ES-MVSNet: Efficient Framework for End-to-end Self-supervised Multi-View Stereo
원문 초록
Compared to the multi-stage self-supervised multi-view stereo (MVS) method, the end-to-end (E2E) approach has received more attention due to its concise and efficient training pipeline. Recent E2E self-supervised MVS approaches have integrated third-party models (such as optical flow models, semantic segmentation models, NeRF models, etc.) to provide additional consistency constraints, which grows GPU memory consumption and complicates the model's structure and training pipeline. In this work, we propose an efficient framework for end-to-end self-supervised MVS, dubbed ES-MVSNet. To alleviate the high memory consumption of current E2E self-supervised MVS frameworks, we present a memory-efficient architecture that reduces memory usage by 43% without compromising model performance. Furthermore, with the novel design of asymmetric view selection policy and region-aware depth consistency, we achieve state-of-the-art performance among E2E self-supervised MVS methods, without relying on third-party models for additional consistency signals. Extensive experiments on DTU and Tanks&Temples benchmarks demonstrate that the proposed ES-MVSNet approach achieves state-of-the-art performance among E2E self-supervised MVS methods and competitive performance to many supervised and multi-stage self-supervised methods.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
DEARLi: Decoupled Enhancement of Recognition and Localization for Semi-supervised Panoptic Segmentation
HNOSeg-XS: Extremely Small Hartley Neural Operator for Efficient and Resolution-Robust 3D Image Segmentation
MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation
MUVOD: A Novel Multi-view Video Object Segmentation Dataset and A Benchmark for 3D Segmentation
ZS-VCOS: Zero-Shot Outperforms Supervised Video Camouflaged Object Segmentation with Zero-Shot Method
ERFNet: Efficient Residual Factorized ConvNet for Real-time Semantic Segmentation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.