MonoNeRF: Learning Generalizable NeRFs from Monocular Videos without Camera Pose
원문 초록
We propose a generalizable neural radiance fields - MonoNeRF, that can be trained on large-scale monocular videos of moving in static scenes without any ground-truth annotations of depth and camera poses. MonoNeRF follows an Autoencoder-based architecture, where the encoder estimates the monocular depth and the camera pose, and the decoder constructs a Multiplane NeRF representation based on the depth encoder feature, and renders the input frames with the estimated camera. The learning is supervised by the reconstruction error. Once the model is learned, it can be applied to multiple applications including depth estimation, camera pose estimation, and single-image novel view synthesis. More qualitative results are available at: https://oasisyang.github.io/mononerf .
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
$π^3$: Scalable Permutation-Equivariant Visual Geometry Learning
Reflections Unlock: Geometry-Aware Reflection Disentanglement in 3D Gaussian Splatting for Photorealistic Scenes Rendering
RA-NeRF: Robust Neural Radiance Field Reconstruction with Accurate Camera Pose Estimation under Complex Trajectories
Half-AVAE: Adversarial-Enhanced Factorized and Structured Encoder-Free VAE for Underdetermined Independent Component Analysis
Voyager: Long-Range and World-Consistent Video Diffusion for Explorable 3D Scene Generation
Uni-DVPS: Unified Model for Depth-Aware Video Panoptic Segmentation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.