MOSAIC: Generating Consistent, Privacy-Preserving Scenes from Multiple Depth Views in Multi-Room Environments
원문 초록
We introduce a novel diffusion-based approach for generating privacy-preserving digital twins of multi-room indoor environments from depth images only. Central to our approach is a novel Multi-view Overlapped Scene Alignment with Implicit Consistency (MOSAIC) model that explicitly considers cross-view dependencies within the same scene in the probabilistic sense. MOSAIC operates through a novel inference-time optimization that avoids error accumulation common in sequential or single-room constraint in panorama-based approaches. MOSAIC scales to complex scenes with zero extra training and provably reduces the variance during denoising processes when more overlapping views are added, leading to improved generation quality. Experiments show that MOSAIC outperforms state-of-the-art baselines on image fidelity metrics in reconstructing complex multi-room environments. Project page is available at: https://mosaic-cmubig.github.io
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Leveraging the Spatial Hierarchy: Coarse-to-fine Trajectory Generation via Cascaded Hybrid Diffusion
On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning
Differentially Private Federated Low Rank Adaptation Beyond Fixed-Matrix
Domain Borders Are There to Be Crossed With Federated Few-Shot Adaptation
Geo-ORBIT: A Federated Digital Twin Framework for Scene-Adaptive Lane Geometry Detection
ScoreAdv: Score-based Targeted Generation of Natural Adversarial Examples via Diffusion Models
토론
이 논문과 연결된 포럼 글이 아직 없습니다.