BELM: Bidirectional Explicit Linear Multi-step Sampler for Exact Inversion in Diffusion Models
The inversion of diffusion model sampling, which aims to find the corresponding initial noise of a sample, plays a critical role in various tasks. Recently, several heuristic exact inversion samplers have been proposed to address the inexact inversion issue in a training-free manner. However, the theoretical properties of these heuristic samplers remain unknown and they often exhibit mediocre sampling quality. In this paper, we introduce a generic formulation, \emph{Bidirectional Explicit Linear Multi-step} (BELM) samplers, of the exact inversion samplers, which includes all previously proposed heuristic exact inversion samplers as special cases. The BELM formulation is derived from the variable-stepsize-variable-formula linear multi-step method via integrating a bidirectional explicit constraint. We highlight this bidirectional explicit constraint is the key of mathematically exact inversion. We systematically investigate the Local Truncation Error (LTE) within the BELM framework and show that the existing heuristic designs of exact inversion samplers yield sub-optimal LTE. Consequently, we propose the Optimal BELM (O-BELM) sampler through the LTE minimization approach. We conduct additional analysis to substantiate the theoretical stability and global convergence property of the proposed optimal sampler. Comprehensive experiments demonstrate our O-BELM sampler establishes the exact inversion property while achieving high-quality sampling. Additional experiments in image editing and image interpolation highlight the extensive potential of applying O-BELM in varying applications.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
PRobELM: Plausibility Ranking Evaluation for Language Models
This paper introduces PRobELM (Plausibility Ranking Evaluation for Language Models), a benchmark designed to assess language models' ability to discern more plausible from less plausible scenarios through their parametri…
Question AnsweringTruthfulQAWorld KnowledgeDeep Dual Learning for Semantic Image Segmentation
Deep neural networks have advanced many computer vision tasks, because of their compelling capacities to learn from large amount of labeled data. However, their performances are not fully exploited in semantic image segm…
Image SegmentationSemantic SegmentationBelMan: Bayesian Bandits on the Belief--Reward Manifold
We propose a generic, Bayesian, information geometric approach to the exploration--exploitation trade-off in multi-armed bandit problems. Our approach, BelMan, uniformly supports pure exploration, exploration--exploitati…
Halluci-Net: Scene Completion by Exploiting Object Co-occurrence Relationships
Recently, there has been substantial progress in image synthesis from semantic labelmaps. However, methods used for this task assume the availability of complete and unambiguous labelmaps, with instance boundaries of obj…
Image GenerationSemantic SegmentationLABELMAKER: Automatic Semantic Label Generation from RGB-D Trajectories
Semantic annotations are indispensable to train or evaluate perception models, yet very costly to acquire. This work introduces a fully automated 2D/3D labeling framework that, without any human intervention, can generat…
Neural RenderingSemantic Segmentation