REVIEW 6 cited by
Truncated Diffusion Probabilistic Models and Diffusion-based Adversarial Auto-Encoders
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Employing a forward diffusion chain to gradually map the data to a noise distribution, diffusion-based generative models learn how to generate the data by inferring a reverse diffusion chain. However, this approach is slow and costly because it needs many forward and reverse steps. We propose a faster and cheaper approach that adds noise not until the data become pure random noise, but until they reach a hidden noisy data distribution that we can confidently learn. Then, we use fewer reverse steps to generate data by starting from this hidden distribution that is made similar to the noisy data. We reveal that the proposed model can be cast as an adversarial auto-encoder empowered by both the diffusion process and a learnable implicit prior. Experimental results show even with a significantly smaller number of reverse diffusion steps, the proposed truncated diffusion probabilistic models can provide consistent improvements over the non-truncated ones in terms of performance in both unconditional and text-guided image generations.
Forward citations
Cited by 6 Pith papers
-
A Generative Framework for Causal Estimation via Importance-Weighted Diffusion Distillation
IWDD distills a pretrained conditional diffusion model into a one-step generator using randomized treatment sampling, implicitly reweighting observational data for confounding bias and reducing gradient variance.
-
Ditto: Accelerating Diffusion Model via Temporal Value Similarity
Diffusion model inference can be accelerated by computing only the small differences between adjacent time steps, with reduced bit-width and zero-skipping, at moderate accuracy loss.
-
Few-Step Diffusion via Score identity Distillation
A few-step, largely data-free extension of Score identity Distillation reaches state-of-the-art FID and CLIP scores on SDXL at 1024x1024 with one or four generation steps.
-
Multi-scale Generative Modeling for Fast Sampling
WMGM generates 128x128 images by diffusing only low-frequency wavelet coefficients and using a shared multi-scale GAN to fill in high-frequency details, improving FID and cutting sampling time and parameters versus SG...
-
Efficient Difficulty-Aware Dynamic Routing for Diffusion-Based Real-World Image Super-Resolution
DDR-SR routes each real-world low-resolution image to one of two diffusion experts based on a high-frequency-loss difficulty score, using a low-compression VAE for hard images and a high-compression VAE for easy image...
-
Efficiency Meets Fidelity: A Novel Quantization Framework for Stable Diffusion
A serial-to-parallel distillation pipeline with per-timestep activation quantization makes W4A8 quantized Stable Diffusion models generate images much closer to the full-precision model than prior PTQ methods.
Discussion (0). Continue with ORCID to comment.