Towards 3D Scene Reconstruction from Locally Scale-Aligned Monocular Video Depth
원문 초록
Existing monocular depth estimation methods have achieved excellent robustness in diverse scenes, but they can only retrieve affine-invariant depth, up to an unknown scale and shift. However, in some video-based scenarios such as video depth estimation and 3D scene reconstruction from a video, the unknown scale and shift residing in per-frame prediction may cause the depth inconsistency. To solve this problem, we propose a locally weighted linear regression method to recover the scale and shift with very sparse anchor points, which ensures the scale consistency along consecutive frames. Extensive experiments show that our method can boost the performance of existing state-of-the-art approaches by 50% at most over several zero-shot benchmarks. Besides, we merge over 6.3 million RGBD images to train strong and robust depth models. Our produced ResNet50-backbone model even outperforms the state-of-the-art DPT ViT-Large model. Combining with geometry-based reconstruction methods, we formulate a new dense 3D scene reconstruction pipeline, which benefits from both the scale consistency of sparse points and the robustness of monocular methods. By performing the simple per-frame prediction over a video, the accurate 3D scene shape can be recovered.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
DEPTHOR: Depth Enhancement from a Practical Light-Weight dToF Sensor and RGB Image
SHADeS: Self-supervised Monocular Depth Estimation Through Non-Lambertian Image Decomposition
BadDepth: Backdoor Attacks Against Monocular Depth Estimation in the Physical World
Depth Anything with Any Prior
Deep Neural Networks for Accurate Depth Estimation with Latent Space Features
MonoMVSNet: Monocular Priors Guided Multi-View Stereo Network
토론
이 논문과 연결된 포럼 글이 아직 없습니다.