Pith. sign in

REVIEW 3 cited by

Isometric Representation Learning for Disentangled Latent Space of Diffusion Models

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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

arxiv 2407.11451 v1 pith:EXEP7SPB submitted 2024-07-16 cs.LG cs.CV

Jaehoon Hahm , Junho Lee , Sunghyun Kim , Joonseok Lee This is my paper · ORCID
classification cs.LGcs.CV
keywords spacelatentdiffusionimagemodelmodelsdisentangledisometric
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The latent space of diffusion model mostly still remains unexplored, despite its great success and potential in the field of generative modeling. In fact, the latent space of existing diffusion models are entangled, with a distorted mapping from its latent space to image space. To tackle this problem, we present Isometric Diffusion, equipping a diffusion model with a geometric regularizer to guide the model to learn a geometrically sound latent space of the training data manifold. This approach allows diffusion models to learn a more disentangled latent space, which enables smoother interpolation, more accurate inversion, and more precise control over attributes directly in the latent space. Our extensive experiments consisting of image interpolations, image inversions, and linear editing show the effectiveness of our method.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. SAEmnesia: Erasing Concepts in Diffusion Models with Supervised Sparse Autoencoders

    cs.CV 2025-09 conditional novelty 6.0 of 10

    A supervised sparse autoencoder binds each concept to a single neuron, letting Stable Diffusion erase a concept by steering one latent.

  2. SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders

    cs.LG 2025-01 conditional novelty 6.0 of 10

    SAeUron removes concepts from text-to-image diffusion models by ablating concept-specific sparse autoencoder features during inference, achieving state-of-the-art unlearning on UnlearnCanvas and I2P without weight updates.

  3. SC-Pro: Training-Free Framework for Defending Unsafe Image Synthesis Attack

    cs.CV 2025-01 conditional novelty 6.0 of 10

    A training-free voting defense, SC-Pro, detects adversarial NSFW prompts by checking images generated from perturbed inputs, with a distilled one-step variant for speed.

Pith tools