paper-with-me

Papers

BELM: Bidirectional Explicit Linear Multi-step Sampler for Exact Inversion in Diffusion Models

2024-10-09 · Fangyikang Wang, Hubery Yin, Yuejiang Dong, Huminhao Zhu, Chao Zhang, Hanbin Zhao, Hui Qian, Chen Li

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.

📄 PDF Abstract BibTeX arXiv:2410.07273

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

PRobELM: Plausibility Ranking Evaluation for Language Models

2024-04-04 · Zhangdie Yuan, Eric Chamoun, Rami Aly, Chenxi Whitehouse 외

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 Knowledge

Deep Dual Learning for Semantic Image Segmentation

2017-10-01 · ICCV 2017 10 · Ping Luo, Guangrun Wang, Liang Lin, Xiaogang Wang

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 Segmentation

BelMan: Bayesian Bandits on the Belief--Reward Manifold

2018-05-04 · Debabrota Basu, Pierre Senellart, Stéphane Bressan

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

2020-04-18 · Kuldeep Kulkarni, Tejas Gokhale, Rajhans Singh, Pavan Turaga 외

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 Segmentation

LABELMAKER: Automatic Semantic Label Generation from RGB-D Trajectories

2023-11-20 · Silvan Weder, Hermann Blum, Francis Engelmann, Marc Pollefeys

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