activity
20242026
collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV2025

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…

cs.CV2025

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…

cs.CV2025

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…

cs.CV2025

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…

cs.CV2024

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…

cs.CV2024

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…