TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

3D Novel View Synthesis with Diffusion Models

106 pointsby dougabugover 2 years ago

7 comments

dougabugover 2 years ago
This approach is interesting in that it applies image-to-image diffusion modeling to autoregressively generate 3D consistent novel views, starting with even a single reference 2D image. Unlike some other approaches, a NeRF is not needed as an intermediate representation.
评论 #33093554 未加载
oifjsidjfover 2 years ago
&gt;&gt; In order to maximize the reproducibility of our results, we provide code in JAX (Bradbury et al., 2018) for our proposed X-UNet neural architecture from Section 2.3<p>Nice.<p>OpenAI shitting their pants even more.
评论 #33088290 未加载
raszover 2 years ago
This is one of the building blocks absolutely required for Full Self driving to ever work.<p>btw I like how it hallucinated bumper carrier mounted Spare Wheel based on the size of tires, heavy duty roof rack and bull bars while ground truth render was in a much less likely configuration of stock undercarriage frame hanger&#x2F;no spare.
mlajtosover 2 years ago
Ok, NeRFs were a distraction then.
评论 #33088329 未加载
dicknuckleover 2 years ago
I&#x27;m entirely unfamiliar with this, but is there a future where we can take a few pictures of something physical, and have AI generate a 3d model that we can then modify and 3d print?<p>Asking as someone who&#x27;s dreadfully slow at 3d modeling.
评论 #33091210 未加载
评论 #33090713 未加载
dr_dshivover 2 years ago
It seems like this be used to create multiple views for fine tuning Stable Diffusion (textual inversion), from a single image.
muschellij2over 2 years ago
Soon to be the Face Back APP!