← Back to all news
arXiv Computer Vision By Marian Lupascu, Mihai-Sorin Stupariu, Wongi Park, Ionut Mironica

Stratified Multi-View Aggregation for Score Distillation

Read the original on arXiv Computer Vision →

The paper introduces Multi-View Aggregated Score Distillation (MV‑SDI), a training‑free sampler that replaces the single‑view per‑step gradient in score distillation with an average over K views while keeping the diffusion prior frozen. By averaging gradients from multiple views—especially antipodal pairs—MV‑SDI reduces per‑step variance by roughly 1/K, improves angular coverage, and cuts optimization steps while boosting CLIP R‑Precision and CLIP score on the SDI benchmark. The method achieves these gains without retraining or additional multi‑view data and is compatible with existing gradient‑based score‑distillation pipelines.

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 arXiv Computer Vision.

Related stories

Hugging Face Trending Papers
Jun 29

Variance Reduction on the Camera Axis: Multi-View Score Distillation for 3D

Score distillation turns a pretrained 2D diffusion model into a 3D generator, but the per-step gradient is estimated from a single randomly chosen view: it is high-variance and blind to global shape consistency. Prior work addresses this by retraining the diffusion prior on multi-view data; this improves consistency but makes the sampling contribution inseparable from prior quality.

diffusionefficiencybenchmarkssafety
More like this →
arXiv AI
Oct 28

A First-Step Bias Restores Lost Diversity in Diffusion Model Distillation

The paper introduces ReSeed, a lightweight post‑distillation technique that restores lost diversity in diffusion model distillation by adding a seed‑response bias adapter only to the first denoising step. By aligning the first step’s velocity with the teacher’s, ReSeed recovers most of the output diversity without altering later steps or adding target images. Experiments on SD3‑Medium, SD3.5‑Medium, FLUX.1‑dev, and Wan2.1‑T2V‑1.3B show a 48.3% increase in DINO diversity with negligible extra parameters and training data.

By Wenwu Tang, Dong Wang, Yun Cheng, Olga Saukh
diffusionfine-tuningefficiencysafety
More like this →
arXiv Machine Learning
Jul 14

BARD: Bridging AutoRegressive and Diffusion Vision-Language Models Via Highly Efficient Progressive Block Merging and Stage-Wise Distillation

arXiv:2604. 16514v5 Announce Type: replace-cross Abstract: Autoregressive vision-language models (VLMs) deliver strong multimodal capability, but their token-by-token decoding imposes a fundamental inference bottleneck.

By Baoyou Chen, Hanchen Xia, Peng Tu, Haojun Shi, Liwei Zhang, Yuxuan Yao, Weihao Yuan, Siyu Zhu
llmsdiffusionefficiencymultimodalbenchmarks
More like this →