Publications (17)
From Thousands to Billions: 3D Visual Language Grounding via Render-Supervised Distillation from 2D VLMs
Ang Cao, Sergio Arnaud, Oleksandr Maksymets +12
3D vision-language grounding faces a fundamental data bottleneck: while 2D models train on billions of images, 3D models have access to only thousands of labeled scenes--a six-orde…
Meta 3D Gen
Raphael Bensadoun, Tom Monnier, Yanir Kleiman +17
We introduce Meta 3D Gen (3DGen), a new state-of-the-art, fast pipeline for text-to-3D asset generation. 3DGen offers 3D asset creation with high prompt fidelity and high-quality 3…
Lightplane: Highly-Scalable Components for Neural 3D Fields
Ang Cao, Justin Johnson, Andrea Vedaldi +1
Contemporary 3D research, particularly in reconstruction and generation, heavily relies on 2D images for inputs or supervision. However, current designs for these 2D-3D mapping are…
Inverting and Understanding Object Detectors
Ang Cao, Justin Johnson
As a core problem in computer vision, the performance of object detection has improved drastically in the past few years. Despite their impressive performance, object detectors suf…
EucliDreamer: Fast and High-Quality Texturing for 3D Models with Stable Diffusion Depth
Cindy Le, Congrui Hetang, Chendi Lin +2
This paper presents a novel method to generate textures for 3D models given text prompts and 3D meshes. Additional depth information is taken into account to perform the Score Dist…
Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Models
Lukas Höllein, Ang Cao, Andrew Owens +2
We present Text2Room, a method for generating room-scale textured 3D meshes from a given text prompt as input. To this end, we leverage pre-trained 2D text-to-image models to synth…
Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass
Jianing Yang, Alexander Sax, Kevin J. Liang +6
Multi-view 3D reconstruction remains a core challenge in computer vision, particularly in applications requiring accurate and scalable representations across diverse perspectives.…
MoE3D: A Mixture-of-Experts Module for 3D Reconstruction
Zichen Wang, Ang Cao, Liam J. Wang +1
We propose a simple yet effective approach to enhance the performance of feed-forward 3D reconstruction models. Existing methods often struggle near depth discontinuities, where st…
EucliDreamer: Fast and High-Quality Texturing for 3D Models with Depth-Conditioned Stable Diffusion
Cindy Le, Congrui Hetang, Chendi Lin +2
We present EucliDreamer, a simple and effective method to generate textures for 3D models given text prompts and meshes. The texture is parametrized as an implicit function on the…
Probing Visual Language Priors in VLMs
Tiange Luo, Ang Cao, Gunhee Lee +2
Despite recent advances in Vision-Language Models (VLMs), they may over-rely on visual language priors existing in their training data rather than true visual reasoning. To investi…
DreamGaussian4D: Generative 4D Gaussian Splatting
Jiawei Ren, Liang Pan, Jiaxiang Tang +4
4D content generation has achieved remarkable progress recently. However, existing methods suffer from long optimization times, a lack of motion controllability, and a low quality…
HexPlane: A Fast Representation for Dynamic Scenes
Ang Cao, Justin Johnson
Modeling and re-rendering dynamic 3D scenes is a challenging task in 3D vision. Prior approaches build on NeRF and rely on implicit representations. This is slow since it requires…
Unified Signal Compression Using Generative Adversarial Networks
Bowen Liu, Ang Cao, Hun-seok Kim
We propose a unified compression framework that uses generative adversarial networks (GAN) to compress image and speech signals. The compressed signal is represented by a latent ve…
Building a physics-aware AI ecosystem for solid-state hydrogen storage materials
Seong-Hoon Jang, Yiwen Yao, Chuanyu Liu +66
Hydrogen storage remains a central bottleneck for scalable hydrogen energy systems due to the multiscale and coupled nature of the thermodynamics, kinetics, and microstructural evo…
Locate 3D: Real-World Object Localization via Self-Supervised Learning in 3D
Sergio Arnaud, Paul McVay, Ada Martin +19
We present LOCATE 3D, a model for localizing objects in 3D scenes from referring expressions like "the small coffee table between the sofa and the lamp." LOCATE 3D sets a new state…
FWD: Real-time Novel View Synthesis with Forward Warping and Depth
Ang Cao, Chris Rockwell, Justin Johnson
Novel view synthesis (NVS) is a challenging task requiring systems to generate photorealistic images of scenes from new viewpoints, where both quality and speed are important for a…
Unified Signal Compression Using a GAN with Iterative Latent Representation Optimization
Bowen Liu, Changwoo Lee, Ang Cao +1
We propose a unified signal compression framework that uses a generative adversarial network (GAN) to compress heterogeneous signals. The compressed signal is represented as a late…