Learning Human Mesh Recovery in 3D Scenes
원문 초록
We present a novel method for recovering the absolute pose and shape of a human in a pre-scanned scene given a single image. Unlike previous methods that perform sceneaware mesh optimization, we propose to first estimate absolute position and dense scene contacts with a sparse 3D CNN, and later enhance a pretrained human mesh recovery network by cross-attention with the derived 3D scene cues. Joint learning on images and scene geometry enables our method to reduce the ambiguity caused by depth and occlusion, resulting in more reasonable global postures and contacts. Encoding scene-aware cues in the network also allows the proposed method to be optimization-free, and opens up the opportunity for real-time applications. The experiments show that the proposed network is capable of recovering accurate and physically-plausible meshes by a single forward pass and outperforms state-of-the-art methods in terms of both accuracy and speed.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
ADHMR: Aligning Diffusion-based Human Mesh Recovery via Direct Preference Optimization
Optimizing Local-Global Dependencies for Accurate 3D Human Pose Estimation
Utilizing Uncertainty in 2D Pose Detectors for Probabilistic 3D Human Mesh Recovery
ARTS: Semi-Analytical Regressor using Disentangled Skeletal Representations for Human Mesh Recovery from Videos
TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation
DPMesh: Exploiting Diffusion Prior for Occluded Human Mesh Recovery
토론
이 논문과 연결된 포럼 글이 아직 없습니다.