Organizing the first NYC vision workshop was super fun! Shout out to other organizers Elliott / Shangzhe Wu Haian Jin and especially Noah Snavely for the generous support!

Made it to NeurIPS. I'd love to chat with anyone about computer vision or graphics or machine learning 🙂

#SIGGRAPHAsia2023 Combining Neural Fields with Monte Carlo methods can result in faster and more accurate PDE solvers. Come to see our talk tomorrow at 15:45pm. C4.8 (level 4). w Guandao Yang @ ICCV 🌺🌺🌺, Xi Deng, Christopher De Sa, Bharath Hariharan, Steve Marschner

I’m excited to share that this Fall I will start a PhD at MIT EECS, supported by the NSF Graduate Research Fellowship Program!

Announcing (fashionably late) our #CVPR2024 paper on GenAI detection! with Avneesh Sud, Thomas Leung, and Ben Usman Fake-Inversion: Learning to Detect Images from Unseen Models by Inverting Stable Diffusion fake-inversion.github.io More info in 🧵 1/7

The latent space of earlier generative models like GANS can linearly encode concepts of the data. What if the data was model weights? We present weights2weights, a subspace in diffusion weights that behaves as an interpretable latent space over customized diffusion models.

Introducing MegaScenes—a scene-level dataset containing 100K SfM reconstructions and 2M images with open content licenses. We validate its effectiveness in training large-scale, generalizable models on the task of novel view synthesis. 1/N project page: megascenes.github.io

Now accepted to #ECCV2024 🥳 CLIP shows emergent understanding of *visual-semantic hierarchies*. Our benchmark *HierarCaps* gives GT to measure and further align this! Work with Hadar Averbuch-Elor Project page: hierarcaps.github.io Paper: arxiv.org/abs/2407.08521 More info below👇1/5

We'll present "Neural Control Variates with Automatic Integration" at the Monte Carlo for PDE session in Mile High 4 at 11:25 tomorrow. Come to our talk to learn more about creating control variates function with arbitrary neural networks! #SIGGRAPH2024

Excited to share our work, ObjectCarver! Given multiview images and click points on one image, ObjectCarver decomposes scenes into separate objects, providing high-quality 3D surfaces while handling occlusion and close-contact objects. (1/6) website: objectcarver.github.io

Differentiable rendering made SIMPLE❗️ Differentiating physically based renderers is hard: Dirac-delta discontinuities arise at object silhouette. Our #SIGGRAPHAsia2024 work shows how a simple relaxation can rescue the day, enabling easy 3D reconstruction and relighting! (1/N)

Announcing Diffusion Forcing Transformer (DFoT), our new video diffusion algorithm that generates ultra-long videos of 800+ frames. DFoT enables History Guidance, a simple add-on to any existing video diffusion models for a quality boost. Website: boyuan.space/history-guidan… (1/7)

How can we use wide-FOV cameras for reconstruction? We propose self-calibration Gaussian Splatting that jointly optimizes camera parameters, lens distortion, and 3D Gaussian representations to directly reconstruct from a set of wide-angle captures. page: denghilbert.github.io/self-cali/

Come see our talk on "Pocket Time-Lapse" at SIGGRAPH today at 4pm in the Image Representation, Editing, & Generation session! West Building, Rooms 118-120. With Žiga Kovačič , Madhav Aggarwal and Abe Davis

When you think of “time-lapse video,” what usually springs to mind is a camera fixed on a tripod taking image after image at predetermined intervals. But what if you could do the same thing by taking out your phone and snapping a picture every time you walk past a certain tree