63 citations · 164 across the 6 of their papers we have counts for
6 papers
CausNVS: Autoregressive Multi-view Diffusion for Flexible 3D Novel View Synthesis
Xin Kong, Daniel Watson, Yannick Strümpler +2
Multi-view diffusion models have shown promise in 3D novel view synthesis, but most existing methods adopt a non-autoregressive formulation. This limits their applicability in worl…
Denoising Diffusion Probabilistic Models for Robust Image Super-Resolution in the Wild
Hshmat Sahak, Daniel Watson, Chitwan Saharia +1
Diffusion models have shown promising results on single-image super-resolution and other image- to-image translation tasks. Despite this success, they have not outperformed state-o…
Novel View Synthesis with Diffusion Models
Daniel Watson, William Chan, Ricardo Martin-Brualla +3
We present 3DiM, a diffusion model for 3D novel view synthesis, which is able to translate a single input view into consistent and sharp completions across many views. The core com…
Learning Fast Samplers for Diffusion Models by Differentiating Through Sample Quality
Daniel Watson, William Chan, Jonathan Ho +1
Diffusion models have emerged as an expressive family of generative models rivaling GANs in sample quality and autoregressive models in likelihood scores. Standard diffusion models…
Learning to Efficiently Sample from Diffusion Probabilistic Models
Daniel Watson, Jonathan Ho, Mohammad Norouzi +1
Denoising Diffusion Probabilistic Models (DDPMs) have emerged as a powerful family of generative models that can yield high-fidelity samples and competitive log-likelihoods across…
Utilizing Character and Word Embeddings for Text Normalization with Sequence-to-Sequence Models
Daniel Watson, Nasser Zalmout, Nizar Habash
Text normalization is an important enabling technology for several NLP tasks. Recently, neural-network-based approaches have outperformed well-established models in this task. Howe…