frames and using a surprise metric for adaptive window sizing, plus a new EpicTours dataset.
-
Stabilizing Streaming Video Geometry via Dynamic Feature Normalization
DyFN is a lightweight recurrent module that dynamically normalizes latent feature statistics to remove scale-shift drift and achieve state-of-the-art temporal consistency in streaming monocular geometry estimation whi...
-
Radar-Guided Polynomial Fitting for Metric Depth Estimation
POLAR converts scaleless monocular depth maps to metric scale via radar-guided polynomial fitting and first-derivative regularization, claiming 24.9% MAE and 33.2% RMSE gains over prior methods on three datasets.
-
DissolveStereo: Coarse Depth Injection for Zero-Shot Stereo Video Generation
DissolveStereo injects coarse dissolved depth maps into video diffusion latents via noisy restart and iterative refinement to produce temporally coherent stereo videos zero-shot.
-
ZipDepth: Bringing Lightweight Zero-Shot Monocular Depth Anywhere, on Any Device
A 6.1M-parameter monocular depth network, distilled from Depth Anything v2-Large over 14.1M multi-domain images, achieves the best zero-shot accuracy–efficiency trade-off among lightweight models across five benchmark...
-
Towards Consistent Video Geometry Estimation
ViGeo is a feed-forward transformer for video geometry that introduces dynamic chunking attention and a completion-based data refinement framework to achieve SOTA on depth, normals, and point map estimation.
-
WildPose: A Unified Framework for Robust Pose Estimation in the Wild
WildPose unifies feedforward 3D features from MASt3R with differentiable bundle adjustment for robust monocular pose estimation across dynamic, static, and low-ego-motion scenes.
-
Geometry-aware 4D Video Generation for Robot Manipulation
A geometry-aware 4D video generation model trained with cross-view pointmap alignment to produce spatio-temporally consistent future videos from novel viewpoints for robot manipulation.
-
MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion
By fine-tuning DUST3R to output per-timestep pointmaps on scarce dynamic video datasets, MonST3R achieves stronger video depth and pose estimation without explicit motion modeling.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.