Hugging Face Trending Papers August 13, 2026

PixSDS: Why Latent SDS Makes Noisy Pixels

Read the original on Hugging Face Trending Papers →

Score Distillation Sampling (SDS) enables text-to-3D generation by optimizing rendered images with a pretrained diffusion prior, but latent SDS often produces structured color artifacts and high-frequency texture noise. We identify a failure mode of latent SDS caused by VAE-induced pixel drift: the optimized image can move along pixel-space directions that are weakly constrained by the VAE encoder, so its latent representation remains clean and semantically meaningful while the image itself accumulates visible artifacts.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at Hugging Face Trending Papers.

Hugging Face Trending Papers

Aug 17

PixRestore: Unified Image Restoration via Pixel Diffusion Transformer

Unified image restoration (UIR) aims to recover high-quality (HQ) content from low-quality (LQ) images with different degradations using a single model. Most recent methods adapt large pretrained text-to-image (T2I) latent diffusion models for their strong capacity and generative priors.

llms diffusion benchmarks safety

arXiv Computer Vision

Sep 1

Discrete Diffusion Bridges for Spatiotemporally Aligned Image Translation and Generation

arXiv:2608.29997v1 Announce Type: new Abstract: We propose Discrete Diffusion Bridges (DDB), a novel framework designed to resolve the fundamental spatiotemporal misalignment of standard discrete dif...

By Xing Xie, Jiawei Liu, Shijun Zhou, Huijie Fan, Zhi Han, Yandong Tang, Liangqiong Qu

diffusion robotics safety

arXiv Computer Vision

3d ago

Rethinking Generative Image Compression at Extremely Low Bitrates

The paper introduces RAE-CoD, a diffusion-based compression method that operates in a representation autoencoder space to preserve recognizable content even at extremely low bitrates. It addresses the problem of semantic collapse observed in existing codecs when the bitrate approaches zero, showing that reconstruction losses conflict with semantic objectives and that VAE diffusion models lose efficiency in preserving semantics. Experiments on MSCOCO-30K demonstrate that RAE-CoD outperforms competitors, reducing VFM feature MSE and Fréchet Distance ratios by at least 25.7% and 69.1% at 0.001–0.008 bpp while maintaining stable recognizability and quality.

By Tianyu Zhang, Zhaoyang Jia, Houqiang Li, Dong Liu

llms diffusion multimodal safety

arXiv AI

Aug 6

AdaCorrection: Adaptive Offset Cache Correction for Accurate Diffusion Transformers

arXiv:2602. 13357v3 Announce Type: replace-cross Abstract: Diffusion Transformers (DiTs) achieve state-of-the-art performance in high-fidelity image and video generation but suffer from expensive inference due to their iterative denoising structure.

By Dong Liu, Yanxuan Yu, Ben Lengerich, Ying Nian Wu

llms diffusion benchmarks

Hugging Face Trending Papers

Jun 1

Exploiting Semantic and Pixel Representations for Ultra-Low Bitrate Image Compression

Most existing extreme compression methods fail to achieve an optimal rate-distortion-perception trade-off, as they typically prioritize perceptual fidelity and visual realism over pixel-level accuracy. Consequently, the resulting reconstructions often deviate noticeably from the originals.

diffusion benchmarks

arXiv Machine Learning

Aug 4

FDIR: Harmonizing Fidelity and Human-Machine Preference in Lossy Compression Image Restoration

arXiv:2608. 00111v1 Announce Type: cross Abstract: Image restoration quality can be evaluated along three complementary facets: pixel-level fidelity, human perception, and downstream machine preference.

By Kuan-Yen Chen, Fang-Yi Su, Philip Chikontwe, Jung-Hsien Chiang

diffusion safety