46 citations · 54 across the 12 of their papers we have counts for
10 papers · 1 filter
BrickWright: Agentic Creation of Physically Feasible Brick Builds
Ava Pun, Kevin Dai, Sally Chen +7
Frontier coding agents are becoming increasingly adept at 3D modeling. Yet, they still face challenges when building objects meant to be assembled in the physical world, often crea…
Generating Physically Stable and Buildable Brick Structures from Text
Ava Pun, Kangle Deng, Ruixuan Liu +3
We introduce BrickGPT, the first approach for generating physically stable interconnecting brick assembly models from text prompts. To achieve this, we construct a large-scale, phy…
Efficient Autoregressive Shape Generation via Octree-Based Adaptive Tokenization
Kangle Deng, Hsueh-Ti Derek Liu, Yiheng Zhu +7
Many 3D generative models rely on variational autoencoders (VAEs) to learn compact shape representations. However, existing methods encode all shapes into a fixed-size token, disre…
Cube: A Roblox View of 3D Intelligence
Foundation AI Team, Kiran Bhat, Nishchaie Khanna +44
Foundation models trained on vast amounts of data have demonstrated remarkable reasoning and generation capabilities in the domains of text, images, audio and video. Our goal at Ro…
Tactile DreamFusion: Exploiting Tactile Sensing for 3D Generation
Ruihan Gao, Kangle Deng, Gengshan Yang +2
3D generation methods have shown visually compelling results powered by diffusion image priors. However, they often fail to produce realistic geometric details, resulting in overly…
MaterialFusion: Enhancing Inverse Rendering with Material Diffusion Priors
Yehonathan Litman, Or Patashnik, Kangle Deng +4
Recent works in inverse rendering have shown promise in using multi-view images of an object to recover shape, albedo, and materials. However, the recovered components often fail t…
Total-Recon: Deformable Scene Reconstruction for Embodied View Synthesis
Chonghyuk Song, Gengshan Yang, Kangle Deng +2
We explore the task of embodied view synthesis from monocular videos of deformable scenes. Given a minute-long RGBD video of people interacting with their pets, we render the scene…
3D-aware Conditional Image Synthesis
Kangle Deng, Gengshan Yang, Deva Ramanan +1
We propose pix2pix3D, a 3D-aware conditional generative model for controllable photorealistic image synthesis. Given a 2D label map, such as a segmentation or edge map, our model l…
Depth-supervised NeRF: Fewer Views and Faster Training for Free
Kangle Deng, Andrew Liu, Jun-Yan Zhu +1
A commonly observed failure mode of Neural Radiance Field (NeRF) is fitting incorrect geometries when given an insufficient number of input views. One potential reason is that stan…
Unsupervised Audiovisual Synthesis via Exemplar Autoencoders
Kangle Deng, Aayush Bansal, Deva Ramanan
We present an unsupervised approach that converts the input speech of any individual into audiovisual streams of potentially-infinitely many output speakers. Our approach builds on…