GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors

• URL: http://arxiv.org/abs/2504.01016v1
• Date: Tue, 01 Apr 2025 17:58:03 GMT
• Title: GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors
• Authors: Tian-Xing Xu, Xiangjun Gao, Wenbo Hu, Xiaoyu Li, Song-Hai Zhang, Ying Shan,
• Abstract summary: We propose GeometryCrafter, a novel framework that recovers high-fidelity point map sequences with temporal coherence from open-world videos.<n>We show that GeometryCrafter achieves state-of-the-art 3D accuracy, temporal consistency, and generalization capability.
• Score: 47.21120442961684
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Despite remarkable advancements in video depth estimation, existing methods exhibit inherent limitations in achieving geometric fidelity through the affine-invariant predictions, limiting their applicability in reconstruction and other metrically grounded downstream tasks. We propose GeometryCrafter, a novel framework that recovers high-fidelity point map sequences with temporal coherence from open-world videos, enabling accurate 3D/4D reconstruction, camera parameter estimation, and other depth-based applications. At the core of our approach lies a point map Variational Autoencoder (VAE) that learns a latent space agnostic to video latent distributions for effective point map encoding and decoding. Leveraging the VAE, we train a video diffusion model to model the distribution of point map sequences conditioned on the input videos. Extensive evaluations on diverse datasets demonstrate that GeometryCrafter achieves state-of-the-art 3D accuracy, temporal consistency, and generalization capability.

Related papers

• CVCP-Fusion: On Implicit Depth Estimation for 3D Bounding Box Prediction [2.0375637582248136]
  Cross-View Center Point-Fusion is a state-of-the-art model to perform 3D object detection. Our architecture utilizes aspects from previously established algorithms, Cross-View Transformers and CenterPoint.
  arXiv  Detail & Related papers  (2024-10-15T02:55:07Z)
• DoubleTake: Geometry Guided Depth Estimation [17.464549832122714]
  Estimating depth from a sequence of posed RGB images is a fundamental computer vision task. We introduce a reconstruction which combines volume features with a hint of the prior geometry, rendered as a depth map from the current camera location. We demonstrate that our method can run at interactive speeds, state-of-the-art estimates of depth and 3D scene in both offline and incremental evaluation scenarios.
  arXiv  Detail & Related papers  (2024-06-26T14:29:05Z)
• COMO: Compact Mapping and Odometry [17.71754144808295]
  We present COMO, a real-time monocular mapping and odometry system that encodes dense geometry via a compact set of 3D anchor points. The representation enables joint optimization of camera poses and dense geometry, intrinsic 3D consistency, and efficient second-order inference.
  arXiv  Detail & Related papers  (2024-04-04T15:35:43Z)
• FrozenRecon: Pose-free 3D Scene Reconstruction with Frozen Depth Models [67.96827539201071]
  We propose a novel test-time optimization approach for 3D scene reconstruction. Our method achieves state-of-the-art cross-dataset reconstruction on five zero-shot testing datasets.
  arXiv  Detail & Related papers  (2023-08-10T17:55:02Z)
• AutoDecoding Latent 3D Diffusion Models [95.7279510847827]
  We present a novel approach to the generation of static and articulated 3D assets that has a 3D autodecoder at its core. The 3D autodecoder framework embeds properties learned from the target dataset in the latent space. We then identify the appropriate intermediate volumetric latent space, and introduce robust normalization and de-normalization operations.
  arXiv  Detail & Related papers  (2023-07-07T17:59:14Z)
• Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistency [114.02182755620784]
  We present an end-to-end joint training framework that explicitly models 6-DoF motion of multiple dynamic objects, ego-motion and depth in a monocular camera setup without supervision. Our framework is shown to outperform the state-of-the-art depth and motion estimation methods.
  arXiv  Detail & Related papers  (2021-02-04T14:26:42Z)
• Multi-view Depth Estimation using Epipolar Spatio-Temporal Networks [87.50632573601283]
  We present a novel method for multi-view depth estimation from a single video. Our method achieves temporally coherent depth estimation results by using a novel Epipolar Spatio-Temporal (EST) transformer. To reduce the computational cost, inspired by recent Mixture-of-Experts models, we design a compact hybrid network.
  arXiv  Detail & Related papers  (2020-11-26T04:04:21Z)
• Consistent Video Depth Estimation [57.712779457632024]
  We present an algorithm for reconstructing dense, geometrically consistent depth for all pixels in a monocular video. We leverage a conventional structure-from-motion reconstruction to establish geometric constraints on pixels in the video. Our algorithm is able to handle challenging hand-held captured input videos with a moderate degree of dynamic motion.
  arXiv  Detail & Related papers  (2020-04-30T17:59:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.