Goto

Collaborating Authors

 asshowninfig


DreamSteerer: EnhancingSourceImageConditioned EditabilityusingPersonalizedDiffusionModels

Neural Information Processing Systems

However, such a solution often shows unsatisfactory editability on the source image. To address this, we propose DreamSteerer, a plug-in method for augmenting existing T2I personalization methods. Specifically, we enhance the source image conditioned editability of a personalized diffusion model via a novel Editability Driven Score Distillation (EDSD) objective. Moreover, we identify amodetrapping issuewithEDSD, andpropose amodeshifting regularization with spatial feature guided sampling to avoid such an issue.







c573258c38d0a3919d8c1364053c45df-Paper-Conference.pdf

Neural Information Processing Systems

Various priors have been used to mitigate the ill-posedness of this problem, including geometric priors[5,6,30,44],referencepriors[24-26],andgenerativepriors[2,37,43].


UnifiedOptimalTransportFrameworkforUniversal DomainAdaptation (SupplementaryMaterial)

Neural Information Processing Systems

Recall measures the fraction ofcommon samples that are retrievedascorrect common class, while specificity measures thefraction ofprivatesamples thatarenotretrieved. Fig. S1(b) shows the sensitivity ofγ, where γ is the rough boundary for splitting positive and negative in adaptive filling. For the cosine similarity of two ℓ2-normalized features, the similarity value is limited from 1to1, where higher value indicates higher similarity. Suchself-supervisedlearning methods encourage the consistency between two augmentations of one image. The display images for source prototypes are chosen by finding the nearest source instance of the prototype.


IKEA-Manual: SeeingShapeAssemblyStepbyStep

Neural Information Processing Systems

Duetothe long-horizon nature ofthe task, we often heavily rely onvisual manuals that provide step-by-step guidance during the assembly process.